diff --git "a/data/validation-00000.jsonl" "b/data/validation-00000.jsonl" new file mode 100644--- /dev/null +++ "b/data/validation-00000.jsonl" @@ -0,0 +1,1000 @@ +{"id": "val_00000", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "repo_scale_reasoning", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f4830c28ad83d0e531b80e84c65db402503101c7"} +{"id": "val_00001", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "evaluation_metrics", "ci_integration"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "244169bebccaabe3d8e94ba33132d8ef6a43569c"} +{"id": "val_00002", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "ci_integration", "auditability", "governance"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "367fd52289a15748a68acc7ca439c3c19bbb6b89"} +{"id": "val_00003", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "tooling", "ci_integration"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0350711c692d7c946eaf453f9a58001db6d4bc00"} +{"id": "val_00004", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "documentation", "security_gates", "auditability"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5802a0f98c087a0c20648ae2ed809b286c4ee5f1"} +{"id": "val_00005", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "auditability", "tests_are_truth", "governance"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0b02f779d3922a9d384cf7c8d6b89983a90ee316"} +{"id": "val_00006", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["governance", "tooling", "auditability", "ci_integration"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "be18e824328be64f6d94f96e9b21839d1f4e9cd3"} +{"id": "val_00007", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["documentation", "security_gates", "ci_integration", "governance"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c407232f486ee1d91866f59f3ad7d7f54eb21dd2"} +{"id": "val_00008", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "ci_integration", "reproducibility", "tooling"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "357289dedfa6831c79c6292d23e8bae32d210085"} +{"id": "val_00009", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "governance", "tooling", "documentation"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d9665f28a65d85a551b46cfbf47cc59f7340ad64"} +{"id": "val_00010", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["governance", "reproducibility", "evaluation_metrics", "tooling"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cbf4a4f463c5a7b3539328f37105ca6a4e6ec51c"} +{"id": "val_00011", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "governance", "auditability", "documentation"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2df2afeab1a7cbef82e7ef032aa28ed3db2f4338"} +{"id": "val_00012", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "governance", "reproducibility", "cost_latency_tradeoffs"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c424773423074c1467bbf1a6e6b9ef3461dc4057"} +{"id": "val_00013", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "evaluation_metrics", "governance", "ci_integration"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "68264a28806318a15ee3ce721b431a1d49444f3d"} +{"id": "val_00014", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "evaluation_metrics", "reproducibility"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "59fe9c3e7f2c9199aa61963c34b286138160862b"} +{"id": "val_00015", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "security_gates", "tests_are_truth", "governance"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "13c24bf7557a0d2b5ba2d48edd4249d135d424eb"} +{"id": "val_00016", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["auditability", "repo_scale_reasoning", "governance", "documentation"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ccdc9fd397e9189af5524c891ad92a12b04e59dc"} +{"id": "val_00017", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["tooling", "governance", "auditability", "documentation"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1810842f2863aa6374f62d33b74fbc69216a6a5c"} +{"id": "val_00018", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "security_gates", "reproducibility", "tests_are_truth"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d2af80b7c7ecc6ef04facbb64f0c04e017175147"} +{"id": "val_00019", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "auditability", "governance", "tests_are_truth"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "229ce157193cfd82efe56f041f4f43959db010d0"} +{"id": "val_00020", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "repo_scale_reasoning", "ci_integration", "tooling"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5a9239f603172f422530eff83215e19bdcf1a7aa"} +{"id": "val_00021", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "ci_integration", "cost_latency_tradeoffs", "evaluation_metrics"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ef257f193ef93ba6817239ad9d878c20be489346"} +{"id": "val_00022", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["evaluation_metrics", "cost_latency_tradeoffs", "reproducibility", "governance"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3738671ead2fbfbdc65ab3ca601bb39977d512d6"} +{"id": "val_00023", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "reproducibility", "evaluation_metrics", "tooling"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a37899ddb5cf4ab6753e3f3a825bac14ba385c16"} +{"id": "val_00024", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "auditability", "evaluation_metrics", "cost_latency_tradeoffs"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "517dbab6e178c3290a7fc429109a1919253f48fe"} +{"id": "val_00025", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["evaluation_metrics", "ci_integration", "security_gates", "cost_latency_tradeoffs"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d707a47ff334a25d25c2d69d9759b0bf2a02c9fd"} +{"id": "val_00026", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "reproducibility", "governance", "tests_are_truth"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "16f1aae8b61c63bd128fdd67143605c505a3fddf"} +{"id": "val_00027", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "ci_integration", "tests_are_truth", "documentation"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "863d0add4b2ae3a37a6000480da2d2bb3fdbb666"} +{"id": "val_00028", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "evaluation_metrics", "auditability"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fc4a975065360a9c89d6041e487fec3620c4f09c"} +{"id": "val_00029", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["auditability", "repo_scale_reasoning", "cost_latency_tradeoffs", "tests_are_truth"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2f1913e04a3a5701046b362d3b107d9278804a98"} +{"id": "val_00030", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "evaluation_metrics", "ci_integration", "tooling"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "27d328cdfba109b1eeb8efbf4dc565b177bd0fc6"} +{"id": "val_00031", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "cost_latency_tradeoffs", "tests_are_truth", "ci_integration"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bef22da4a720ac02205eb9a657029fb14580090e"} +{"id": "val_00032", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "tooling", "security_gates"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9fc4c972f6947b22f0ea020c685962b04f7b406a"} +{"id": "val_00033", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "ci_integration", "security_gates", "governance"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "383e777deec5ba948a0bc7df7700a5551d91925c"} +{"id": "val_00034", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "evaluation_metrics", "tooling", "documentation"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0201feb751ef8426db71c8b00cce6e688d33ddbf"} +{"id": "val_00035", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "cost_latency_tradeoffs", "tooling", "security_gates"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e3424a71bfdd07d575f26e86218a3f477209a94f"} +{"id": "val_00036", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tooling", "cost_latency_tradeoffs", "ci_integration", "tests_are_truth"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c62e4a27f2e8ce6aafd39b3452bfd97ef65fcd96"} +{"id": "val_00037", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "tooling", "evaluation_metrics"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0d55e57563a7f2b8e9a13df9aba20ce75cc80e27"} +{"id": "val_00038", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "governance", "auditability", "cost_latency_tradeoffs"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "417005f437c0c6dad4f359e90b637de1fed9e44c"} +{"id": "val_00039", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "evaluation_metrics", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "34fc08b5225bcf93d5e964cde131913aa1df4f06"} +{"id": "val_00040", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nScaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=4):\n history = []\n p = plan(issue)\n for _ in range(max_iters):\n patch = edit(issue, p)\n ok, report = test(patch)\n history.append({\"plan\": p, \"ok\": ok})\n if ok:\n return patch, history\n p = p + \" | refine\"\n return patch, history\n\n```\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "reproducibility", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9ce17238cb4e00d87940a904e4d5646f0b416a25"} +{"id": "val_00041", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "cost_latency_tradeoffs", "security_gates", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "82671206827793e1fd765d879f63e1eeb24a2dfc"} +{"id": "val_00042", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["documentation", "security_gates", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f00da9594f3e5f1360450074e4123c8b970b774e"} +{"id": "val_00043", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "tests_are_truth", "security_gates"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "78df32db1cb8d459d516e4b21b826bc2cf0a3dfa"} +{"id": "val_00044", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "tooling", "documentation", "governance"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7550deb1cc5f93e94e368506ec81e522ab055690"} +{"id": "val_00045", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["reproducibility", "tests_are_truth", "security_gates", "governance"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1125592db3f66599ee8dc948478911307c916c01"} +{"id": "val_00046", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "cost_latency_tradeoffs", "governance", "ci_integration"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5f07998ae30140753035f8235ba1ce7dbb811ca3"} +{"id": "val_00047", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "documentation", "evaluation_metrics", "reproducibility"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "544e455dceac3e1f075717b2401f2870fd857f69"} +{"id": "val_00048", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "tests_are_truth", "ci_integration", "governance"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b36b526b1c8612e913afa8273d0f83c95fb6087a"} +{"id": "val_00049", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "security_gates", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "eb622528085ff0131c5a9a87d726b98a3c9ae79a"} +{"id": "val_00050", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["ci_integration", "cost_latency_tradeoffs", "governance", "evaluation_metrics"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ab3de36494a4d82daf4d80ca33e4811e515eb43e"} +{"id": "val_00051", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["tooling", "ci_integration", "cost_latency_tradeoffs", "documentation"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1792a90830716f1873cf0297874af708ce6d93de"} +{"id": "val_00052", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "auditability", "governance", "tooling"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e09f9fc44c103463794cee723a1eb39424fae2f7"} +{"id": "val_00053", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["governance", "cost_latency_tradeoffs", "ci_integration", "tooling"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0a859652b0e69c0cc65ad848a841ccdffffe25c3"} +{"id": "val_00054", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["documentation", "evaluation_metrics", "repo_scale_reasoning", "auditability"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9099a2502621d5d6bafbd5df04cc86e4791c0f11"} +{"id": "val_00055", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "evaluation_metrics", "ci_integration", "documentation"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e37905028b64951e5f1fffc110755a26d96421e0"} +{"id": "val_00056", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["auditability", "security_gates", "documentation", "governance"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9ed7e24fbf054de36059c3e7fc06ae443fdb70b8"} +{"id": "val_00057", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "evaluation_metrics", "tests_are_truth", "documentation"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "73e0bc61a90f00e4635b2dbb5e974eb9efb5bf56"} +{"id": "val_00058", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["documentation", "tests_are_truth", "tooling", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ac523aa8af9cd5e753cac9b4ae5180128a5bb647"} +{"id": "val_00059", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "ci_integration", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "250f06c6bf91e9f25e0d926d9f40b82fe57a74fd"} +{"id": "val_00060", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["governance", "ci_integration", "documentation", "cost_latency_tradeoffs"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "88af51de11a7be725f59b57137f4456c8d415bd5"} +{"id": "val_00061", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "cost_latency_tradeoffs", "documentation", "ci_integration"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9b26c774a268f08d03b1c7aa72f4dc0da86ed668"} +{"id": "val_00062", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "tests_are_truth", "governance", "repo_scale_reasoning"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "50dad75fc1edde2a40c14df7aa5c321dc2de22c0"} +{"id": "val_00063", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "reproducibility", "tests_are_truth", "tooling"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3e422c2d9c30e4b095b53f7353ac4f24ac8b3600"} +{"id": "val_00064", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "tooling", "reproducibility", "tests_are_truth"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4ced0cd42a9eac9f8927f2f26aa127945904fe79"} +{"id": "val_00065", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["cost_latency_tradeoffs", "documentation", "reproducibility", "governance"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "369f8476612a04791f506b5300e7041e2f749506"} +{"id": "val_00066", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "evaluation_metrics", "documentation", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "113049b74ac122ee8f84a0e2aff49f59179b5cd2"} +{"id": "val_00067", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["governance", "security_gates", "reproducibility", "tooling"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c46bf7619015e4ffa107dcf8c65bf84568396743"} +{"id": "val_00068", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "tooling", "security_gates", "cost_latency_tradeoffs"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b4be97a35f487479b7880fda326a10d0e139d004"} +{"id": "val_00069", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tests_are_truth", "reproducibility", "governance", "documentation"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "be2d4397aecbf5d27859c1379174952851d3f508"} +{"id": "val_00070", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "governance", "evaluation_metrics", "auditability"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1d0ee659d3afdacd8926114c3c56ef0c800e17e1"} +{"id": "val_00071", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "auditability", "evaluation_metrics", "tooling"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "00e99b4f16944ada6bdc673d9256972ea7ddb926"} +{"id": "val_00072", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "repo_scale_reasoning", "ci_integration"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a944281425809492f1cf167373156382b931abe6"} +{"id": "val_00073", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "tooling", "repo_scale_reasoning", "cost_latency_tradeoffs"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7aadf648dc7e729cd50163930bc4cd7b35282497"} +{"id": "val_00074", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "ci_integration", "reproducibility"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1325363ea5f946858a59daae1d96794f600cc898"} +{"id": "val_00075", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "ci_integration", "governance", "tooling"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "22367942ebd91115ff1df5cda1a3c1af6f57e7f1"} +{"id": "val_00076", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["cost_latency_tradeoffs", "governance", "security_gates", "tests_are_truth"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "757cf394289043792c3830f0aee58d717299bdcc"} +{"id": "val_00077", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "documentation", "governance", "tooling"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4db7783313f95d8bd2040986d8b42976f6565391"} +{"id": "val_00078", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "repo_scale_reasoning", "tests_are_truth", "documentation"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "731a295a8a178fe203abb59800e92c3bdaa43174"} +{"id": "val_00079", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "governance", "ci_integration", "reproducibility"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1d57b5392c1611bc37b5673825f1c37ab4e54922"} +{"id": "val_00080", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "governance", "security_gates", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "896a3d5983d31bd026ee0ff14ffe8ba1bc6da6fd"} +{"id": "val_00081", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["cost_latency_tradeoffs", "documentation", "tests_are_truth", "auditability"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "57ed91f171a46301c23b6d89c5ebdd45ebfe4ef2"} +{"id": "val_00082", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "repo_scale_reasoning", "evaluation_metrics", "documentation"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cb5c4eb8c65c5a55f49644b39ca214111559b9f1"} +{"id": "val_00083", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "tests_are_truth", "tooling", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9e2c3b5240c0ec9727b42508ab715f23f23a136c"} +{"id": "val_00084", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "security_gates", "documentation", "evaluation_metrics"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e73c15097e408b300bea1c7bba1647e7a3af5392"} +{"id": "val_00085", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "ci_integration", "governance", "tooling"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ea8a235f197e0ab16d75ca79821a794019b6423c"} +{"id": "val_00086", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tests_are_truth", "evaluation_metrics", "reproducibility", "security_gates"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9bb915b0610119ae27845b79bf266482a222de95"} +{"id": "val_00087", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "tests_are_truth", "repo_scale_reasoning", "cost_latency_tradeoffs"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "448d4f1704488a2753638bf9ff67781f36406cd6"} +{"id": "val_00088", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "governance", "security_gates", "ci_integration"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bc7c5098010985719c7e703cfac5cdf1d9bf3800"} +{"id": "val_00089", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "governance", "repo_scale_reasoning", "evaluation_metrics"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "058fe2ec8bcd61067d2f13ec42e5b01ffb9415f1"} +{"id": "val_00090", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["evaluation_metrics", "tooling", "auditability", "ci_integration"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "27574483c0e3f5f3c221a07971897e65bd207d47"} +{"id": "val_00091", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["governance", "ci_integration", "reproducibility", "evaluation_metrics"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "67c6e43020f548ec9e3225f47b69e68678bd1f88"} +{"id": "val_00092", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "tooling", "cost_latency_tradeoffs", "auditability"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "33b89348338c3fd76334ecb77f5f7680b3a40239"} +{"id": "val_00093", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "governance", "security_gates", "reproducibility"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f972ce0152b5990ad24dad02c9290ca41a804fc9"} +{"id": "val_00094", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "documentation", "repo_scale_reasoning", "ci_integration"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9e710542c8b62c3458649e92fbc74c225395ac13"} +{"id": "val_00095", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["auditability", "reproducibility", "governance", "tooling"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a21e406d6e5741ccf08b709070207f2108d66bdd"} +{"id": "val_00096", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "auditability", "evaluation_metrics", "documentation"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1330e0ac71028d4d99e8b72ca4f2518d12394158"} +{"id": "val_00097", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["tests_are_truth", "documentation", "cost_latency_tradeoffs", "reproducibility"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f4e86774c325aea2a354e6f1a40bb41e49b6350d"} +{"id": "val_00098", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nScaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=4):\n history = []\n p = plan(issue)\n for _ in range(max_iters):\n patch = edit(issue, p)\n ok, report = test(patch)\n history.append({\"plan\": p, \"ok\": ok})\n if ok:\n return patch, history\n p = p + \" | refine\"\n return patch, history\n\n```\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "repo_scale_reasoning", "cost_latency_tradeoffs", "tests_are_truth"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a997f5cf481d7854f8369e7669bda42f57edc0c3"} +{"id": "val_00099", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["auditability", "security_gates", "evaluation_metrics", "governance"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5503e99466b1698a760ff586e987822312b0bd5a"} +{"id": "val_00100", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tests_are_truth", "ci_integration", "tooling", "reproducibility"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c702830f27a0f4b564406364989b9fb9e201ae83"} +{"id": "val_00101", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["documentation", "evaluation_metrics", "tooling", "cost_latency_tradeoffs"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "02c1ffebfff5c97b1efb71334dad4cb2d5b4d865"} +{"id": "val_00102", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["governance", "ci_integration", "repo_scale_reasoning", "documentation"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fc6802aa050f3c2df011b995af0b277535b79fda"} +{"id": "val_00103", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["tooling", "ci_integration", "documentation", "evaluation_metrics"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bf94109358a5c5f7c731210c9c6b7ef39c2aa4b6"} +{"id": "val_00104", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "governance", "repo_scale_reasoning", "documentation"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8db12cd953c49b44b029bb19790680b06cd45bf8"} +{"id": "val_00105", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["governance", "cost_latency_tradeoffs", "tests_are_truth", "ci_integration"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7587c5b0ec9bb3ccb00b1b844292aa6dd238e4e0"} +{"id": "val_00106", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "reproducibility", "auditability"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0421f35663dcb0136d9a77e05272a7ab56ba2207"} +{"id": "val_00107", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "security_gates", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bd2a7d54895639a8782da3f59c094d1aac9077de"} +{"id": "val_00108", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "cost_latency_tradeoffs", "documentation", "ci_integration"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d0347aed9169f6eeb25640e99dc03a8bb5801656"} +{"id": "val_00109", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["governance", "repo_scale_reasoning", "evaluation_metrics", "tooling"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "165c815b06bfa31ddc74ae029a0627ea5b3a324d"} +{"id": "val_00110", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "governance", "tests_are_truth", "cost_latency_tradeoffs"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "785542d7df6fbe55dd2cf65af085b4fb6ce01140"} +{"id": "val_00111", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "reproducibility", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6a9515829db3f650484e3d856e28924cf5aa6e25"} +{"id": "val_00112", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["reproducibility", "repo_scale_reasoning", "governance", "tooling"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "afdd3b82d923895fc27dd3f1f8385ede9ef6bd44"} +{"id": "val_00113", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "evaluation_metrics", "documentation"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a5601366bfdf46bdd7c9fbca11c8e4200aba0616"} +{"id": "val_00114", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["tooling", "auditability", "documentation", "ci_integration"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8aeda6cbb39d71687b6bdcb7e169201a7533334b"} +{"id": "val_00115", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "security_gates", "auditability", "tests_are_truth"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "02bbd351d685048a1e645d3f8dcc28e10cb8e18c"} +{"id": "val_00116", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["governance", "documentation", "repo_scale_reasoning", "security_gates"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d8d6d0ff963cec8d8e0dd1615ed6f6026df66815"} +{"id": "val_00117", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "auditability", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c8feeaac072d085827743926e9f89406122237a9"} +{"id": "val_00118", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["auditability", "repo_scale_reasoning", "security_gates", "ci_integration"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e86f732d8d677d1022034b58c77390195a5d0b19"} +{"id": "val_00119", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "tests_are_truth", "ci_integration", "governance"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "639a838b19a932b08c25d10fb5c0f3239017d1c7"} +{"id": "val_00120", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "auditability", "cost_latency_tradeoffs", "tooling"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b0215e77a5cd5015376203717084857944507021"} +{"id": "val_00121", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "evaluation_metrics", "auditability", "tests_are_truth"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7381b00502c7d4e519a5cafef2ac1ca70fa9e41e"} +{"id": "val_00122", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "security_gates", "evaluation_metrics", "governance"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b49df7a7c521b798d3af2cc6a3a195e8493ff802"} +{"id": "val_00123", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["documentation", "security_gates", "tooling", "ci_integration"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9cebfac8c7601310c3580e936e5619ab433727dc"} +{"id": "val_00124", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "ci_integration", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "67779841d1881753f16ed530d7f45ea92e0d3493"} +{"id": "val_00125", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["evaluation_metrics", "security_gates", "governance", "reproducibility"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d1e62de3b7371aa23799b339bd52b1606da66954"} +{"id": "val_00126", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "tests_are_truth", "tooling", "ci_integration"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "102b5b7a247c6185580f3764257368202ab17ad4"} +{"id": "val_00127", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["documentation", "repo_scale_reasoning", "tooling", "reproducibility"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "877ce1a5a3dba96fc1ce4b602e5008fbf061bc46"} +{"id": "val_00128", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["reproducibility", "tests_are_truth", "cost_latency_tradeoffs", "security_gates"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "47a45c3bbe827362d434b8f7b20406e1e74d2737"} +{"id": "val_00129", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "governance", "ci_integration", "cost_latency_tradeoffs"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2a8059d65ec871c8ce867448582dff6cc89b8571"} +{"id": "val_00130", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "repo_scale_reasoning", "auditability", "documentation"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7471989bc81435145ac9620ec2850bebea228ec0"} +{"id": "val_00131", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["governance", "evaluation_metrics", "cost_latency_tradeoffs", "auditability"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "40177e3f1fa0dfab430fc79465c42fb7fb554007"} +{"id": "val_00132", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "evaluation_metrics", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "40f8d017ae7a95b019184d268dcdcf2d426441c6"} +{"id": "val_00133", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "documentation", "tests_are_truth", "tooling"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f6f2ddb21203fb57a814a907dee642bfdb02891b"} +{"id": "val_00134", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["ci_integration", "tooling", "security_gates", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b3b8450566ee90251006d274fde99839b0e07b3b"} +{"id": "val_00135", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["tests_are_truth", "reproducibility", "auditability", "governance"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6061700c7b21f59048ae32530f6b0406b66322af"} +{"id": "val_00136", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "documentation", "auditability", "reproducibility"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c11dfbc7b389a87d89eeefaba429e1f0e60a616e"} +{"id": "val_00137", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "documentation", "security_gates", "tooling"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1d4ec445ff4eb880877408461c9bedc459b50b75"} +{"id": "val_00138", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "ci_integration", "reproducibility", "tests_are_truth"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "699f7fb3b77e989c6d3fb751243333bc52cff1e9"} +{"id": "val_00139", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "evaluation_metrics", "auditability", "tests_are_truth"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "185284ab2592cb6b45be08f6b31ee63522a47b86"} +{"id": "val_00140", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "tooling", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b6b2927c385d5258018c9605374c072a4f68ffa3"} +{"id": "val_00141", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "documentation", "evaluation_metrics", "tooling"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b95a29768738c549a16f0d6e83db1b77a3a013e9"} +{"id": "val_00142", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nScaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=4):\n history = []\n p = plan(issue)\n for _ in range(max_iters):\n patch = edit(issue, p)\n ok, report = test(patch)\n history.append({\"plan\": p, \"ok\": ok})\n if ok:\n return patch, history\n p = p + \" | refine\"\n return patch, history\n\n```\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "reproducibility", "cost_latency_tradeoffs", "tooling"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4f5fcc9f67f01bb1865969c558c283a2a29687dd"} +{"id": "val_00143", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "security_gates", "repo_scale_reasoning", "documentation"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "079cefc92567c85c26d1d61b7903b0abd9d5d5da"} +{"id": "val_00144", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "evaluation_metrics", "cost_latency_tradeoffs", "auditability"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5ac1f8eac9e60a79dbb51f0d34e168247719f89d"} +{"id": "val_00145", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["tests_are_truth", "reproducibility", "tooling", "cost_latency_tradeoffs"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6a2899339895c2700638f0fa48e938cecf062da2"} +{"id": "val_00146", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["governance", "evaluation_metrics", "repo_scale_reasoning", "documentation"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "46bd3eafbf8adf6d0e5ba6e39cd6f0e7e0d79311"} +{"id": "val_00147", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["governance", "tests_are_truth", "reproducibility", "documentation"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b62f9cf18b5ffb2182f8559ed1ba35eed72637a6"} +{"id": "val_00148", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "governance", "documentation", "tooling"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6dc61b7829a9f5074aec158e20e817f99a0b554d"} +{"id": "val_00149", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "repo_scale_reasoning", "governance", "documentation"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e3310479a7f3dc342ed8c36e1b2d4b82644bb188"} +{"id": "val_00150", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["tests_are_truth", "security_gates", "documentation", "evaluation_metrics"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7e59645475f3ed9608d6fe900b90dc0bfbfefd90"} +{"id": "val_00151", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "tooling", "reproducibility", "security_gates"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1d72872900be1160437eef7dd4bd6a9ccef48e12"} +{"id": "val_00152", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "cost_latency_tradeoffs", "evaluation_metrics", "reproducibility"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9818ed9375dbf0e364af8ba8c8f43cd6eecb1ef2"} +{"id": "val_00153", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "tooling", "reproducibility"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "07ed27097fba57a0f15f7c1c572bba75602b0621"} +{"id": "val_00154", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "tests_are_truth", "ci_integration", "governance"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "927c897e967378eb884fa3176182387a0db84d57"} +{"id": "val_00155", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "repo_scale_reasoning", "evaluation_metrics", "documentation"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9851eb4b6ce909e82704cdfb39868f1f3e4cf184"} +{"id": "val_00156", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["governance", "security_gates", "evaluation_metrics", "auditability"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8291588bda31045f8ff9ae83761ca48621e6ff0b"} +{"id": "val_00157", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "reproducibility", "tests_are_truth", "documentation"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0e8e31749d19358df370009266c32ebbc55dcbc5"} +{"id": "val_00158", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tests_are_truth", "security_gates", "cost_latency_tradeoffs", "governance"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "939ce7ecd64b6b8010d0b8bd42bec849d41ddb64"} +{"id": "val_00159", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "auditability", "tooling", "tests_are_truth"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9c87b53dc83ac7b9ddf4638aab7712973d8236cc"} +{"id": "val_00160", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "ci_integration", "tests_are_truth", "governance"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a736c28a4a1c15bcaf15a28476793ce7c449cf2f"} +{"id": "val_00161", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "governance", "cost_latency_tradeoffs", "documentation"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b4fd83a756d23be0ea909dd7efe40f3af4abaa8f"} +{"id": "val_00162", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "auditability", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "07f1acb6348612acf2aac4ff8cf46354ea324c24"} +{"id": "val_00163", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["governance", "tooling", "ci_integration", "documentation"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1da6829e74bd2905ebbc9e07cac10bea77397601"} +{"id": "val_00164", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["tests_are_truth", "repo_scale_reasoning", "tooling", "auditability"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3aee3fe66a451b3bb784e10b3a5c7723a93bfbe7"} +{"id": "val_00165", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "tooling", "repo_scale_reasoning", "auditability"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f2ac60b6fe7de8e00d557d4ab273cb40f680d3be"} +{"id": "val_00166", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "tooling", "governance", "auditability"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "839ed65cdbc1c25dbcedf60101d9b1ed87f68857"} +{"id": "val_00167", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["documentation", "auditability", "governance", "evaluation_metrics"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d189466cb4029e394c33a666b184c828705c2c4b"} +{"id": "val_00168", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "reproducibility", "ci_integration"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "924f3fee9b63dfe3c5bdcbdf44b7dd8f14bd29a2"} +{"id": "val_00169", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "repo_scale_reasoning", "auditability"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c14b70e181baab5e3b7af8a552dcd1cabdac0143"} +{"id": "val_00170", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "evaluation_metrics", "tests_are_truth", "reproducibility"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2e0ab5be59d6582f32a7e10c0234693d5c14f532"} +{"id": "val_00171", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["security_gates", "repo_scale_reasoning", "tooling", "auditability"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d3a3fc8639b4060a23920254a9813e94569fa0b9"} +{"id": "val_00172", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "auditability", "repo_scale_reasoning", "cost_latency_tradeoffs"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fc7f6ee73f5af258aca64fd245ef0a17a68cc421"} +{"id": "val_00173", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["documentation", "ci_integration", "evaluation_metrics", "tests_are_truth"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7f18c5554fc1b0dbd3a8cb6518c162def4da8b1b"} +{"id": "val_00174", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "repo_scale_reasoning", "tooling", "auditability"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e4c08fcfed1d42236b874b767f4dcc73ec369154"} +{"id": "val_00175", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "reproducibility", "repo_scale_reasoning", "documentation"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ea0e6eb9ce9ec2e5aada129f0d832eaa9d97a287"} +{"id": "val_00176", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["auditability", "cost_latency_tradeoffs", "tests_are_truth", "governance"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "488a0b3281011bf8533f7ac504b32219d2da5bd4"} +{"id": "val_00177", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "ci_integration", "reproducibility", "cost_latency_tradeoffs"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3d08f6910a230c511728705f0a54f0c516932c73"} +{"id": "val_00178", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["evaluation_metrics", "tests_are_truth", "documentation", "tooling"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "aab1785c13f555db4314f6718fa59f40a9a691a4"} +{"id": "val_00179", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["evaluation_metrics", "reproducibility", "repo_scale_reasoning", "governance"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7fb53b304994a1e7327b4d6c9d0b403e161190fc"} +{"id": "val_00180", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "tests_are_truth", "security_gates", "tooling"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "dba8452eafbb660ddf0bf35eb15f5bc593401054"} +{"id": "val_00181", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "documentation", "auditability", "governance"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d6bf647af8b637ec37b15a701e1c97a4d8c09a15"} +{"id": "val_00182", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["documentation", "cost_latency_tradeoffs", "tests_are_truth", "governance"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3e44c8cdf9dbf638d9de5131683f9a92d4fa88d7"} +{"id": "val_00183", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "reproducibility", "documentation", "ci_integration"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b38e71edd49bf689024f9180e26482c54894ad5a"} +{"id": "val_00184", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "auditability", "cost_latency_tradeoffs", "tests_are_truth"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bcf01333d0275f7837f48f1e66bb4aef993bd08d"} +{"id": "val_00185", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "cost_latency_tradeoffs", "governance", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "dc437405fcc457f1de769a4b9b5a42004727b5d1"} +{"id": "val_00186", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "cost_latency_tradeoffs", "security_gates", "tests_are_truth"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4a214d75b27326e37a45e963669b6ddfe43d2c72"} +{"id": "val_00187", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "ci_integration", "tests_are_truth"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4241c9ec8490360fc8eb770c7121903f7e2cdb62"} +{"id": "val_00188", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["auditability", "documentation", "evaluation_metrics", "governance"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "384f650b4c0b7cf79bc8201078187fe5b3c061d1"} +{"id": "val_00189", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "security_gates", "repo_scale_reasoning", "ci_integration"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bd080ecae3014e0ac3c0c951b1f8f322a908fcdd"} +{"id": "val_00190", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["security_gates", "repo_scale_reasoning", "tooling", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "474cde69a8a2b4b68089ca03d490b2de09017ae3"} +{"id": "val_00191", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "tooling", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0d26c4399a52eb6878cfd2ee399d9695365c7535"} +{"id": "val_00192", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "evaluation_metrics", "repo_scale_reasoning", "auditability"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4c5cc823c6893235f796cc8a06cbe9e477912310"} +{"id": "val_00193", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "governance", "security_gates"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3789740d6ad21228e75e7ba29797474437549b7c"} +{"id": "val_00194", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "documentation", "repo_scale_reasoning", "tooling"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0f53be0b5288d2a747575a5b78eafa08dcd53a47"} +{"id": "val_00195", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "auditability", "reproducibility", "security_gates"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c36ccc361340199c12229ea1de440b87573d0c1f"} +{"id": "val_00196", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "tooling", "evaluation_metrics"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cf463183c10e8e6137d6343d10b358aab1f534a6"} +{"id": "val_00197", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["governance", "tooling", "tests_are_truth", "documentation"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f46c44527e18fbcbc2e7329ab64186baf28c8e39"} +{"id": "val_00198", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "ci_integration", "tooling", "security_gates"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "124535f824ad81f48e045b67f918d703e6a1921f"} +{"id": "val_00199", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "reproducibility", "cost_latency_tradeoffs", "governance"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "38a8070ff1ab065240c2411c7923b523bd2d7f2a"} +{"id": "val_00200", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "documentation", "evaluation_metrics", "tests_are_truth"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "234056a10b479c701c24918edbd23453d9a856c0"} +{"id": "val_00201", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "tooling", "documentation", "governance"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e70d1e540ba2b6b449e70087020d28188f75e6fd"} +{"id": "val_00202", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "evaluation_metrics", "auditability", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b0e68631065654b259e69c195790834cdca7ce0a"} +{"id": "val_00203", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["ci_integration", "documentation", "auditability", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3f80d7373d273fbab80b7aace57b44d2d5056bec"} +{"id": "val_00204", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["ci_integration", "auditability", "evaluation_metrics", "documentation"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "54de4d6d318669347357ff35cc9bb08e6b74df20"} +{"id": "val_00205", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "reproducibility", "evaluation_metrics", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e6d4d9624e7ef93c8e56b827cce84e12e0cdbea5"} +{"id": "val_00206", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "evaluation_metrics", "reproducibility", "ci_integration"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8ad94c56f8f25543c8c097aab0a020d5720e70fb"} +{"id": "val_00207", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["governance", "repo_scale_reasoning", "ci_integration", "auditability"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3f7d58ab5c7f67a3642d2753dc8b140d5a881522"} +{"id": "val_00208", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["governance", "security_gates", "tests_are_truth", "ci_integration"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "688f1968888b00e5f0a72ee413721db650527232"} +{"id": "val_00209", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "ci_integration", "cost_latency_tradeoffs", "documentation"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "24dbfd66ca72b915cefeb62ea0b6fbf2bc90d60f"} +{"id": "val_00210", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["tooling", "evaluation_metrics", "reproducibility", "auditability"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0cc582385ff569c0f8e90dca0f97474c48be578f"} +{"id": "val_00211", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "security_gates", "cost_latency_tradeoffs", "tests_are_truth"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "734353c31339a2f6b647dfeb947348399abf7a15"} +{"id": "val_00212", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nScaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=4):\n history = []\n p = plan(issue)\n for _ in range(max_iters):\n patch = edit(issue, p)\n ok, report = test(patch)\n history.append({\"plan\": p, \"ok\": ok})\n if ok:\n return patch, history\n p = p + \" | refine\"\n return patch, history\n\n```\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "ci_integration", "tests_are_truth", "documentation"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a7ba571297cc2c6a5eff1191042c16d14d116d70"} +{"id": "val_00213", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "repo_scale_reasoning", "cost_latency_tradeoffs", "governance"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cca2cd25801f553288fc75720688d046f9916be5"} +{"id": "val_00214", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "ci_integration", "tooling", "security_gates"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "674441381cafdd9eba6c85fc9615cb742703eafb"} +{"id": "val_00215", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["tooling", "security_gates", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a3df3afa142d49d861a56572212e6fed3098d16f"} +{"id": "val_00216", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "repo_scale_reasoning", "tooling"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f002bd5bbf4b5d23ce872a3c126bd918041cbfac"} +{"id": "val_00217", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "tooling", "evaluation_metrics", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "eb4163661b4ff4a8ae307f6e7179dab34305a33b"} +{"id": "val_00218", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "ci_integration", "repo_scale_reasoning", "security_gates"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "33b6625a93fa9cfffd685109aba4c4a4a72e3f65"} +{"id": "val_00219", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "ci_integration", "reproducibility"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d22ff3bddee5641239767c1bce3e3df0dde489d0"} +{"id": "val_00220", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["repo_scale_reasoning", "evaluation_metrics", "tooling", "security_gates"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c4d70c3494b2cf0c929137834d23a699420d2219"} +{"id": "val_00221", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "ci_integration", "tests_are_truth", "auditability"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fcd1187348b74fb3ae9b23e70733c1f8964865de"} +{"id": "val_00222", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "documentation", "security_gates", "evaluation_metrics"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e8750b697a845315552380f221b7ae1cb0b6bf63"} +{"id": "val_00223", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "reproducibility", "tests_are_truth", "ci_integration"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "01acca79c311d8e27ff3e8b691741895fb3456bd"} +{"id": "val_00224", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "evaluation_metrics", "governance", "tests_are_truth"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "882ae4b3377b757213526467641bc4f8a6c3c2e3"} +{"id": "val_00225", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "tooling", "ci_integration", "reproducibility"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "91b22f68ea9214948e39b262402a5fd4cb89458b"} +{"id": "val_00226", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["ci_integration", "tooling", "evaluation_metrics", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b76447f282f1d2af20893a68a1fb46280050e0c7"} +{"id": "val_00227", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "tests_are_truth", "documentation", "tooling"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "43b50ace4a02c8c99073670fd750b47f0c3d2003"} +{"id": "val_00228", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["evaluation_metrics", "tests_are_truth", "repo_scale_reasoning", "governance"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b816f638eb13275815128b5016dd595be1ffd932"} +{"id": "val_00229", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["documentation", "reproducibility", "tests_are_truth", "auditability"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9e4f7fccbdb4f47a970d351968dff4e680f606c7"} +{"id": "val_00230", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "reproducibility", "evaluation_metrics", "documentation"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a03a09131207a259825c6b5571702a9d8881ba78"} +{"id": "val_00231", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["governance", "tooling", "reproducibility", "cost_latency_tradeoffs"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b05037d5a7a20ac0963583682be30bd150e3fa94"} +{"id": "val_00232", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["tooling", "tests_are_truth", "governance", "ci_integration"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "42cebae9e9a4e2ad964b02b088226946635465a1"} +{"id": "val_00233", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "ci_integration", "documentation"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "dede9eba7d2283e8eb936d62b3fb96733cf8a97b"} +{"id": "val_00234", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "auditability", "cost_latency_tradeoffs"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "805b14b77384f5335439c592990e522a3c39fe97"} +{"id": "val_00235", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "cost_latency_tradeoffs", "reproducibility", "security_gates"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9084b6c775307071cdb5221110460985bee2343b"} +{"id": "val_00236", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "evaluation_metrics", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7f05a3da4f0ecd0be6971bddb5076b89d1a4cc65"} +{"id": "val_00237", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["governance", "security_gates", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0f159440d4cb7886c81408b24d9b208a660afbd7"} +{"id": "val_00238", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "cost_latency_tradeoffs", "evaluation_metrics", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3116112577e5a11525babf39da9d90b0d750838c"} +{"id": "val_00239", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "tests_are_truth", "repo_scale_reasoning", "cost_latency_tradeoffs"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "458dd9a67482154c63dc272ed7d90cd1832b1e2d"} +{"id": "val_00240", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "tests_are_truth", "security_gates", "reproducibility"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b970e5694ac346f3af910b118a6b8a77aa4db3f0"} +{"id": "val_00241", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["governance", "reproducibility", "security_gates", "ci_integration"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2ee67da0889bc608d3dcf71f95e54ded1776c668"} +{"id": "val_00242", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["documentation", "repo_scale_reasoning", "governance", "evaluation_metrics"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2f74327d38c0553aaa711c20a4672044c5567985"} +{"id": "val_00243", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["governance", "auditability", "cost_latency_tradeoffs", "reproducibility"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "735d42deff201e7d1daa7c1aa90cd77db472e235"} +{"id": "val_00244", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["documentation", "auditability", "governance", "cost_latency_tradeoffs"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "65a03680d08dbfbe8e8ab25c368180ecb7c4a962"} +{"id": "val_00245", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["auditability", "documentation", "tests_are_truth", "reproducibility"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "da982dd89d00c925d967c326b89c969622cd4ab5"} +{"id": "val_00246", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "governance", "repo_scale_reasoning", "tooling"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cb019b4ea967f9082d0729eef2eb040de32615dd"} +{"id": "val_00247", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "governance", "cost_latency_tradeoffs", "tests_are_truth"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2b1fa6fcf05720be52c2c8fdcd3bdc34f49ed982"} +{"id": "val_00248", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "documentation", "ci_integration", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ab6bb6f093d69eea3d951a6e92a2b9e4697956c0"} +{"id": "val_00249", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "governance", "security_gates", "documentation"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "41fba1e297c75d4a443fd5a944b6e8a2b1d4d5b7"} +{"id": "val_00250", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "auditability", "ci_integration", "tests_are_truth"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c94b16ce36e1f579d4fff16241ec784e8dd552fd"} +{"id": "val_00251", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "governance", "security_gates"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e9a1d71ea8f44dbf8b6b81a611809fcc5243f2ca"} +{"id": "val_00252", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "reproducibility", "governance", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f8b275459e9d048374e19bf8b53126c889036d41"} +{"id": "val_00253", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "documentation", "ci_integration", "tooling"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d8ea2754c64d0e94c5d044120d3222c0b48e2724"} +{"id": "val_00254", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["tooling", "cost_latency_tradeoffs", "tests_are_truth", "security_gates"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1d2978aa5e18f15e6e368caf8a6aac010f77a16c"} +{"id": "val_00255", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "security_gates", "tooling", "cost_latency_tradeoffs"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "46edf4dca9073c7bbcdc47c82aaea37f56484d03"} +{"id": "val_00256", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "ci_integration", "evaluation_metrics"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "93b7be84c69047d9f2a045db0db123ab3c1f59f9"} +{"id": "val_00257", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "documentation", "reproducibility", "cost_latency_tradeoffs"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e22fea428835534d1a0460d139d1198319a3f46b"} +{"id": "val_00258", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "repo_scale_reasoning", "tests_are_truth", "cost_latency_tradeoffs"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1de1ed78407d2b0edcdfe52d32103af5ed357c85"} +{"id": "val_00259", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["auditability", "security_gates", "documentation", "reproducibility"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0acf90a6e78e2d052b707034f451dbed77b4d863"} +{"id": "val_00260", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "documentation", "tooling", "tests_are_truth"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "371c854032ce9913c12980b2183520809243f0a0"} +{"id": "val_00261", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "tests_are_truth", "governance", "security_gates"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fd68868ed678ad6f3c6d043bfc28efd60631f2ff"} +{"id": "val_00262", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "evaluation_metrics", "security_gates"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "12fe1d0a85373b8fc52d2aa1ac44736924633daa"} +{"id": "val_00263", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "auditability", "governance"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "19ba6400121632d90c792214e9deacc81d1b35ea"} +{"id": "val_00264", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tooling", "reproducibility", "ci_integration", "auditability"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3ab3b3a1491ae549d06f0dd66b93645a1e26add0"} +{"id": "val_00265", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "documentation", "tests_are_truth", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "36ccf8d160aa32177598b80e43ede6e05e6543cc"} +{"id": "val_00266", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "security_gates", "evaluation_metrics", "documentation"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bea488ce503408c5723cbb2e00cc07e8d8789cb2"} +{"id": "val_00267", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["tooling", "ci_integration", "tests_are_truth", "repo_scale_reasoning"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "965780648d89ab462b2664f9209e51d9bf9dc194"} +{"id": "val_00268", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "evaluation_metrics", "cost_latency_tradeoffs", "auditability"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "56847a90fe8b0ff8b828121106d97092690082d7"} +{"id": "val_00269", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "tooling", "tests_are_truth", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f6cf70e7fcc72db905824e58a4b23edf1d19cd0f"} +{"id": "val_00270", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["auditability", "cost_latency_tradeoffs", "tooling", "evaluation_metrics"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a6f1679ace860b7a2ebfd00625f65d40c033aa7a"} +{"id": "val_00271", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["governance", "ci_integration", "security_gates", "repo_scale_reasoning"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f705a7b44f9f6ce2ee10ca837ad9b029ec86c883"} +{"id": "val_00272", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "tooling", "repo_scale_reasoning", "ci_integration"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4860d2a55e8363dbb9677be537ea3ce266985a75"} +{"id": "val_00273", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "documentation", "auditability", "governance"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "64697bf40bd97dab151d6ece41c16e1932128c8d"} +{"id": "val_00274", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["auditability", "evaluation_metrics", "documentation", "reproducibility"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2ca410e5c81e7ae7912d15d01d838e0ee541e0a0"} +{"id": "val_00275", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["ci_integration", "evaluation_metrics", "repo_scale_reasoning", "reproducibility"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b32617d58afe2471ba508c2c4c42cbc7ae84521d"} +{"id": "val_00276", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["repo_scale_reasoning", "auditability", "governance", "evaluation_metrics"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fb53e937d8ac08d2ca312bd6af26492082048cae"} +{"id": "val_00277", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "governance", "evaluation_metrics", "security_gates"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "dc807745add7eeef1f9b016c3a827eef32f36323"} +{"id": "val_00278", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["tests_are_truth", "governance", "security_gates", "evaluation_metrics"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3f9d7c6231418dc32a092a3460a61b6e8eabb66c"} +{"id": "val_00279", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "tooling", "security_gates", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "16791bbb3017908aa7221f9d97a896d3e425ef46"} +{"id": "val_00280", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["auditability", "cost_latency_tradeoffs", "evaluation_metrics", "tests_are_truth"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b013bbb18c29d13436738b7720fd53bdca30b2c0"} +{"id": "val_00281", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "tooling", "reproducibility", "governance"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2d3587d3deed4a1eea26a8b68521be2df9554419"} +{"id": "val_00282", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["auditability", "reproducibility", "documentation", "ci_integration"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "381355bc057458fe524e37c2c5b19a73b8f753df"} +{"id": "val_00283", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "documentation", "security_gates", "tests_are_truth"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "924c0507fefd78e67bbeb637fe30641f2901735e"} +{"id": "val_00284", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["governance", "tooling", "reproducibility", "ci_integration"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9764f7df1f04d8594188d37e837d54d34ce002e3"} +{"id": "val_00285", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["governance", "documentation", "ci_integration", "repo_scale_reasoning"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3017b9f9d984cffbdd090feaebc00ba1141f9bbb"} +{"id": "val_00286", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "reproducibility", "ci_integration", "documentation"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5136f4f035e7c487a4433fb55c0a8f969fa82ae1"} +{"id": "val_00287", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "evaluation_metrics", "ci_integration", "reproducibility"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ad5673c2a037a8fd3b012788a3d668ecc4f5557f"} +{"id": "val_00288", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "documentation", "security_gates", "repo_scale_reasoning"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "15c103ba376755d289d36fc591c533f4dcc1bc49"} +{"id": "val_00289", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "ci_integration", "cost_latency_tradeoffs", "security_gates"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b681a4d9b7d344dc803b47ff444043aeadffc417"} +{"id": "val_00290", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "repo_scale_reasoning", "cost_latency_tradeoffs", "evaluation_metrics"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6221f43a55a77ae8f9a9554ee8801e98d21a9a3c"} +{"id": "val_00291", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tests_are_truth", "repo_scale_reasoning", "tooling", "reproducibility"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fcd7a6a2991d14aa21e5bd3fd430a6636447dd7a"} +{"id": "val_00292", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "ci_integration", "security_gates"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "df27f4657e34dfacc0474e5b954aa35a69285cce"} +{"id": "val_00293", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "security_gates", "auditability", "tests_are_truth"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e8632f4c3f15680d7dc192e6ac7324cdbfb292dc"} +{"id": "val_00294", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "cost_latency_tradeoffs", "tests_are_truth", "security_gates"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bf87db71ac275f0a11264a686d137232e0129873"} +{"id": "val_00295", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["documentation", "governance", "cost_latency_tradeoffs", "security_gates"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bdb4665545b056d0f661047ed8a57d11a95f1665"} +{"id": "val_00296", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "tooling", "documentation"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6535039a9979d1abdc06edc144bb1cca657cb369"} +{"id": "val_00297", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "security_gates", "tooling", "reproducibility"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6213f495734277a4cb1738aa4368ec51ae3ef25e"} +{"id": "val_00298", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "auditability", "reproducibility", "documentation"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cdaf4f130b6c41ac5b63b6c9cb7d011203074173"} +{"id": "val_00299", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["governance", "tooling", "security_gates", "reproducibility"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ddca09243334266497561e55fb424bceb4a5be64"} +{"id": "val_00300", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "security_gates", "governance", "tests_are_truth"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0e795f9a3367fd4946d466ae55ca9ce6310f740b"} +{"id": "val_00301", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "reproducibility", "tooling"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e2c3f2470fa08b6d52f36f6f984895192e3b1a67"} +{"id": "val_00302", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "repo_scale_reasoning", "governance"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3b7672280615747da4e3db98013964fd7c3c8b83"} +{"id": "val_00303", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "reproducibility", "security_gates", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9ba815c0491400b8e1125c957607e254de810918"} +{"id": "val_00304", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["ci_integration", "tests_are_truth", "evaluation_metrics", "documentation"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "19fe0f03f14f31aa0c8e6e3b04d6d3d94bf23535"} +{"id": "val_00305", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "documentation", "auditability", "evaluation_metrics"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "50933541e70ebf4446d31d20efc2c0533ebca47e"} +{"id": "val_00306", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["cost_latency_tradeoffs", "tests_are_truth", "reproducibility", "security_gates"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8587b24e6c2f45855c38f0718960a31ff6a435c9"} +{"id": "val_00307", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "tests_are_truth", "repo_scale_reasoning", "governance"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a54b8aea89c0f329eaf952431aaf509db525b320"} +{"id": "val_00308", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "cost_latency_tradeoffs", "tooling", "governance"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "93b81b9fcfa5157e691f7968e6e59bc15064916d"} +{"id": "val_00309", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tooling", "governance", "auditability", "evaluation_metrics"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0184b0fdf199fb200d1f0ed66c26118c2d14aa7a"} +{"id": "val_00310", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "governance", "tests_are_truth", "cost_latency_tradeoffs"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0c5d653801ef47914cdec172708e762438180ba9"} +{"id": "val_00311", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "cost_latency_tradeoffs", "tooling", "reproducibility"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d8aeada899da5817f73794b55aeecdc86e849604"} +{"id": "val_00312", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "repo_scale_reasoning", "reproducibility", "ci_integration"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ca9fd6d9f890869349b3ac5892a8dc32357aacb4"} +{"id": "val_00313", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "governance", "repo_scale_reasoning", "security_gates"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cc61cc712dcbf3f364d63b3ed2d5d5610c44760b"} +{"id": "val_00314", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "tests_are_truth", "repo_scale_reasoning", "governance"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6ff2dad90e1e1276d3ddc93b22a603c11fc33cf8"} +{"id": "val_00315", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["evaluation_metrics", "security_gates", "auditability", "tests_are_truth"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c73f4a064f324dc82fc4c0fadbb4fecd5b80636c"} +{"id": "val_00316", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["auditability", "ci_integration", "reproducibility", "security_gates"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cf943dbedc687a95cd214f7411c0ee3b19404ef1"} +{"id": "val_00317", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["auditability", "security_gates", "cost_latency_tradeoffs", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0494692566269aa93554b35ab32160c99769bbbe"} +{"id": "val_00318", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["ci_integration", "documentation", "cost_latency_tradeoffs", "governance"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "30a471505b238c15df03d5673d3cbec08fac2824"} +{"id": "val_00319", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["cost_latency_tradeoffs", "repo_scale_reasoning", "tooling", "documentation"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a2aaed0f0d579c4d0d966d7ea21578581fc4e9c2"} +{"id": "val_00320", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "governance", "tests_are_truth", "security_gates"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5817a1e88377e57aed0f1935fdb0ff71a66cf775"} +{"id": "val_00321", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["auditability", "reproducibility", "security_gates", "tooling"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fd344743fca8d1b85ed986602802f2ae0c63cdef"} +{"id": "val_00322", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["auditability", "evaluation_metrics", "governance", "tests_are_truth"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "303bf4a7626689769aabe14f8a03ddf5a8d6da2d"} +{"id": "val_00323", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["governance", "cost_latency_tradeoffs", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d4ffd1faee426cff582e01e7b1141aad59d67f3d"} +{"id": "val_00324", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["tooling", "governance", "ci_integration", "tests_are_truth"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3be385c74396685ce2387b13123ab3a7af4f3b99"} +{"id": "val_00325", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tests_are_truth", "documentation", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a7e8d375823eb96e683841a0a54ac2d8d4e3beeb"} +{"id": "val_00326", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "security_gates", "documentation", "governance"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "500053cea39fa7057c14f56c10cfbcdee84e6d98"} +{"id": "val_00327", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "documentation", "security_gates", "tests_are_truth"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6fc126fff15285ec48d349477afce6e1b832e167"} +{"id": "val_00328", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "documentation", "repo_scale_reasoning", "tests_are_truth"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ba88987617b18be8fc0e5e4d0e9a4a0f54fcc073"} +{"id": "val_00329", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "reproducibility", "tests_are_truth", "governance"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d9ee809ca90fa5ee163872bbefa52d0afba37536"} +{"id": "val_00330", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "auditability", "cost_latency_tradeoffs", "tooling"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b893c3b8da8a81ae23d56b41cff55334bef6e99e"} +{"id": "val_00331", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["governance", "ci_integration", "security_gates", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "65321aa0e9c1a47862802a0ce6b6d36e5db174bb"} +{"id": "val_00332", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "ci_integration", "auditability", "cost_latency_tradeoffs"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "43c0888eb486dd67e7fdbdb04253dfa2ea12117a"} +{"id": "val_00333", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "evaluation_metrics", "auditability", "governance"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "415e4c9ae19e12a7a94ec631fd2a63de2fa4aaf7"} +{"id": "val_00334", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "auditability", "governance", "evaluation_metrics"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4b12b98edee6193dfed94b0e978758cd3cd87211"} +{"id": "val_00335", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "governance", "documentation", "evaluation_metrics"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "18a90d01e0d232e17f92ac6a812aa9c66e7dee17"} +{"id": "val_00336", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["cost_latency_tradeoffs", "governance", "documentation", "reproducibility"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bb8b08013f913f919e95af0e34e21b9707f33728"} +{"id": "val_00337", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["ci_integration", "governance", "tooling", "reproducibility"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "25ed7be5b30b06d54aab1e8d99441575517aab9c"} +{"id": "val_00338", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "documentation", "repo_scale_reasoning", "ci_integration"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c2acdb6593480244b13f0c63e8a04bd40b4ecf33"} +{"id": "val_00339", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nScaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=4):\n history = []\n p = plan(issue)\n for _ in range(max_iters):\n patch = edit(issue, p)\n ok, report = test(patch)\n history.append({\"plan\": p, \"ok\": ok})\n if ok:\n return patch, history\n p = p + \" | refine\"\n return patch, history\n\n```\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["governance", "reproducibility", "documentation", "tooling"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5aac6c04b6fb9985f23d3ccd1f7c1b31ebddad5d"} +{"id": "val_00340", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "tooling", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f9199706d032336d99a83682ce320351629a7eeb"} +{"id": "val_00341", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "governance", "reproducibility", "security_gates"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c6d3d30a7d397ad608afd43b662e5a5b332d3018"} +{"id": "val_00342", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["repo_scale_reasoning", "reproducibility", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d42c926ae32f8e9eeee3d0366e9a4a8308acb60f"} +{"id": "val_00343", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "governance", "tooling", "repo_scale_reasoning"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "223e7781d4a7af911a27617028ea73b1840e1aaa"} +{"id": "val_00344", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["ci_integration", "repo_scale_reasoning", "tests_are_truth", "documentation"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "648f22a685fbab89d245e3dfec9da24e9a7bba79"} +{"id": "val_00345", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "security_gates", "cost_latency_tradeoffs", "tests_are_truth"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c1c150e80fbb86479ef98f40d784a2cbd8f6aeb8"} +{"id": "val_00346", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["reproducibility", "evaluation_metrics", "security_gates", "documentation"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c366733fc0a96a513e411c624c88844c4d7e18af"} +{"id": "val_00347", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["repo_scale_reasoning", "ci_integration", "tooling", "governance"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "07f1acb6348612acf2aac4ff8cf46354ea324c24"} +{"id": "val_00348", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "evaluation_metrics", "tooling", "documentation"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6094463eeb47d3c31322131329d51b7930cb6df9"} +{"id": "val_00349", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "auditability", "security_gates"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "486b9a395b67fb6360e3c1156d0fba9777643d8b"} +{"id": "val_00350", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tests_are_truth", "security_gates", "cost_latency_tradeoffs", "reproducibility"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5678613f1b01eeb27e3654d09b33d09dfe3b7193"} +{"id": "val_00351", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "tooling", "evaluation_metrics"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0e24280ae09aa4ad2dee3a1c48de8fb95367b341"} +{"id": "val_00352", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "governance", "security_gates", "ci_integration"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c52c22eb9186c34162533b9e84e810a136d9aa82"} +{"id": "val_00353", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["auditability", "ci_integration", "tests_are_truth", "governance"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e4c08fcfed1d42236b874b767f4dcc73ec369154"} +{"id": "val_00354", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "evaluation_metrics", "ci_integration", "auditability"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "790fc1a430034338f7fe24f195ff7210e514ed91"} +{"id": "val_00355", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "auditability", "cost_latency_tradeoffs", "security_gates"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8337b77ae9590b62d50dd3b6384d766a580678e8"} +{"id": "val_00356", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "evaluation_metrics", "documentation", "governance"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "12545497def44c1dfbc96ee218c0f48e53b3bafc"} +{"id": "val_00357", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["auditability", "cost_latency_tradeoffs", "governance", "ci_integration"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0ec6275b1f5b3ddd4e119ddc2570469d4db1481a"} +{"id": "val_00358", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nScaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=4):\n history = []\n p = plan(issue)\n for _ in range(max_iters):\n patch = edit(issue, p)\n ok, report = test(patch)\n history.append({\"plan\": p, \"ok\": ok})\n if ok:\n return patch, history\n p = p + \" | refine\"\n return patch, history\n\n```\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["auditability", "ci_integration", "tests_are_truth", "reproducibility"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "63e671e021db6a7b51017194ab6e92393ae2057d"} +{"id": "val_00359", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["tooling", "security_gates", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "105681a87e7b6f5f0d193751a2ce55869518bf66"} +{"id": "val_00360", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["governance", "reproducibility", "documentation", "evaluation_metrics"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d3479f7aa366423b0ea88fd353a1a1e50ed40f42"} +{"id": "val_00361", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "auditability", "reproducibility", "ci_integration"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7010014d311694a54d7cce8930a7e79f3e6099ae"} +{"id": "val_00362", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["tooling", "auditability", "governance", "evaluation_metrics"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8020b0e8a3b2b0e639a07b580a7d669b5b4cb4ac"} +{"id": "val_00363", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["tooling", "evaluation_metrics", "cost_latency_tradeoffs", "documentation"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d92c0a0e0fbe7b90a29054cf551735f5d919132f"} +{"id": "val_00364", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "evaluation_metrics", "repo_scale_reasoning", "governance"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f3bd8ec65917d76745d3931754fb6f48e341a966"} +{"id": "val_00365", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["security_gates", "tests_are_truth", "ci_integration", "reproducibility"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "29012cc1229e3c87136696667e65f648fb476923"} +{"id": "val_00366", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["evaluation_metrics", "ci_integration", "governance", "tests_are_truth"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c9246ff92059bf93a058cf4444404d221b5b7435"} +{"id": "val_00367", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "reproducibility", "evaluation_metrics", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b94245fe6a128a53c89cd4c4a914e0013096f343"} +{"id": "val_00368", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "repo_scale_reasoning", "evaluation_metrics", "auditability"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e54a5beb76970b3d40510463e4113336fd172b45"} +{"id": "val_00369", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["auditability", "cost_latency_tradeoffs", "tooling", "tests_are_truth"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "550cecc0d0952c213c230975b7cf3e3070db2ad3"} +{"id": "val_00370", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "repo_scale_reasoning", "tooling", "evaluation_metrics"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9f164f0353732f4c493c5decfc35aa8006e83ba2"} +{"id": "val_00371", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["documentation", "cost_latency_tradeoffs", "governance", "tests_are_truth"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c8d85ee55413434f49bc12fcc2b315dd757601f6"} +{"id": "val_00372", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "reproducibility", "repo_scale_reasoning", "cost_latency_tradeoffs"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "74d2b0fd1e15b3ad4bacfe8e73f889cf0d82ca4d"} +{"id": "val_00373", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "auditability", "documentation"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e2117b38530d5306b4b932a11145550b42c727fb"} +{"id": "val_00374", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["security_gates", "evaluation_metrics", "ci_integration", "cost_latency_tradeoffs"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "38eba707b2c3b36d09ea4983275f361fa81e2b23"} +{"id": "val_00375", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["governance", "tests_are_truth", "cost_latency_tradeoffs", "auditability"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ea0e6eb9ce9ec2e5aada129f0d832eaa9d97a287"} +{"id": "val_00376", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "ci_integration", "repo_scale_reasoning", "reproducibility"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "eaa0647f35ad3de265709a764f035dca23126211"} +{"id": "val_00377", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "cost_latency_tradeoffs", "auditability", "security_gates"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e6b99d0452e381e84750d7263bde3a4d93db7695"} +{"id": "val_00378", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "cost_latency_tradeoffs", "reproducibility", "tests_are_truth"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8205b568b3b3f62b7980bc242c6f513fefdf6e5e"} +{"id": "val_00379", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["auditability", "evaluation_metrics", "tooling", "tests_are_truth"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "79a89ba0ac8ca778d0edae9d72c243654d9f2096"} +{"id": "val_00380", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["ci_integration", "evaluation_metrics", "documentation", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4dd6236b8eaf559fd0707e749cfe89af400d5c99"} +{"id": "val_00381", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["governance", "tests_are_truth", "security_gates", "tooling"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "830a9fd51f5b725eba8bce7cb84d79cc33201fd9"} +{"id": "val_00382", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "evaluation_metrics", "auditability", "documentation"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "945e2400256d4cd641cf48edcf637ebf1cdbe5b4"} +{"id": "val_00383", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["auditability", "cost_latency_tradeoffs", "repo_scale_reasoning", "tooling"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "982ba2fa2e70020438f68e3b10ab27cc96cc9966"} +{"id": "val_00384", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "auditability", "cost_latency_tradeoffs", "evaluation_metrics"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5aa95260e762995df665ef0bef039c3bc6a0eb35"} +{"id": "val_00385", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "auditability", "tests_are_truth", "tooling"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b430788b8062e49a7f4bf3a8ed01fb437d7fee6f"} +{"id": "val_00386", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "security_gates", "tooling", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "10fc9770090acc4e4c53c4993955290c28858a51"} +{"id": "val_00387", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "cost_latency_tradeoffs", "security_gates", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0a0f679ce3ab060a30990b119acc129f4c05625b"} +{"id": "val_00388", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "documentation", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9db365cad2e0283b4e72d8ab9222e1fe9e37500d"} +{"id": "val_00389", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["cost_latency_tradeoffs", "tooling", "repo_scale_reasoning", "security_gates"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3d74931321744b25fecff8b48cb56f4857b3620a"} +{"id": "val_00390", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "tests_are_truth", "repo_scale_reasoning", "auditability"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "56f5330b09d33f479605f27ea0c3a9b0112686b3"} +{"id": "val_00391", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nScaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=4):\n history = []\n p = plan(issue)\n for _ in range(max_iters):\n patch = edit(issue, p)\n ok, report = test(patch)\n history.append({\"plan\": p, \"ok\": ok})\n if ok:\n return patch, history\n p = p + \" | refine\"\n return patch, history\n\n```\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "evaluation_metrics", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2de44013b2ddf26479bb47b56c2aa01b4894cba5"} +{"id": "val_00392", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "ci_integration", "documentation", "reproducibility"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f2e572b9b8493cb2e1dde6c7c227d483e185d4bd"} +{"id": "val_00393", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["evaluation_metrics", "tooling", "cost_latency_tradeoffs", "reproducibility"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4a2869e58b0edb9816f204ec6d130382a69fdd1c"} +{"id": "val_00394", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["evaluation_metrics", "documentation", "repo_scale_reasoning", "reproducibility"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "53273da4a7b20f8d5bc1f36025534d0175800f3a"} +{"id": "val_00395", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["documentation", "repo_scale_reasoning", "auditability", "reproducibility"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7a6e414c37f28990217cb1b887a26ead01abfea2"} +{"id": "val_00396", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "governance", "ci_integration", "evaluation_metrics"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0cd46b783c9c50bf44e9f09dcd9383e37486d146"} +{"id": "val_00397", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "governance", "auditability"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "65beedf2f61f879c71e5d519410ec6f0cac92ce6"} +{"id": "val_00398", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "security_gates", "tests_are_truth", "tooling"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "102a6642efa770721e97bc6bb65ccc7c789630cd"} +{"id": "val_00399", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "auditability", "tooling", "tests_are_truth"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "acc4f570e322ef62f6d0cff06232f56f081f5461"} +{"id": "val_00400", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "tooling", "auditability"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5ad91af11ed56d7fdef164c0fd9fa1734f66f89d"} +{"id": "val_00401", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "tests_are_truth", "auditability", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "10bd1554a514ea7b876b18bb892858f57f313e30"} +{"id": "val_00402", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "cost_latency_tradeoffs", "governance", "reproducibility"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "40776be96a5d6ca2c27d4d704e736ffe97aa724a"} +{"id": "val_00403", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "documentation", "ci_integration", "tests_are_truth"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f1c31949bd9519f5d8c46f7ed63a1977fbe3e1eb"} +{"id": "val_00404", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["auditability", "tests_are_truth", "security_gates", "governance"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "80fc8ea400fe2bd6507b4e44e31cb8aa2bdc5330"} +{"id": "val_00405", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["tooling", "ci_integration", "security_gates", "governance"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8aea59f6a0e7699dafe1dd8ce240f07cc89bf971"} +{"id": "val_00406", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "repo_scale_reasoning", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "27d1b37b67ab1fc8745da5ac5f9c823ec28e002f"} +{"id": "val_00407", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "evaluation_metrics", "governance"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "dc0c2ee21295ca345dd0ee558e75d8fd41f9ca78"} +{"id": "val_00408", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["evaluation_metrics", "tooling", "auditability", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b8b2a1fd9eca68baec40ec31ee4b176573e66c74"} +{"id": "val_00409", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "security_gates", "reproducibility", "tests_are_truth"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9db365cad2e0283b4e72d8ab9222e1fe9e37500d"} +{"id": "val_00410", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["reproducibility", "evaluation_metrics", "ci_integration", "tooling"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "04879379981de9dfda0e199b92c238a080b3cde7"} +{"id": "val_00411", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["cost_latency_tradeoffs", "tests_are_truth", "governance", "reproducibility"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4ef28da35cd2a5c987e6612b81e541f39875bfb5"} +{"id": "val_00412", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["governance", "security_gates", "repo_scale_reasoning", "ci_integration"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d7c4376ca9c984bb63064f147b6177f16c414713"} +{"id": "val_00413", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "ci_integration", "cost_latency_tradeoffs", "reproducibility"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b77f35f00184b8293353eddf7da2742a1e796a2c"} +{"id": "val_00414", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "security_gates", "documentation", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "96b2bc0d12a5288865547552e4f1bbd6f1528b00"} +{"id": "val_00415", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "reproducibility", "cost_latency_tradeoffs", "security_gates"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "958d0aac4995ecbaa2c68abd3bb91c53a4c4b015"} +{"id": "val_00416", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "governance", "repo_scale_reasoning", "auditability"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "36a54b4db525c8afcd2ff5181845040f072c52ca"} +{"id": "val_00417", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "ci_integration", "reproducibility", "security_gates"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9b0dd3d0c11f4bbe2da50ed323870408a6fe68a6"} +{"id": "val_00418", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["tests_are_truth", "documentation", "tooling", "evaluation_metrics"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2e753c89983269730e08b9afcb3a12cba2e18063"} +{"id": "val_00419", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["repo_scale_reasoning", "cost_latency_tradeoffs", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ebe5b3fe380edbf2eda526c55e0dcf0f83161817"} +{"id": "val_00420", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["evaluation_metrics", "governance", "ci_integration", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f9e393646230998889595632c8d516ef1fa294f9"} +{"id": "val_00421", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "auditability", "documentation"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "40282c6bfa1144ad3235cb972e96b7ce0661056b"} +{"id": "val_00422", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["ci_integration", "cost_latency_tradeoffs", "governance", "repo_scale_reasoning"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3789740d6ad21228e75e7ba29797474437549b7c"} +{"id": "val_00423", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "ci_integration", "repo_scale_reasoning", "tooling"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7d3ea98e925864bb10520d499f6d4f9c4f406bf5"} +{"id": "val_00424", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["documentation", "ci_integration", "tests_are_truth", "auditability"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fe98195c38de21b4bb6ac8d3992402c530c65b39"} +{"id": "val_00425", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "security_gates", "tooling", "reproducibility"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "01cb51f3c50fe6822c591ba7b7c26a5e21d50ce0"} +{"id": "val_00426", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "repo_scale_reasoning", "security_gates", "ci_integration"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1dcf607e9a41d230195faa37bbb70a3808e34049"} +{"id": "val_00427", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["governance", "tests_are_truth", "evaluation_metrics", "documentation"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "051d64dc518573e33af39fbf3ac2853b2daaf05f"} +{"id": "val_00428", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "tooling", "ci_integration", "auditability"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b18f1c4d212e72ca5b82b2aff030fb28e3dddefa"} +{"id": "val_00429", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["documentation", "cost_latency_tradeoffs", "auditability", "tooling"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3dbcefe14a88a0872b2fac86cb5ec5882847b377"} +{"id": "val_00430", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["tests_are_truth", "repo_scale_reasoning", "reproducibility", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7250e95920e6b73d3b5736603c4535c054d5ee52"} +{"id": "val_00431", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "cost_latency_tradeoffs", "tooling", "ci_integration"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "354b33c143e4ac2a00b7cbecb7d8b5d9bf959f7f"} +{"id": "val_00432", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["evaluation_metrics", "documentation", "reproducibility", "governance"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "82e126870324777ac9addfd16d34af99d88e85bc"} +{"id": "val_00433", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "governance", "reproducibility"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a81ca665098e9eb2ed0a8bf2a85882724cfa2d18"} +{"id": "val_00434", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "tests_are_truth", "auditability", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b32fb3b00e9d43796985a5da90a77cd5607e0984"} +{"id": "val_00435", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["documentation", "ci_integration", "security_gates", "governance"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1eb89efa4c56171a7ce61b9043bef3ec0d9ed0b5"} +{"id": "val_00436", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "tests_are_truth", "governance", "evaluation_metrics"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e1a2a0fa91a568c9ca4c7481fed27d5915dadc49"} +{"id": "val_00437", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["repo_scale_reasoning", "security_gates", "cost_latency_tradeoffs", "documentation"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1866f00525595df28b06de51676688d8472f39b1"} +{"id": "val_00438", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["ci_integration", "repo_scale_reasoning", "documentation", "auditability"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4dd0264d94027a235ed4c65d222af0f299f99571"} +{"id": "val_00439", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "auditability", "governance"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f7cb61e461cc0b6977049e2c011cb4483c82040a"} +{"id": "val_00440", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "ci_integration", "tests_are_truth", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5014eb56809eb114706ce5443909f6101d7ad443"} +{"id": "val_00441", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "governance", "evaluation_metrics", "security_gates"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "102c9f6e44d378faf9e5e9f515813f73defefd45"} +{"id": "val_00442", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "governance", "security_gates", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7d25cf2e974e1c9d92caadc961f66ea6555758f6"} +{"id": "val_00443", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "tooling", "reproducibility", "ci_integration"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "618e817e1851541678f726c55829a94f0cf04ddb"} +{"id": "val_00444", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["documentation", "evaluation_metrics", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3ef523b4b30c563165e0b9cec9f1564f71c9ef74"} +{"id": "val_00445", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["evaluation_metrics", "documentation", "auditability", "ci_integration"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ae7271cee9ecacbd2db86133dcc36cc53588e518"} +{"id": "val_00446", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["ci_integration", "tests_are_truth", "security_gates", "tooling"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1b19cb36bf4519ebeb4afea455881524972b44c6"} +{"id": "val_00447", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "evaluation_metrics", "ci_integration", "reproducibility"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e30027a9304757d4ee801ffb4d5bab3e8fdd4b96"} +{"id": "val_00448", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["governance", "reproducibility", "repo_scale_reasoning", "security_gates"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7dbd36e2f7336989befe83203722b7ea0a8aff59"} +{"id": "val_00449", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["repo_scale_reasoning", "auditability", "evaluation_metrics", "governance"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c6e57866e027fa3718aa46848036157b4eca66df"} +{"id": "val_00450", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["auditability", "ci_integration", "security_gates", "cost_latency_tradeoffs"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "14a5f89f8b73ff46fdf3dbe80fb2a09719780ef7"} +{"id": "val_00451", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "governance", "documentation", "tests_are_truth"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "50754d607820113116d94a597d90140c1ebf5357"} +{"id": "val_00452", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["documentation", "cost_latency_tradeoffs", "tooling", "ci_integration"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4f232c51f20ae6d9ba65ab6aaf6d474a9fdbd7a0"} +{"id": "val_00453", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["ci_integration", "reproducibility", "evaluation_metrics", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fa9fe2d9ce0ccef9e21634a2ec68658e817e8bcc"} +{"id": "val_00454", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["auditability", "tests_are_truth", "ci_integration", "repo_scale_reasoning"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a27ddc7824cec25dcbbc8010141c660b3813f26b"} +{"id": "val_00455", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["evaluation_metrics", "governance", "tests_are_truth", "security_gates"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1cd2ca3b30521db7bb1bef09e1f105bf2f691571"} +{"id": "val_00456", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "governance", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3a51160bfed993c4a53e8c2ac746dc78fd4e53ed"} +{"id": "val_00457", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "repo_scale_reasoning", "security_gates", "evaluation_metrics"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5ac1f8eac9e60a79dbb51f0d34e168247719f89d"} +{"id": "val_00458", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "tooling", "auditability", "documentation"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e21472c8fccd7af485f89ae3913cf5e6c1ad7c92"} +{"id": "val_00459", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "ci_integration", "tests_are_truth", "tooling"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "11bbccf6e441bf5055ad82241a62ac46ffed24b9"} +{"id": "val_00460", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["security_gates", "documentation", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "73ef181bc7b83a46da2c651c5fe55685a7503fa7"} +{"id": "val_00461", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "reproducibility", "security_gates", "cost_latency_tradeoffs"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "364f482807fc8a1b571ddc3e6a28ead00d4fd013"} +{"id": "val_00462", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "governance", "tooling"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3e422c2d9c30e4b095b53f7353ac4f24ac8b3600"} +{"id": "val_00463", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["governance", "tooling", "evaluation_metrics", "cost_latency_tradeoffs"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "08d12fcd5ff0b2311f950913bec1dcd119d849be"} +{"id": "val_00464", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["documentation", "cost_latency_tradeoffs", "security_gates", "governance"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b3976a2d35c6949590a3714eae958de8ed20412d"} +{"id": "val_00465", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "tooling", "evaluation_metrics", "documentation"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d3a808df2ea4260430e8575e918143dc5ac2caf5"} +{"id": "val_00466", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["tooling", "evaluation_metrics", "governance", "repo_scale_reasoning"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "273d2cd0398ad3ad37a67b9ab9b96511b1a45e40"} +{"id": "val_00467", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "documentation", "evaluation_metrics", "security_gates"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "401f5bf072879d7585db2b9855da360082772006"} +{"id": "val_00468", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "governance", "evaluation_metrics", "documentation"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0b841cfc7d03819b30ff70aeff5a6c7ee8ae0249"} +{"id": "val_00469", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "evaluation_metrics", "tooling", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1c6ed7af229fbea693d7dcb0eb3f98cf2b03a909"} +{"id": "val_00470", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "tests_are_truth", "ci_integration", "security_gates"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "afecf56309acd34a4bb91cad96abffbab8e31d42"} +{"id": "val_00471", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["ci_integration", "documentation", "tooling", "governance"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "214c29199f262534dab640cdaf4ad2ec41752826"} +{"id": "val_00472", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "tests_are_truth", "governance", "security_gates"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5d86d6979aecb8931222d7623d956f461c45358f"} +{"id": "val_00473", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["repo_scale_reasoning", "tooling", "reproducibility", "governance"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "926ecebd817202758ab453bc860de3b2d31bf007"} +{"id": "val_00474", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["governance", "evaluation_metrics", "documentation", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "350c3adf77ac4d51c5008cd66a4f8792b2f19f43"} +{"id": "val_00475", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "security_gates", "documentation", "governance"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "01410e8a50313da234229fa95d45e1b51310842e"} +{"id": "val_00476", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "cost_latency_tradeoffs", "auditability", "tooling"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7958aa65de35f0d6ba2b616725f3dfb8cdb1d5ed"} +{"id": "val_00477", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "cost_latency_tradeoffs", "evaluation_metrics", "tooling"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "db3ade8898625c94c5189cceb2ef4c1d96997a26"} +{"id": "val_00478", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "repo_scale_reasoning", "documentation", "ci_integration"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0587f3ac5dac187b5a1653a6a0b222578c7f5492"} +{"id": "val_00479", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["documentation", "repo_scale_reasoning", "ci_integration", "governance"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "87dfab0b64d657b78a59d915c03f6d26a8fa7cef"} +{"id": "val_00480", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "tests_are_truth", "documentation"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6df90cb7cd7f1fbb39f563ea78414e16c836f3fb"} +{"id": "val_00481", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "reproducibility", "security_gates", "documentation"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bf48c41e695f4296343dc2cebab5e6fc66f1fec6"} +{"id": "val_00482", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "tests_are_truth", "evaluation_metrics", "auditability"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bbe2d3c0b4fd59ad0c18190af9e2b81ae74751fe"} +{"id": "val_00483", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "governance", "tests_are_truth", "cost_latency_tradeoffs"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "46c8fe37d3fd320156c5cdc823dddf1a607cee1b"} +{"id": "val_00484", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["governance", "repo_scale_reasoning", "tooling", "tests_are_truth"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b99f510f8fa48621501669287c2fc77e56128d40"} +{"id": "val_00485", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "repo_scale_reasoning", "evaluation_metrics", "tests_are_truth"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "221d802af38eb1cd86fce9f34f66275c22c32a80"} +{"id": "val_00486", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["governance", "ci_integration", "tooling", "reproducibility"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "034d2a3e6e9998d6ed59ea1252f09d2ffaa1dce7"} +{"id": "val_00487", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tests_are_truth", "documentation", "repo_scale_reasoning", "reproducibility"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3c77d139717af6e8bf76035afafacc550e0d7967"} +{"id": "val_00488", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "reproducibility", "ci_integration"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4befb2c4376feaaad5418298be9fde7d3eba1ca0"} +{"id": "val_00489", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "reproducibility", "tests_are_truth", "governance"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ae95c77ece7c20695ef27c2b6b84695ae923313a"} +{"id": "val_00490", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "documentation", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "46c3539b58872c080acc8d3554f22e13173ad01f"} +{"id": "val_00491", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "governance", "tooling", "ci_integration"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3c6b6324552e978b798e26912a951bcbbcd44552"} +{"id": "val_00492", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "reproducibility", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fac589c9b20dc12e31b2fb0cb00b7149e71076f1"} +{"id": "val_00493", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "documentation", "tooling", "governance"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6f2775484fef7b4b6a7a3b47fa29c2fb755a8ebc"} +{"id": "val_00494", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["tests_are_truth", "auditability", "tooling", "governance"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a6a501cde4451f9e4f8de0f9a478299776547336"} +{"id": "val_00495", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["governance", "cost_latency_tradeoffs", "evaluation_metrics", "tooling"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f99d400040ba2aefebb0d72203305cb064ae16d8"} +{"id": "val_00496", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "documentation", "repo_scale_reasoning", "ci_integration"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "341dbd254b5dceedf0a2517ad83af81cea0d2d3c"} +{"id": "val_00497", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "governance", "tests_are_truth", "security_gates"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d9b4641fd9993b374c257dc0baed64a19a3e29d6"} +{"id": "val_00498", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "ci_integration", "security_gates", "governance"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a350356fee6a2f3e3e19ed44c28a4cbc7684a296"} +{"id": "val_00499", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "tooling", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7eebacc5e08d4ca8f8d1badaa576a11521bbc122"} +{"id": "val_00500", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "tooling", "security_gates", "ci_integration"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ee3be44609c1be7e06fa1ba006ebff359d1bf56e"} +{"id": "val_00501", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["tooling", "tests_are_truth", "ci_integration", "security_gates"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4200f0ffb83ee26e1aeb1711332a7c46f4b318b9"} +{"id": "val_00502", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["auditability", "tooling", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d24165d0bb788660dd3a0751c03421bf04b92b22"} +{"id": "val_00503", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["documentation", "governance", "tests_are_truth", "tooling"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8bdd6a277ce236a8659e585f0364815b194e4d71"} +{"id": "val_00504", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "tooling", "tests_are_truth", "security_gates"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ff76105755eaa066094c491bc87cbe82a7b987bd"} +{"id": "val_00505", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "cost_latency_tradeoffs", "reproducibility", "governance"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2b1fa6fcf05720be52c2c8fdcd3bdc34f49ed982"} +{"id": "val_00506", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["ci_integration", "tests_are_truth", "reproducibility", "auditability"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "807cf9d1da1de9454dc5a4e77667b2e44bd2979f"} +{"id": "val_00507", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "evaluation_metrics", "repo_scale_reasoning", "reproducibility"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "dbeced256290e4992501b9d14bd6706fc58c4c4d"} +{"id": "val_00508", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["tests_are_truth", "tooling", "evaluation_metrics", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5547ce7b5d61dea3db7b7ce5c3a870e338014cbf"} +{"id": "val_00509", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "ci_integration", "reproducibility", "cost_latency_tradeoffs"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "95c04330ca4607bf8ea72366b2f48e38bbac55a2"} +{"id": "val_00510", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "documentation", "tooling", "auditability"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "904dc64e581713666ac9707c731bbc749205adc1"} +{"id": "val_00511", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "documentation", "auditability", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "223989e58503a388102d56aabcc78174266309de"} +{"id": "val_00512", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["documentation", "evaluation_metrics", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "46d1c5c32a90b2847b7f85ea6f62a7944e117fda"} +{"id": "val_00513", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["documentation", "ci_integration", "evaluation_metrics", "governance"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6bf819ba8871a82b9c0ea5738d0323a1cdfebe6c"} +{"id": "val_00514", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "cost_latency_tradeoffs", "documentation", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "15593ef14303f584fd59209bb48a68260bf4abd0"} +{"id": "val_00515", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "cost_latency_tradeoffs", "tooling", "ci_integration"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6c09f9b7537609b31beecc3f81ff8ae165e399b4"} +{"id": "val_00516", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["tooling", "ci_integration", "repo_scale_reasoning", "reproducibility"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a2343e64bcaf96a29bf14ff59c7359dcedc7632d"} +{"id": "val_00517", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "governance", "cost_latency_tradeoffs", "evaluation_metrics"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5c72a0f5afdeda870f8fa27029337f65dd29eb05"} +{"id": "val_00518", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "ci_integration", "auditability", "security_gates"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fc93a4cf5d56079ac98f3c8675fdaaf4bab536ec"} +{"id": "val_00519", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "cost_latency_tradeoffs", "ci_integration", "reproducibility"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "29eef297b2793400707b763ef77bf2840f758311"} +{"id": "val_00520", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["evaluation_metrics", "tooling", "repo_scale_reasoning", "reproducibility"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "739a5277096c1b19c463a2bf31e4c2ab40ad037a"} +{"id": "val_00521", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "repo_scale_reasoning", "governance", "evaluation_metrics"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b2d66175c49d98f2491e806b365fd77ff0662b24"} +{"id": "val_00522", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "auditability", "cost_latency_tradeoffs", "tests_are_truth"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9e8340b7c056f9fb55a075b9ed42859c5e966591"} +{"id": "val_00523", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nScaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=4):\n history = []\n p = plan(issue)\n for _ in range(max_iters):\n patch = edit(issue, p)\n ok, report = test(patch)\n history.append({\"plan\": p, \"ok\": ok})\n if ok:\n return patch, history\n p = p + \" | refine\"\n return patch, history\n\n```\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["ci_integration", "documentation", "cost_latency_tradeoffs", "auditability"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e26b7f0f952965016947597509a90856231ef3fb"} +{"id": "val_00524", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tests_are_truth", "auditability", "tooling", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "37fbabbba2fbfa5276b58e25021bc8a3da22b358"} +{"id": "val_00525", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "governance", "ci_integration", "reproducibility"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "64f89c36267e78e28f6a566f41e30fb99a7df3ac"} +{"id": "val_00526", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["ci_integration", "tooling", "auditability", "evaluation_metrics"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1d94f42db64babdf1d48e98fba0da10482601895"} +{"id": "val_00527", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["tests_are_truth", "reproducibility", "evaluation_metrics", "tooling"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "86196e774e155ad2e08d6831fa0dec4e1b1e8748"} +{"id": "val_00528", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["tests_are_truth", "auditability", "security_gates", "governance"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "078ac111116620df8be2942f8ccaf7eecde43577"} +{"id": "val_00529", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["evaluation_metrics", "documentation", "reproducibility", "auditability"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ebdca48e7871a75d461ab19198ebfe761d298328"} +{"id": "val_00530", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "governance", "evaluation_metrics", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f29fd1df44bbf61453c9a64e94b9c18f45cf1b0b"} +{"id": "val_00531", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "documentation", "auditability", "cost_latency_tradeoffs"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5b0fd8a4558de4f90a96e5c2070124656f970910"} +{"id": "val_00532", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["documentation", "security_gates", "auditability", "evaluation_metrics"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1000a0872705356d6ad708372a3550b86c3b0b3e"} +{"id": "val_00533", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "repo_scale_reasoning", "cost_latency_tradeoffs", "security_gates"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b140fadabf18a775ee912fd2b223db1f4e9fd9ad"} +{"id": "val_00534", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "repo_scale_reasoning", "tests_are_truth", "auditability"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0cefd391273ffa4df92931fdaefef3a69b0733f8"} +{"id": "val_00535", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "repo_scale_reasoning", "security_gates", "evaluation_metrics"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "93b7be84c69047d9f2a045db0db123ab3c1f59f9"} +{"id": "val_00536", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "tests_are_truth", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8e70e064cba9e92cb0f63b775521d6356e99eeb9"} +{"id": "val_00537", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "repo_scale_reasoning", "tooling", "documentation"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d6d05bcb729e78963b2e019f56f39d956631230e"} +{"id": "val_00538", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["tooling", "cost_latency_tradeoffs", "repo_scale_reasoning", "ci_integration"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e888c309c790b35565f69d453e0b4328e3943e7c"} +{"id": "val_00539", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "documentation", "security_gates", "governance"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "770641b7c69a7c8f2ab265b60e71a2b5b8fb747a"} +{"id": "val_00540", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "reproducibility", "tooling", "auditability"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3e1fa0a19adead1adfe9198f6743240fa9f74614"} +{"id": "val_00541", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "ci_integration", "repo_scale_reasoning", "evaluation_metrics"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ff167e2dd89774f30df63247c7a06cd505951765"} +{"id": "val_00542", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["documentation", "security_gates", "tests_are_truth", "governance"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8afbefef07bbf17fd4eeacdcfe39c0156059af98"} +{"id": "val_00543", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "documentation", "reproducibility", "security_gates"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "54e57c9a53644ba59b9e4fd596ba26b62dc955c0"} +{"id": "val_00544", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "reproducibility", "governance", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "689f6e288216779816983d7ed9a291783ba35d7b"} +{"id": "val_00545", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["auditability", "tooling", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c996019e77cb745c67be7bac2c4ee00f805cfef3"} +{"id": "val_00546", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "evaluation_metrics", "ci_integration", "governance"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "29f43ccef72af2dddbc6f4e132bab073c5d648e7"} +{"id": "val_00547", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["auditability", "evaluation_metrics", "tooling", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3d9dc9ee418c302de18fce55eb33852975657397"} +{"id": "val_00548", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "repo_scale_reasoning", "tests_are_truth", "governance"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e281a8308799d381215fa2a733e7c1810dd9b67d"} +{"id": "val_00549", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "auditability", "tooling", "governance"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a0ba3d34319b5a674e964f0fed48a697e98d200d"} +{"id": "val_00550", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["cost_latency_tradeoffs", "documentation", "tests_are_truth", "reproducibility"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f692e7be9925b729e092530858ce3f841e948592"} +{"id": "val_00551", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "auditability", "evaluation_metrics", "tests_are_truth"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "843bcc86f6752dd1a8aa48cca36ebbeedab5c1c6"} +{"id": "val_00552", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "ci_integration", "documentation", "repo_scale_reasoning"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "35f6a8012bf57f352b3fd75d3997b1eecb204ceb"} +{"id": "val_00553", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "ci_integration", "governance", "documentation"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "118c8a7f70d6716abf2a7598fcc6a0ab25a9a072"} +{"id": "val_00554", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["auditability", "cost_latency_tradeoffs", "tests_are_truth", "reproducibility"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "78603d76027931318ba5ba5931653827fcb35cde"} +{"id": "val_00555", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["governance", "security_gates", "reproducibility", "auditability"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e06e710d54b6ebb9658621fc7bd4a8209fbd6752"} +{"id": "val_00556", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "governance", "ci_integration", "security_gates"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "858665b0efe1eebda45fe337253c2db280392e1f"} +{"id": "val_00557", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "security_gates", "governance"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b3eedea4a7d3716d75ef6bcf3d97eb9d0f29d36e"} +{"id": "val_00558", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "auditability", "security_gates", "documentation"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f955a3ceab42c58aeb370046e6f851a63d7040a8"} +{"id": "val_00559", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "security_gates", "tests_are_truth", "documentation"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cb201427cbeb6237ef6c2a688c951e5e9e35a54a"} +{"id": "val_00560", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "documentation", "auditability"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cb4dc2f49d2723095d657a4ba4854e1f84cc033d"} +{"id": "val_00561", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["auditability", "ci_integration", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9b71620a408a58b896959960b76b63d9f6a0516e"} +{"id": "val_00562", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["evaluation_metrics", "ci_integration", "tooling", "security_gates"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7d059c198ae9a0034f0c6d2642c0a36320467c45"} +{"id": "val_00563", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["tooling", "ci_integration", "reproducibility", "security_gates"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2640a467ed5cc1a96d65b138e7d7df83b847344a"} +{"id": "val_00564", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "documentation", "governance", "cost_latency_tradeoffs"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bf5fc704a6d22ce8a96cbc6d69b6f93bdf905ae3"} +{"id": "val_00565", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "reproducibility", "auditability"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "86f8b1fb7c3428738ae7d5b11bb46490a34bf0ef"} +{"id": "val_00566", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "evaluation_metrics", "governance", "security_gates"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8b3972cd60d853afa7c1587f903236490968c1f3"} +{"id": "val_00567", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "security_gates", "tests_are_truth", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "589e96187b2833d7eaba7252680b03799e266057"} +{"id": "val_00568", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "tooling", "cost_latency_tradeoffs", "reproducibility"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "466e9757e26f0978329dd48859985eeeceb9ff49"} +{"id": "val_00569", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "cost_latency_tradeoffs", "evaluation_metrics", "auditability"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9ace65a74ee1660664439b9653f32f248d5a26d7"} +{"id": "val_00570", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "tests_are_truth", "security_gates", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "56c9d75e67dc2a60264e2327d3bcdf8679882dac"} +{"id": "val_00571", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "auditability", "repo_scale_reasoning", "ci_integration"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bd8e496aca38d16103a073d29a905a0aec42579d"} +{"id": "val_00572", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "cost_latency_tradeoffs", "repo_scale_reasoning", "auditability"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2c47870b2abc98a60394806b309b799b57de66d3"} +{"id": "val_00573", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "tooling", "auditability", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "762d7511047cbfffae46949873985dcecfbe13a3"} +{"id": "val_00574", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["cost_latency_tradeoffs", "tests_are_truth", "auditability", "evaluation_metrics"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1a1944ce4e90b6102cb5298900ecd670022c9a34"} +{"id": "val_00575", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "cost_latency_tradeoffs", "auditability", "governance"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fc95aba9767272637685e4a90da6f81ec859df4f"} +{"id": "val_00576", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "tooling", "ci_integration", "security_gates"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "568f38e6ce6055300324b1d04db8e289fa9d3b2a"} +{"id": "val_00577", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "governance", "documentation", "tests_are_truth"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c96596c5bbc9e4df620deb384da1a5ed4974d8c1"} +{"id": "val_00578", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["governance", "tests_are_truth", "auditability", "ci_integration"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c2b7dd443b9fea4ec0e28fdb6c91b5449dc72206"} +{"id": "val_00579", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "tests_are_truth", "security_gates", "tooling"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f214dad4a53352219b203e056a18c2d8f7942e11"} +{"id": "val_00580", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "security_gates", "ci_integration", "reproducibility"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f65c14c4225bd14d1150bbf390e2fc8913e54a6f"} +{"id": "val_00581", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "tooling", "governance", "reproducibility"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2b7fde822257174bf675b9ff0ec64dcd583590c0"} +{"id": "val_00582", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "ci_integration", "cost_latency_tradeoffs", "evaluation_metrics"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bff6903cfff7a53900919eecefd595d20dcead8d"} +{"id": "val_00583", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "tooling", "ci_integration"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3aa24bc71b87db887aea10ffab84a7a33eb577e6"} +{"id": "val_00584", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["governance", "repo_scale_reasoning", "auditability", "tooling"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "337f915f3daa47a25ec36620d50af97e5c19a4bb"} +{"id": "val_00585", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "tooling", "cost_latency_tradeoffs", "governance"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "58dae66998295f3b6909fe46d571715252c239b0"} +{"id": "val_00586", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["reproducibility", "tests_are_truth", "documentation", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "044868caa0a35c6d219d7cc577af58bcf1a75f4f"} +{"id": "val_00587", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["tests_are_truth", "evaluation_metrics", "governance", "ci_integration"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e96dc5da82a3a088a4e7f39217ad6641a9e1d869"} +{"id": "val_00588", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["evaluation_metrics", "tooling", "tests_are_truth", "documentation"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1d2a84eb702eb67c43252d2d94d7cb815db255da"} +{"id": "val_00589", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["cost_latency_tradeoffs", "auditability", "ci_integration", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "398a3f8d7894e3d63ad7e693453b2e2f6fd4a914"} +{"id": "val_00590", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["tests_are_truth", "evaluation_metrics", "security_gates", "ci_integration"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fbe1ccd7d27f8e515bdca8203cfe29fb58f818cf"} +{"id": "val_00591", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["governance", "tests_are_truth", "security_gates", "repo_scale_reasoning"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e974df8e1d7ed2513c8c6ddc631b7ff2baae2500"} +{"id": "val_00592", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["governance", "repo_scale_reasoning", "reproducibility", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "18bed592e4d0e7c49992e8d4ee9152f621c3a94d"} +{"id": "val_00593", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["repo_scale_reasoning", "cost_latency_tradeoffs", "reproducibility", "evaluation_metrics"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "85d38e0f51a7dbfc07e874f4553e03dc65e8bb44"} +{"id": "val_00594", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["cost_latency_tradeoffs", "tooling", "ci_integration", "tests_are_truth"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e3fceb7e50920614a490af6cb8237f58ec589ee7"} +{"id": "val_00595", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["tooling", "documentation", "security_gates", "governance"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9399c5c78c849c1944c4c64faa64d158d6802d66"} +{"id": "val_00596", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["security_gates", "governance", "ci_integration", "auditability"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "01d06444a2f2adfba849c15664418c9216c528ca"} +{"id": "val_00597", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "evaluation_metrics", "repo_scale_reasoning", "cost_latency_tradeoffs"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f9bc5c15f15b9547dea7376b002a51423257b8a9"} +{"id": "val_00598", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["auditability", "documentation", "governance", "security_gates"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "af7ce911cd079db4d68cefe4a9f5207366dd6b4f"} +{"id": "val_00599", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["tests_are_truth", "ci_integration", "governance", "security_gates"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6e38c6edc27775760eebe4822692a904772eafc2"} +{"id": "val_00600", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "documentation", "auditability", "reproducibility"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7363c627c1f7687b1b5d0b3fb43ea2195803be63"} +{"id": "val_00601", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["security_gates", "ci_integration", "tests_are_truth", "cost_latency_tradeoffs"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3b773a20c817c41cb81f3c5fdb1004cc0b7cc8f9"} +{"id": "val_00602", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "ci_integration", "documentation", "cost_latency_tradeoffs"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e0c47d45d15ec40775403edf6e899b088aab687e"} +{"id": "val_00603", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "ci_integration", "tests_are_truth", "tooling"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "62622fca2911a58f244aeaabe18f06439a2be1d3"} +{"id": "val_00604", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "documentation", "cost_latency_tradeoffs", "governance"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5bf7ecbba48af921cc1149fd1f0902a1d3047888"} +{"id": "val_00605", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "documentation", "evaluation_metrics"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "dd8748dc774a37e29566f83b5285dadc9d47d45d"} +{"id": "val_00606", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["evaluation_metrics", "tooling", "governance", "security_gates"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f97c030ae0cd957c3835677687ece12ed401d05d"} +{"id": "val_00607", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tests_are_truth", "evaluation_metrics", "documentation", "governance"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2c56237399e36a54cab96f63d4249e0d24414929"} +{"id": "val_00608", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "repo_scale_reasoning", "tests_are_truth", "governance"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b15d805506c2b72afbbb2447278759a8e96045cd"} +{"id": "val_00609", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "security_gates", "documentation", "tests_are_truth"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "405838758f38f1b8b4e6a81932a5514b316baa77"} +{"id": "val_00610", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "ci_integration", "tooling", "documentation"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3650191c93c16cff15238940d8dc85d35412cd57"} +{"id": "val_00611", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "documentation", "governance", "tooling"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "93c078721be15ca4f6385d188c697f02ea1144d2"} +{"id": "val_00612", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "tests_are_truth", "reproducibility", "documentation"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1a422a74f9bb27050bbc25b5a36f10b3081db527"} +{"id": "val_00613", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "governance", "tooling", "auditability"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "90a31dbe3f1451114046b5939921aaa595b2ae34"} +{"id": "val_00614", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "tests_are_truth", "documentation", "tooling"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a4d736ddb62bc7008988eb14c7cd107341382994"} +{"id": "val_00615", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "evaluation_metrics", "governance", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3f4edb39f8d0007a1d99db0cc942ea490415112b"} +{"id": "val_00616", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["governance", "ci_integration", "security_gates", "cost_latency_tradeoffs"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4dae736e87b99fe5979a76e758fddcab392fbc8d"} +{"id": "val_00617", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "evaluation_metrics", "auditability", "tests_are_truth"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "39ddc80008f3b79700b642d8e5338dc300200013"} +{"id": "val_00618", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["ci_integration", "auditability", "reproducibility", "security_gates"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b8606e21d7fea64af11b0db8d20b5e0f6ae1bf10"} +{"id": "val_00619", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["governance", "auditability", "security_gates", "tooling"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "efac26b08c24271d59a0e35e87df8f8effb5b5db"} +{"id": "val_00620", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "auditability", "ci_integration", "governance"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "198dd560bda3e99b971716f20c5e4eaef7a406d0"} +{"id": "val_00621", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "repo_scale_reasoning", "tooling", "documentation"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c04485d9a2ec5b160cf3c586eff7d4e856d78a61"} +{"id": "val_00622", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["evaluation_metrics", "ci_integration", "documentation", "reproducibility"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "317335088b6160cf81d4e06055c597fcb37e3414"} +{"id": "val_00623", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "documentation", "auditability"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7c8a34f1182c97b6d02e4259832b7b0756fc7f77"} +{"id": "val_00624", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["tests_are_truth", "auditability", "security_gates", "governance"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "096ece51ac1dcbb306a81a79bcd6406615a805a5"} +{"id": "val_00625", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["governance", "ci_integration", "security_gates", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b1c8d7009406d784fdb651cdc16f7aa59024e22a"} +{"id": "val_00626", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "governance", "tests_are_truth", "reproducibility"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5f216cfdbe2fa54bef42e7c3988e2ff1bc6513e7"} +{"id": "val_00627", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "auditability", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c63c9102fa395af58cac038b924c0e5fa93cc6de"} +{"id": "val_00628", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "governance", "repo_scale_reasoning", "evaluation_metrics"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d1abd9b30a5e70d95a928223501e3c18019315d6"} +{"id": "val_00629", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "security_gates", "auditability", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9c216346d4c10ce0291b062f66a6e7f41968642b"} +{"id": "val_00630", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "auditability", "reproducibility", "governance"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "288bb1b86c4cb1b7c6e0b8c39103b2309fbd6385"} +{"id": "val_00631", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "tests_are_truth", "documentation", "cost_latency_tradeoffs"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5cfa908d17cf4eb3f5c3b862eacd56dd10729fd8"} +{"id": "val_00632", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["auditability", "ci_integration", "tests_are_truth", "governance"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "82ff61824d05ec68609a38016e9e4dcb004c47f1"} +{"id": "val_00633", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "reproducibility", "documentation", "evaluation_metrics"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5976639c522c4bcb35f7f7e15bf16b06ae114bdd"} +{"id": "val_00634", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tests_are_truth", "reproducibility", "tooling", "cost_latency_tradeoffs"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d06bbdb533a1b899631b1ab1d39b2dcb6f2cb043"} +{"id": "val_00635", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "reproducibility", "security_gates", "governance"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "170aee58e1c2b7ea00350ca1b1adc1d27af25a0f"} +{"id": "val_00636", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "evaluation_metrics", "governance"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "93bc75d6d68218e24a5c1379ffed93c4d1444572"} +{"id": "val_00637", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["governance", "security_gates", "cost_latency_tradeoffs", "tests_are_truth"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "db71a26db7f47ffd4e74a1893859906cf1d6766e"} +{"id": "val_00638", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "governance", "tests_are_truth", "security_gates"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2be88a2f9a411c24e21c9b8e392699eabfef58d3"} +{"id": "val_00639", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["governance", "reproducibility", "tooling", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "df0646b3eee38852a887bcf11dabbde677e5b5a1"} +{"id": "val_00640", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["documentation", "cost_latency_tradeoffs", "governance", "ci_integration"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c88a1545522e11c2af630c310a1e92450341709a"} +{"id": "val_00641", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "tests_are_truth", "documentation", "governance"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0497b58493edb67906620bce10cc7eb24d41a562"} +{"id": "val_00642", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tests_are_truth", "security_gates", "repo_scale_reasoning", "tooling"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2d23dd82c272ee58bd914005f76fb70a260ab784"} +{"id": "val_00643", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "security_gates", "tests_are_truth", "governance"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8caceb915181228be977f49aa2bb6162cff171cd"} +{"id": "val_00644", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "ci_integration", "cost_latency_tradeoffs", "tests_are_truth"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f346aaf08f021fb592e01985fae800c81cf4fbf9"} +{"id": "val_00645", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "ci_integration", "security_gates"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0e7278895535c4ff6bba2f816a56bfdb640fe930"} +{"id": "val_00646", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "security_gates", "repo_scale_reasoning", "tests_are_truth"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "73a744dd564c7e9a0dee1764f2ad57ea589eb407"} +{"id": "val_00647", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "ci_integration", "evaluation_metrics", "auditability"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "eb6c4be42320321f15fe6296f59b2bf601943e81"} +{"id": "val_00648", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["auditability", "tests_are_truth", "repo_scale_reasoning", "tooling"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1f914b6966c8707f3de1c85d2ed1d67300f72b07"} +{"id": "val_00649", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "tooling", "auditability", "security_gates"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "327ada0846cc3ebe47e0fab8732d6113f811983d"} +{"id": "val_00650", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "auditability", "ci_integration", "cost_latency_tradeoffs"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5e5da117f8390220839069629c37076445641ac3"} +{"id": "val_00651", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["security_gates", "auditability", "tests_are_truth", "ci_integration"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6ed63d2e92b725c261cdf56338923254c71cde46"} +{"id": "val_00652", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["auditability", "cost_latency_tradeoffs", "governance", "evaluation_metrics"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c6e65d8391f361c5556d501bbfe96dd42c763750"} +{"id": "val_00653", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "tests_are_truth", "security_gates", "auditability"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fa38dafae1deb68de63804f69b7ed1aeb653fe95"} +{"id": "val_00654", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "governance", "security_gates", "reproducibility"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8d8bdb9b775caddfde99f0683811a65d84389cbb"} +{"id": "val_00655", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "tests_are_truth", "repo_scale_reasoning", "auditability"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cc361847b4b304b67e51d8c68b8b719ac1b24bed"} +{"id": "val_00656", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "ci_integration", "tooling", "auditability"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fd6e07f9d77941bb0eae8271b97013311ce22133"} +{"id": "val_00657", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["documentation", "security_gates", "auditability", "reproducibility"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "411fad2efda8631649dd40235eff42f7ef66a309"} +{"id": "val_00658", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["governance", "documentation", "tooling", "ci_integration"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6c0f48df440d5eb3fe77e651cda5c3a4ad7a319a"} +{"id": "val_00659", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "auditability", "documentation", "tests_are_truth"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4876c7627bec5804faa8c790dc1ac1ad5dcaf4a3"} +{"id": "val_00660", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["auditability", "tooling", "cost_latency_tradeoffs", "reproducibility"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c99292056d98c31eb1a583967c8cdb8d33a667b3"} +{"id": "val_00661", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "governance", "auditability", "evaluation_metrics"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "69dba35c2384177e4ccf7abccb57c5c07b326dfe"} +{"id": "val_00662", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "repo_scale_reasoning", "tooling"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "629ea52fe3f88e076cd410b6b88e2c8254e8ed2e"} +{"id": "val_00663", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "cost_latency_tradeoffs", "security_gates", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "212fd619d9dc946a5baf698982795a332c3523de"} +{"id": "val_00664", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "repo_scale_reasoning", "cost_latency_tradeoffs", "reproducibility"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1024fa3569426561e444de15811b9d0ca258f0b6"} +{"id": "val_00665", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "documentation", "tests_are_truth", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2fe14a714e2d923a836e9836a95e9713ca2caa4b"} +{"id": "val_00666", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["tests_are_truth", "documentation", "security_gates", "tooling"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f104700d81732069f945b8a9e01f460e8818b609"} +{"id": "val_00667", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "evaluation_metrics", "tests_are_truth", "documentation"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ab21195765124b88c88de0a966ab6aa2071ef63d"} +{"id": "val_00668", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["governance", "reproducibility", "cost_latency_tradeoffs", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4bbc41f0da1d7d7a4d6867babeee4a8db05b57ef"} +{"id": "val_00669", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["auditability", "repo_scale_reasoning", "cost_latency_tradeoffs", "security_gates"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "888f7c1cbc2a27a53a4aa9d09e43edd992b3a4fa"} +{"id": "val_00670", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "repo_scale_reasoning", "governance", "tests_are_truth"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c0bad43b8e4c4f93f361c490f867560915ad7da3"} +{"id": "val_00671", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "auditability", "tests_are_truth", "governance"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c7cce51c0cd9263102dd47f8d749ff0bd280f423"} +{"id": "val_00672", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "cost_latency_tradeoffs", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c6a8e59652088955c7907115c5acabb04e0e0cbe"} +{"id": "val_00673", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "repo_scale_reasoning", "tests_are_truth", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "07a69f61710db9e665370538306ea6ae62220b31"} +{"id": "val_00674", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "cost_latency_tradeoffs", "security_gates", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "622a8bf1395c518c283edbed16c96d0834ebaf72"} +{"id": "val_00675", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "repo_scale_reasoning", "documentation", "evaluation_metrics"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d5002a77096709517dd028501473baa241239038"} +{"id": "val_00676", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "repo_scale_reasoning", "reproducibility", "evaluation_metrics"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b7b902b0843079348a76cf5d1d0e325bbd71274e"} +{"id": "val_00677", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "tooling", "auditability", "evaluation_metrics"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "33bdc23be6076b9f9a2a10571dc6130144e3e544"} +{"id": "val_00678", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["documentation", "ci_integration", "auditability", "evaluation_metrics"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2dfa8e05ee13da8a287a3ea440cf51488d4ea63f"} +{"id": "val_00679", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["tooling", "cost_latency_tradeoffs", "evaluation_metrics", "tests_are_truth"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e68a0da6665682b104a06fdfb380eaea0dcfa6da"} +{"id": "val_00680", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "evaluation_metrics", "cost_latency_tradeoffs", "auditability"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cbf4a4f463c5a7b3539328f37105ca6a4e6ec51c"} +{"id": "val_00681", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["documentation", "cost_latency_tradeoffs", "reproducibility", "ci_integration"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0c52ceb99b61ddfb1676fcc6cfe43029bde4f4c5"} +{"id": "val_00682", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "tooling", "cost_latency_tradeoffs", "tests_are_truth"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "888f7c1cbc2a27a53a4aa9d09e43edd992b3a4fa"} +{"id": "val_00683", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["tooling", "evaluation_metrics", "documentation", "auditability"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2543504549d1eda696b7560bdf87516f98bb8a4f"} +{"id": "val_00684", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "auditability", "repo_scale_reasoning"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e8d9cb1da200d672fa508e3df6ff66beba9f8968"} +{"id": "val_00685", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "ci_integration", "cost_latency_tradeoffs", "security_gates"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2a06ccda13f628819d2ec3608918e864dd109f85"} +{"id": "val_00686", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["evaluation_metrics", "security_gates", "repo_scale_reasoning", "ci_integration"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "be22b979faddcdc8d083825d30845d228fd9ba81"} +{"id": "val_00687", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "security_gates", "ci_integration", "auditability"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cf8bbcdfcd8c398e8cf9552ccb4938827ecf5ce5"} +{"id": "val_00688", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["cost_latency_tradeoffs", "tests_are_truth", "reproducibility", "governance"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0eedcebcb6133de89affeaa90df0fd3511e8a85d"} +{"id": "val_00689", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "auditability", "tests_are_truth", "cost_latency_tradeoffs"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "854204bf480e7a2a173cc5cd935a2564d8b86f70"} +{"id": "val_00690", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "governance", "tooling", "tests_are_truth"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "85f7d4287c2a7cd8d25da7c79f24ba85783adb8e"} +{"id": "val_00691", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "auditability", "documentation", "ci_integration"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2bae99aa8afb085fa0b6fca61190df915195a992"} +{"id": "val_00692", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "ci_integration", "governance", "reproducibility"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ad06a23af4b9925be759ecfd519796411c8c9694"} +{"id": "val_00693", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["auditability", "tooling", "documentation", "security_gates"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9a3053aff88bceaae54a1bc996ce4d4e7b593561"} +{"id": "val_00694", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "evaluation_metrics", "tests_are_truth", "auditability"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "647aba7b6399aadbf294c8af3f701f920434bd2b"} +{"id": "val_00695", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "evaluation_metrics", "repo_scale_reasoning", "tests_are_truth"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "834763ac97c15740ca5111141a2a28fb20cf77fc"} +{"id": "val_00696", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "reproducibility", "evaluation_metrics", "tooling"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "718e103d48919e91941db321175dce71d4c1ae64"} +{"id": "val_00697", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "repo_scale_reasoning", "governance", "cost_latency_tradeoffs"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "43229a28fd53b1decde62f3ed17ccd78d3d3c956"} +{"id": "val_00698", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "evaluation_metrics", "cost_latency_tradeoffs", "governance"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "06aea12865268a94865c0effbcbb77227a1c98a0"} +{"id": "val_00699", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "security_gates", "auditability"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c3e939c14600e9cd66f22f26be9b80f7efa00da5"} +{"id": "val_00700", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "afba720d1358075acb8057c4c1986c38239d6aad"} +{"id": "val_00701", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nScaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=4):\n history = []\n p = plan(issue)\n for _ in range(max_iters):\n patch = edit(issue, p)\n ok, report = test(patch)\n history.append({\"plan\": p, \"ok\": ok})\n if ok:\n return patch, history\n p = p + \" | refine\"\n return patch, history\n\n```\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "ci_integration", "security_gates", "governance"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "76af5f70f701944b18b0c00c539b2c450f02fd5a"} +{"id": "val_00702", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "auditability", "documentation", "security_gates"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "562289edea085b49f241c78b07f3f75016739dfc"} +{"id": "val_00703", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "reproducibility", "tooling", "documentation"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "81d848bdcd784a7f04c62c3e2f2799f86cf2eea0"} +{"id": "val_00704", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "documentation", "ci_integration", "evaluation_metrics"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b3eedea4a7d3716d75ef6bcf3d97eb9d0f29d36e"} +{"id": "val_00705", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "tests_are_truth", "reproducibility", "documentation"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bd6300f4313b4713c4e975a56133b70ef13e1a40"} +{"id": "val_00706", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "documentation", "tests_are_truth", "security_gates"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d24ddbd475cb7bf8b3e680269dc96028463de666"} +{"id": "val_00707", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "tests_are_truth", "repo_scale_reasoning", "documentation"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "36b356357d58e97e6feea84bf0bafd9d317d8791"} +{"id": "val_00708", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["governance", "evaluation_metrics", "reproducibility", "tests_are_truth"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fe9523f8281f043fe9c56172ab706ef3850ed93a"} +{"id": "val_00709", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "tooling", "auditability", "cost_latency_tradeoffs"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bde13b44e38bdcd4e84b3e87435ada12e04ace0e"} +{"id": "val_00710", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "cost_latency_tradeoffs", "governance", "tooling"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b30019b198a402048bb7d949a3ded373acf4844e"} +{"id": "val_00711", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["repo_scale_reasoning", "evaluation_metrics", "documentation", "auditability"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "54f90d9ff562a8071946763fde64d042fc0fac87"} +{"id": "val_00712", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "evaluation_metrics", "repo_scale_reasoning", "documentation"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "986fa607ac2986c771a312615e1ee3a734745917"} +{"id": "val_00713", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "cost_latency_tradeoffs", "auditability"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7e6898bceec258d36069737257012d3f3f1ba8de"} +{"id": "val_00714", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "tooling", "auditability", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "385a393b69d55cd1d57e32576a1635abce39d6b4"} +{"id": "val_00715", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "ci_integration", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6d3225c49b9b847f366bb2022f9bfc3a9c67b51b"} +{"id": "val_00716", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "cost_latency_tradeoffs", "tooling", "repo_scale_reasoning"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a45cdccf93070c29a30eec796489c8c2b74b877c"} +{"id": "val_00717", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tests_are_truth", "repo_scale_reasoning", "reproducibility", "tooling"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "abae2346d2f87f83f893e7b9bf8c56676607bb2a"} +{"id": "val_00718", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["auditability", "governance", "cost_latency_tradeoffs", "documentation"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e359c3a48fc14ba782cfe2fec3ec6c9d381af191"} +{"id": "val_00719", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "security_gates", "reproducibility"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a1cd5b6fd3562917f950a8bf8d68a356078c90cd"} +{"id": "val_00720", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "ci_integration", "documentation", "security_gates"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3c4656c710ceac33b9c5e0f2d3404c05e787cc3c"} +{"id": "val_00721", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "tests_are_truth", "governance", "auditability"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0aea0f1f70f0c8000e4095d0fc3336c1864b2bda"} +{"id": "val_00722", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "repo_scale_reasoning", "governance"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bbb464ee073a227d221f9a6c61b1ccff683b3343"} +{"id": "val_00723", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "repo_scale_reasoning", "documentation", "cost_latency_tradeoffs"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5e2673464801bdc44dd9a25070942471e5c208f5"} +{"id": "val_00724", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "auditability", "cost_latency_tradeoffs", "reproducibility"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1886f8b0611ab8ed38c03835d78c0ec1ee707f3c"} +{"id": "val_00725", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "tests_are_truth", "cost_latency_tradeoffs", "reproducibility"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d09e2ebba92e123d6ce6068dbcb7deeef30d5da4"} +{"id": "val_00726", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "documentation", "governance", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2fe14a714e2d923a836e9836a95e9713ca2caa4b"} +{"id": "val_00727", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "tooling", "ci_integration", "governance"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "695ac3cfa5c8d7b2aaf6ad107183be0461fa3457"} +{"id": "val_00728", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "auditability", "documentation", "ci_integration"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f4c14cc0fc365959d7a90afa572002c492af50eb"} +{"id": "val_00729", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "evaluation_metrics", "documentation", "cost_latency_tradeoffs"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "422299fbd10d02da0d7ce7de3c9d6f0d9ce235f8"} +{"id": "val_00730", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "tests_are_truth", "tooling", "cost_latency_tradeoffs"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6aef7e23c21d67a32bfba05b16c99bf73816a508"} +{"id": "val_00731", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "cost_latency_tradeoffs", "auditability", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6883e4f09772979a9938faee1921a7de45df18ab"} +{"id": "val_00732", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "repo_scale_reasoning", "governance", "reproducibility"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f3875f0f0aa729e265dbe052eaf28a236fa938ed"} +{"id": "val_00733", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "documentation", "tooling", "auditability"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e97a30ce647a6850298a885e6c28234b5513c54f"} +{"id": "val_00734", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "cost_latency_tradeoffs", "auditability"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7a9783cea5d90177a5b791d64127bdf238d3ff34"} +{"id": "val_00735", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "evaluation_metrics", "security_gates"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "01935169c094cc6dfd82aeddfcf6919aff10a5fe"} +{"id": "val_00736", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["governance", "security_gates", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d008a2e469279df12a991eca8e30a8b6c28d40f1"} +{"id": "val_00737", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["auditability", "tooling", "reproducibility", "ci_integration"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9f4d118f4c360e1f909612afd21fb1088e674bb8"} +{"id": "val_00738", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "governance", "ci_integration", "security_gates"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8bef0bf1b2dc941a52195b3ad7f3d1db4b11bd5a"} +{"id": "val_00739", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "evaluation_metrics", "tests_are_truth"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d078c570307305a501746be2d5f05463b43d2aaa"} +{"id": "val_00740", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["cost_latency_tradeoffs", "documentation", "security_gates", "reproducibility"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1a303d8f0b9ea3be2014c6ba89eab86df035ceeb"} +{"id": "val_00741", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "governance", "reproducibility", "documentation"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4edea9dc10d77999ae4e69f6a7d2eb2c5279c538"} +{"id": "val_00742", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "ci_integration", "auditability", "cost_latency_tradeoffs"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9294e03fbd30a18b0221a09d36e0a1b9c69a2910"} +{"id": "val_00743", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["auditability", "tests_are_truth", "documentation", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9092493249bf5ad15d4efbc2bba2982a55c54031"} +{"id": "val_00744", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["governance", "tooling", "reproducibility", "ci_integration"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f5f45192a044d6ad0f9e17647ab4a91da685a277"} +{"id": "val_00745", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "security_gates", "reproducibility", "ci_integration"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ebdac0c8a15fdbe143d21f58aad2d5c0bf1266b9"} +{"id": "val_00746", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["tooling", "evaluation_metrics", "governance", "auditability"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3d2f4b30364cf14638e3a7a163be5ab815329340"} +{"id": "val_00747", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["repo_scale_reasoning", "security_gates", "auditability", "ci_integration"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a7f39a2eabe384fe5a753dce8e2377a46758da43"} +{"id": "val_00748", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "ci_integration", "cost_latency_tradeoffs", "auditability"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2708d552ceec24abcb6a87a5afcd198f718b1ad1"} +{"id": "val_00749", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "tooling", "tests_are_truth", "documentation"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4e8fd12f7909a302748d10c4f8f8c807e4093a2d"} +{"id": "val_00750", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["auditability", "tests_are_truth", "cost_latency_tradeoffs", "tooling"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "913d4f47093e32f070b8643b636815c0aa7b785a"} +{"id": "val_00751", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "reproducibility", "repo_scale_reasoning", "security_gates"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "dd39ee8f67a4f7aa6531fb35bc8442276fa2ad2e"} +{"id": "val_00752", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "auditability", "governance", "documentation"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6ef41f2ce9da4a95da6f24ea02c94ac6f3178df2"} +{"id": "val_00753", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "ci_integration", "cost_latency_tradeoffs", "security_gates"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "06fa193e412dd08011f111e0e07490e2d44cc85b"} +{"id": "val_00754", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "governance", "auditability", "cost_latency_tradeoffs"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ffb640a62586ab1c908c112eb030526dbc63ee24"} +{"id": "val_00755", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["cost_latency_tradeoffs", "evaluation_metrics", "tests_are_truth", "ci_integration"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9e528dafeb58b56aae093551b7cf5e16046ad083"} +{"id": "val_00756", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "tooling", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b32a4379510ba1e8fcfe1e6aa50b19345efc1032"} +{"id": "val_00757", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "evaluation_metrics", "governance", "cost_latency_tradeoffs"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "56d3659565d80fdc36e056f30b05a59872517988"} +{"id": "val_00758", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "tooling", "reproducibility", "ci_integration"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "861372f45563d49d95a880e7cfcb750d7031792f"} +{"id": "val_00759", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "tests_are_truth", "governance", "documentation"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e16848fa009f266879e207b7ec4f6344040449db"} +{"id": "val_00760", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "auditability", "reproducibility", "documentation"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4ea35580e409eb99bb5a99e17254c1ea1ed9eb32"} +{"id": "val_00761", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "auditability", "cost_latency_tradeoffs", "tooling"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1d0ee659d3afdacd8926114c3c56ef0c800e17e1"} +{"id": "val_00762", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "governance", "repo_scale_reasoning", "reproducibility"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "248adb0fb38147e3c02d32519e5d5b39add2ff97"} +{"id": "val_00763", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["governance", "tooling", "tests_are_truth", "security_gates"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "546879b328d462051b1b6a35b4023567d2508e5c"} +{"id": "val_00764", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["evaluation_metrics", "tests_are_truth", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4a96fd8511d84102206b2d4b21d23dc4653e9bb7"} +{"id": "val_00765", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "repo_scale_reasoning", "cost_latency_tradeoffs", "governance"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "db3ca86ffbb854adbce52e90bf61cb4471d4b91d"} +{"id": "val_00766", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["tests_are_truth", "ci_integration", "documentation", "security_gates"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "68424145e971815920b2fcfaf26d1b4d8785f642"} +{"id": "val_00767", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "auditability", "reproducibility"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "787e870cae58da2bca0cb25c6be09c8ac506be81"} +{"id": "val_00768", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "security_gates", "auditability", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9fea1f6a832aa4e72e48bb4df5d4f6c2d3d70df3"} +{"id": "val_00769", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["tests_are_truth", "ci_integration", "reproducibility", "security_gates"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "76f643fa289ca25a2a4fefe029af368ba1f598ab"} +{"id": "val_00770", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "security_gates", "repo_scale_reasoning", "governance"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f0ae334f216fd2d603ebbac8d83d78d8689cb942"} +{"id": "val_00771", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["governance", "tests_are_truth", "tooling", "ci_integration"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9e348d35895987db20383dec1283b7d935c171fb"} +{"id": "val_00772", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["documentation", "evaluation_metrics", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "53dffe64dbe6eea233108c297844e9c5f6a97a87"} +{"id": "val_00773", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "reproducibility", "ci_integration", "security_gates"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "efe00d90b0a1a29d29879048e31b2640077b0cb5"} +{"id": "val_00774", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "cost_latency_tradeoffs", "ci_integration", "security_gates"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5c4c9ee63503dae5156bc3b25a4d65579f4eb3ee"} +{"id": "val_00775", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "tooling", "security_gates", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "28d08a3295bdebe1cb2c29f9db62470426cf62ce"} +{"id": "val_00776", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["governance", "ci_integration", "reproducibility", "auditability"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "33e1cdb79f1c9625e42c103203bda86d39f97964"} +{"id": "val_00777", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "tests_are_truth", "auditability", "tooling"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7f78201193d3c9428c67bac795b5a039a76add2d"} +{"id": "val_00778", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "security_gates", "governance", "ci_integration"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "716244f33ad0a93fb99c33cdca8b1bc9e767ec34"} +{"id": "val_00779", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "documentation", "security_gates"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c941f2036ec6041d8542950f43fca1bccebe8dd0"} +{"id": "val_00780", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "governance", "evaluation_metrics", "auditability"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a0d54473b49d84c6147d7056073e6b2111933156"} +{"id": "val_00781", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["reproducibility", "tests_are_truth", "security_gates", "documentation"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3463497bd8951c9c9662a8f43f2a5d6b52a78c24"} +{"id": "val_00782", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "cost_latency_tradeoffs", "governance", "tests_are_truth"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a497cb0d91eb3b8720d2730c001d26e8a8eb0162"} +{"id": "val_00783", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "evaluation_metrics", "tests_are_truth", "tooling"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ac87c3d72d6b7fff06f0f1c9b87534f94a662e15"} +{"id": "val_00784", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "documentation", "auditability", "tooling"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "56229da2f426577bdbab396ebdf05207b484b76b"} +{"id": "val_00785", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "reproducibility", "tooling", "repo_scale_reasoning"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ec03340f5b15f3dcec64acda17035200ddbbd4f5"} +{"id": "val_00786", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "reproducibility", "auditability", "security_gates"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ef62a8d27c63472b9707b9d40827a770f415dd83"} +{"id": "val_00787", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["governance", "security_gates", "repo_scale_reasoning", "cost_latency_tradeoffs"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "02e58272c04d7c53a062e4f73867dd96881ab4c6"} +{"id": "val_00788", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["tests_are_truth", "documentation", "auditability", "evaluation_metrics"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ac72625ff6c7339ecc9b20bc890e97cd36f28361"} +{"id": "val_00789", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["tests_are_truth", "evaluation_metrics", "auditability", "security_gates"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "69a3f89f39702ee4b27c57398c8b1def49f40712"} +{"id": "val_00790", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["security_gates", "documentation", "repo_scale_reasoning", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0e28c085e1ba2ffcb2f04d52d8ef57c65dde5deb"} +{"id": "val_00791", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "evaluation_metrics", "governance", "documentation"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "79fcf052686e970dcdc5c6cfa726dda56f03e9df"} +{"id": "val_00792", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["repo_scale_reasoning", "auditability", "cost_latency_tradeoffs", "security_gates"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0595739edf2316af653519ca1276c21e6fbe762b"} +{"id": "val_00793", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "tooling", "security_gates", "evaluation_metrics"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d08016954e0f0cf6435469ea00d4d88bc523c878"} +{"id": "val_00794", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "governance", "documentation", "cost_latency_tradeoffs"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f75fa30ca3c7c6babbf0583c2384cee1f17f5c96"} +{"id": "val_00795", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["cost_latency_tradeoffs", "evaluation_metrics", "tooling", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "76b8e73949d7586e09cc1d1a997ba50e5cc9b4d5"} +{"id": "val_00796", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "security_gates", "ci_integration", "tooling"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bd080ecae3014e0ac3c0c951b1f8f322a908fcdd"} +{"id": "val_00797", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "tests_are_truth", "security_gates", "ci_integration"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bd173b0ca2d9488fae2105fbf12c400308d28312"} +{"id": "val_00798", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["tests_are_truth", "security_gates", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "07dcace3016de9db694229975fe14e4d057637c4"} +{"id": "val_00799", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "reproducibility", "documentation", "evaluation_metrics"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5ad213088ebfa4db02c4b9df9d1c1397abd0a7b7"} +{"id": "val_00800", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "repo_scale_reasoning", "evaluation_metrics", "security_gates"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "279227a82e65bdd4549abc601f6a029b126ab61b"} +{"id": "val_00801", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["documentation", "security_gates", "ci_integration", "reproducibility"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "01f858482c732721a1d6bff9ae4dcf9cfa6e2d3c"} +{"id": "val_00802", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "cost_latency_tradeoffs", "ci_integration", "auditability"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d9c64480a9d618baaa79a4dbfdbd4911deacf03d"} +{"id": "val_00803", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "tooling", "ci_integration", "repo_scale_reasoning"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6967c89777e2691c882678731b7d91e73ca2b788"} +{"id": "val_00804", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["security_gates", "documentation", "reproducibility", "ci_integration"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "674441381cafdd9eba6c85fc9615cb742703eafb"} +{"id": "val_00805", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nScaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=4):\n history = []\n p = plan(issue)\n for _ in range(max_iters):\n patch = edit(issue, p)\n ok, report = test(patch)\n history.append({\"plan\": p, \"ok\": ok})\n if ok:\n return patch, history\n p = p + \" | refine\"\n return patch, history\n\n```\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "governance", "ci_integration"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6a051352ae0f11f4871d21e35fba3026a71c5bb9"} +{"id": "val_00806", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "ci_integration", "reproducibility", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "20d10197250ae320a558c3dd8c0a70009e666ab3"} +{"id": "val_00807", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "documentation", "reproducibility", "governance"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6075d88683d53f041756c48b9826a62209bd4232"} +{"id": "val_00808", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "tooling", "evaluation_metrics", "governance"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3aeb0cbb224e6b8aec630233810f401f5615b1fc"} +{"id": "val_00809", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["evaluation_metrics", "tooling", "cost_latency_tradeoffs", "documentation"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6b69dfe7be2e69a4e54993346a66298006fb7228"} +{"id": "val_00810", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["evaluation_metrics", "reproducibility", "auditability", "security_gates"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1e9eac9a77a4bf1be04128a44af2f46c23191618"} +{"id": "val_00811", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["security_gates", "repo_scale_reasoning", "documentation", "reproducibility"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "919f8e8a825204f9e680c9382eb80052719e4475"} +{"id": "val_00812", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "tests_are_truth", "ci_integration", "reproducibility"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "522dd8179c510e5d4519301d04228eab536f5c55"} +{"id": "val_00813", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "evaluation_metrics", "cost_latency_tradeoffs", "documentation"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "476868835a06bc800888d182d28587ae799da304"} +{"id": "val_00814", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "security_gates", "repo_scale_reasoning", "documentation"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "655d9fcd55ac7a254feb7c7f32367d05b6151dda"} +{"id": "val_00815", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["tests_are_truth", "tooling", "reproducibility", "auditability"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "01dee36d3b30a4b4a8b4574f3d96cf839f3f82c5"} +{"id": "val_00816", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["governance", "evaluation_metrics", "ci_integration", "auditability"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5860918d116d86dd0acc121c9a16973feee9baee"} +{"id": "val_00817", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "tests_are_truth", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "03545badabc72deddaaa02eca279212c8cb197bf"} +{"id": "val_00818", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tooling", "tests_are_truth", "reproducibility", "ci_integration"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b55927dad577b798a18b20fc800194c722383a6e"} +{"id": "val_00819", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "security_gates", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bcdad556f625a8755df8080ff4def0e95d1be9b4"} +{"id": "val_00820", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "tooling", "documentation", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "375627ae41815fc4fc3ac3e7cdee117698899079"} +{"id": "val_00821", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "tests_are_truth", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0392945190ca56b272d05d5bbce244f1774e2dda"} +{"id": "val_00822", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["governance", "repo_scale_reasoning", "ci_integration", "reproducibility"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7363c627c1f7687b1b5d0b3fb43ea2195803be63"} +{"id": "val_00823", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["cost_latency_tradeoffs", "governance", "evaluation_metrics", "tooling"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "75ab7b4b21d8dffc4be6790c38064564d1869c45"} +{"id": "val_00824", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["security_gates", "governance", "cost_latency_tradeoffs", "documentation"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "856e7afdfa88603b73e332a73e27eb44bc673587"} +{"id": "val_00825", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "governance", "tests_are_truth", "reproducibility"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f9eea1f7877a03d1428d1af755e8eaf9fca13c26"} +{"id": "val_00826", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: C#\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["cost_latency_tradeoffs", "auditability", "documentation", "reproducibility"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d7b3b8a90e5e137f9a82e04eb1401842784b09cb"} +{"id": "val_00827", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "security_gates", "governance", "auditability"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1e8dcf7d65ab28fd7cc476b217757c979f7f150c"} +{"id": "val_00828", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Rust\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["governance", "evaluation_metrics", "tests_are_truth", "documentation"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f70c41d07eec8e1edb6056755a47540d43ee2173"} +{"id": "val_00829", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["security_gates", "reproducibility", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fac310d7d385e1c4832e3d89be4f36d8e89194c2"} +{"id": "val_00830", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "ci_integration", "cost_latency_tradeoffs", "tooling"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d071f1bf0f32c7c554373ccd1d8b1ac6a90e1b16"} +{"id": "val_00831", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "documentation", "evaluation_metrics", "reproducibility"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3be385c74396685ce2387b13123ab3a7af4f3b99"} +{"id": "val_00832", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "repo_scale_reasoning", "documentation", "tests_are_truth"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "aa0de43774851cf84ef703198ee12cd2922e0917"} +{"id": "val_00833", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "evaluation_metrics", "documentation", "auditability"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "253a05b716a12460724a5f0d69076cfc7c62989d"} +{"id": "val_00834", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "ci_integration", "reproducibility", "auditability"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8df91c2c297fdebb6aeefc5a652edacc9c19a030"} +{"id": "val_00835", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["governance", "evaluation_metrics", "repo_scale_reasoning", "documentation"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b8e585307df0095c6e25ec5c47b1b7320a4d8161"} +{"id": "val_00836", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "governance", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1a57f4743fad107200cd0c3402fd90a8df1d4dcb"} +{"id": "val_00837", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "evaluation_metrics", "governance", "tests_are_truth"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "56b4edd5324ae1b474aea3edcbaeaa64d7f1e59f"} +{"id": "val_00838", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["auditability", "governance", "tooling", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a1ad92aae4ef4d7585829795917a4f2ad9b5be9c"} +{"id": "val_00839", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "governance", "tests_are_truth", "reproducibility"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fbf861e83568a23b8d2b2a0114f4e5178022a991"} +{"id": "val_00840", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "repo_scale_reasoning", "tooling", "auditability"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4733490befe5e2f8d001205c280af0d68d656fea"} +{"id": "val_00841", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "tooling", "repo_scale_reasoning", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "eb24e5864c14ec346b4b099dac25f1eb273e66c6"} +{"id": "val_00842", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "reproducibility", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8050253e897ee59a88c76093a9f1e2a4fb4a2794"} +{"id": "val_00843", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["tests_are_truth", "reproducibility", "documentation", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "88ad90bf7b0a5389336468e603cb68bb847b4ae6"} +{"id": "val_00844", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "governance", "repo_scale_reasoning", "tooling"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cbe7a6d1379a5b8fcb3cf70b36c27d3a453205b0"} +{"id": "val_00845", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: expert\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "tests_are_truth", "evaluation_metrics", "ci_integration"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "253a05b716a12460724a5f0d69076cfc7c62989d"} +{"id": "val_00846", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "tests_are_truth", "repo_scale_reasoning", "governance"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ab79efa2a9b406afbbc76ce74b93ded7626b4019"} +{"id": "val_00847", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["tooling", "reproducibility", "evaluation_metrics", "documentation"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b36018df692e45d485fc6fc38ed641eb95c11528"} +{"id": "val_00848", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "evaluation_metrics", "tooling", "governance"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2ba4b32643d12aa8e46287d4bb186ec4868fa504"} +{"id": "val_00849", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["documentation", "auditability", "reproducibility", "ci_integration"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "28bd68ca16324f00515312881ffa1f036196c17c"} +{"id": "val_00850", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "tooling", "repo_scale_reasoning", "evaluation_metrics"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3645940aefd5de8590ceb13d0ce732a04732b1bf"} +{"id": "val_00851", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "evaluation_metrics", "governance"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "63893d19fa45a7e30a3ddbbfcc771325fc8ad030"} +{"id": "val_00852", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "repo_scale_reasoning", "tooling", "tests_are_truth"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f8ee4bb00c3fceade8c5e19f63c1ccdcb8c4a51c"} +{"id": "val_00853", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "ci_integration", "reproducibility", "cost_latency_tradeoffs"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "428e6c9f8d70dc9fd7482c4b7b7f0caa60d8a7a6"} +{"id": "val_00854", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "reproducibility", "evaluation_metrics"], "moe_experts": ["governance_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2e329dd54e38c2c42ce36f03a4ea792cb01c0658"} +{"id": "val_00855", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["auditability", "evaluation_metrics", "tooling", "security_gates"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0e600fb5425983a2f830e226d30eba563dd441ca"} +{"id": "val_00856", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["auditability", "tests_are_truth", "security_gates", "ci_integration"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8ca6df4f0cf342c0ec54af62aa1e61e3dba53f55"} +{"id": "val_00857", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "governance", "auditability", "tooling"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a8298c3e85ec586dd2b712db3468d51e2c85844d"} +{"id": "val_00858", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "security_gates", "tests_are_truth", "tooling"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "39d8a5dc321d3ff6d8fde8ceaa3d626cfead741b"} +{"id": "val_00859", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "reproducibility", "ci_integration", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "86b98cc8bdd12e7af85c79a968e16c11ae16d23b"} +{"id": "val_00860", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "reproducibility", "evaluation_metrics", "governance"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "635d74d740cb990fb59074577953e28fa289b7c3"} +{"id": "val_00861", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "tooling", "security_gates", "repo_scale_reasoning"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a7e252071df823f941fdd65de0a6205fc89757ce"} +{"id": "val_00862", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "auditability", "ci_integration", "reproducibility"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "eee5edb079c48b84fd6310e0a029284d080cb01d"} +{"id": "val_00863", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "repo_scale_reasoning", "tooling", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2657afa036d5ed5ce553194a90582e24c8f5c81f"} +{"id": "val_00864", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "reproducibility", "security_gates", "evaluation_metrics"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "81b97909062fbf3c9e068032042069a5d47c2d1b"} +{"id": "val_00865", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "governance", "tooling", "auditability"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6845c5fbbd7e15112b1ea811bab15bb404fee310"} +{"id": "val_00866", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "repo_scale_reasoning", "tooling", "tests_are_truth"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "883f923ef8fa2c8887bece876e12b1f1f67a3695"} +{"id": "val_00867", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "governance", "security_gates"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0a3a6a5a25bc8153dab601b14b40ea5fc220d694"} +{"id": "val_00868", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: advanced\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "ci_integration", "documentation"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d3f4266e804c22d4a2844f6bad8ad679fd44e1e0"} +{"id": "val_00869", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "reproducibility", "tests_are_truth", "tooling"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d72cc3d3fabe7c546eab1ef9a8373dabf5be5d2e"} +{"id": "val_00870", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "evaluation_metrics", "governance", "security_gates"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d360736e52c5e6ea95574fb05cad8b668bdad338"} +{"id": "val_00871", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["documentation", "tests_are_truth", "security_gates", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "006387ceb4bc165c398f216dc92dc6fdbfe3030d"} +{"id": "val_00872", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "tests_are_truth", "governance"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e69dd797687dd8726ae30bbea84094697b7bdfd4"} +{"id": "val_00873", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["ci_integration", "documentation", "tests_are_truth", "tooling"], "moe_experts": ["agentic_systems_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1e86d8dffd0b36132b4b7a7e2ac479c3c4438d95"} +{"id": "val_00874", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["auditability", "tooling", "repo_scale_reasoning", "reproducibility"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ac29755b8471a09c12f017e6e6c3299eb05e1fe1"} +{"id": "val_00875", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "cost_latency_tradeoffs", "evaluation_metrics", "security_gates"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b16d1a598d9b27b7b513f243eb82132d86c0f941"} +{"id": "val_00876", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "ci_integration", "reproducibility", "security_gates"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0430b74031480ded46a942d0723e751bd9844640"} +{"id": "val_00877", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["ci_integration", "documentation", "cost_latency_tradeoffs", "repo_scale_reasoning"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "10fc2bff648a6353a07ba8e35e60c6cf5e46d1fc"} +{"id": "val_00878", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "evaluation_metrics", "tests_are_truth", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7c368f1cbf38cb216504c136de12407c647f233b"} +{"id": "val_00879", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "data_pipeline", "difficulty": "expert", "instruction": "Task: data_pipeline\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "evaluation_metrics", "cost_latency_tradeoffs", "governance"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "63478e3c18029c0a7a6ea05f53acb01d1e9053e8"} +{"id": "val_00880", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["ci_integration", "repo_scale_reasoning", "security_gates", "governance"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1087713866939887d947f06be605f1b69be33bbb"} +{"id": "val_00881", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "ci_integration", "evaluation_metrics", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3d14d5b86e126931c7b1a64bf4ea5ecaaf384c0e"} +{"id": "val_00882", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "governance", "auditability"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "36fec1eb406b8fb922e3203be013609880edb6bb"} +{"id": "val_00883", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: expert\nTarget language: SQL\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["tests_are_truth", "reproducibility", "cost_latency_tradeoffs", "tooling"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "24942ec508063fc7b42c07ec544bfc0169f706e5"} +{"id": "val_00884", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "ci_integration", "repo_scale_reasoning", "security_gates"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "eddc5b458e9729f358bc33752b5d4cfec45cf79d"} +{"id": "val_00885", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["governance", "auditability", "ci_integration", "tooling"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0c08f5c7956190a10f8ae573b5554ea3586f39e5"} +{"id": "val_00886", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "intermediate", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: intermediate\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "documentation", "ci_integration", "tests_are_truth"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a38041335c201c52edd01f17d1e697edc7c48e10"} +{"id": "val_00887", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "cost_latency_tradeoffs", "tooling", "reproducibility"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "fe8ae829990c97fa904c86b5cbbe795594ee40ed"} +{"id": "val_00888", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["tooling", "documentation", "governance", "auditability"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "463d403136c44ac8064641ba6f6753192218f877"} +{"id": "val_00889", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["governance", "cost_latency_tradeoffs", "auditability", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8573db12577bc47d449d78a0044464068155ca5b"} +{"id": "val_00890", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "auditability", "security_gates", "tooling"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1cbdbb46984c0489627834d9b17d0adfefb30900"} +{"id": "val_00891", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "reproducibility", "cost_latency_tradeoffs", "evaluation_metrics"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a4dd36662148c54c4e3d0f4b8ee3789e60187b72"} +{"id": "val_00892", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["ci_integration", "tooling", "reproducibility", "tests_are_truth"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7e4e7c8efae745cb85f4801975c4deaeb2b05740"} +{"id": "val_00893", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "repo_scale_reasoning", "evaluation_metrics", "tests_are_truth"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e1681229f4834c232534e3fc5bd2bdee10b88a88"} +{"id": "val_00894", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["tooling", "ci_integration", "governance", "documentation"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ba24c042848c2a8bf7a0aed7b71904283e22a2ca"} +{"id": "val_00895", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Latency, cost, and reliability optimization\nDifficulty: intermediate\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "ci_integration", "security_gates", "evaluation_metrics"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f095d746bcf6695a1b998c1db9654c74c9ff9139"} +{"id": "val_00896", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "ci_integration", "governance"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "af465ffdafa86a596384ffb9bb23374b947a1628"} +{"id": "val_00897", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["auditability", "evaluation_metrics", "tests_are_truth", "ci_integration"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cfbd03f2cba2f868e40d7c3534e0062ddee1b04c"} +{"id": "val_00898", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["tests_are_truth", "evaluation_metrics", "repo_scale_reasoning", "tooling"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "422299fbd10d02da0d7ce7de3c9d6f0d9ce235f8"} +{"id": "val_00899", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["documentation", "auditability", "security_gates", "tooling"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "30a63cfd52e893a05a4b59ed924a5d5ce10f5218"} +{"id": "val_00900", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["ci_integration", "tooling", "tests_are_truth", "documentation"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "aaf91a093e92550408a8960e9636380eb6db33c5"} +{"id": "val_00901", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["ci_integration", "evaluation_metrics", "governance", "repo_scale_reasoning"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6f80196915192b409205d8dd63f83d40a641e9b2"} +{"id": "val_00902", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tooling", "auditability", "reproducibility", "documentation"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d0cfe039fd3f8b278acdfe123df8e9fffb9c82ae"} +{"id": "val_00903", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["tests_are_truth", "tooling", "repo_scale_reasoning", "auditability"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1115301701af81904a8bc8322df46bd8e6d2e46d"} +{"id": "val_00904", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "evaluation_metrics", "governance"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c0e1753cf47df3bd13fbda5ec1cb4369e10bd754"} +{"id": "val_00905", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "ci_integration", "security_gates", "tooling"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "57b24d372b63f95fcf74370cab614cd1aa4132b0"} +{"id": "val_00906", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: expert\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "security_gates", "governance", "evaluation_metrics"], "moe_experts": ["coding_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d939d9f766d1892a95d0b6f078168dbaec84c2b4"} +{"id": "val_00907", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "evaluation_metrics", "tooling", "security_gates"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "71e29496cdba2867c2fe9ca0481ce2b9b06306b1"} +{"id": "val_00908", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "security_gates", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "028c30d4fda3a86dc74016af63e9ecde2b169a5b"} +{"id": "val_00909", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "governance", "cost_latency_tradeoffs", "auditability"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "56384012a60417dbf7d1e8191b3acdbecd6d6151"} +{"id": "val_00910", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["repo_scale_reasoning", "governance", "security_gates", "cost_latency_tradeoffs"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "dd842111904b5364844a0d1298e001ad58c9d322"} +{"id": "val_00911", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: JavaScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "evaluation_metrics", "repo_scale_reasoning", "reproducibility"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "979833cfe99d9193ea7e55bef1d15c221f5ecef3"} +{"id": "val_00912", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "repo_scale_reasoning", "cost_latency_tradeoffs", "tooling"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f7d60c1562a3ea10ead990825479271f6a71412b"} +{"id": "val_00913", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["evaluation_metrics", "tests_are_truth", "tooling", "governance"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "438f37efadcc9c33da7a8d58f2da8841d840acef"} +{"id": "val_00914", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: intermediate\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nScaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=4):\n history = []\n p = plan(issue)\n for _ in range(max_iters):\n patch = edit(issue, p)\n ok, report = test(patch)\n history.append({\"plan\": p, \"ok\": ok})\n if ok:\n return patch, history\n p = p + \" | refine\"\n return patch, history\n\n```\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["cost_latency_tradeoffs", "documentation", "evaluation_metrics", "tooling"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7606cf7bb103a4abad41ad28d6b6ec1d6b58a3cd"} +{"id": "val_00915", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "review", "difficulty": "advanced", "instruction": "Task: review\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["auditability", "security_gates", "documentation", "governance"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d6bf647af8b637ec37b15a701e1c97a4d8c09a15"} +{"id": "val_00916", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: intermediate\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["auditability", "cost_latency_tradeoffs", "security_gates", "ci_integration"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "dcc9b9b34cf4ed89793294b1adba85e699ee8cdc"} +{"id": "val_00917", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "tooling", "tests_are_truth", "documentation"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c217de961c2f09687a2759b705db1ed5b4fd15cf"} +{"id": "val_00918", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "evaluation_metrics", "governance", "documentation"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c95093a66e7b92c23fd416fc2c52e3d5e7dc4323"} +{"id": "val_00919", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["cost_latency_tradeoffs", "tooling", "tests_are_truth", "auditability"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1b1319cdf1fde96fa08c38f8ae00d683d3c77174"} +{"id": "val_00920", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "governance", "ci_integration", "tests_are_truth"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a7ea0415d92302841858ec39471a24920d245041"} +{"id": "val_00921", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "evaluation_metrics", "documentation", "cost_latency_tradeoffs"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "29aa54dfafe4d0da87f525119d3fa0954f8ea5b6"} +{"id": "val_00922", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["governance", "repo_scale_reasoning", "security_gates", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "10cebbd1408e8805d5c706b5e480ed223643efb3"} +{"id": "val_00923", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "expert", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["auditability", "tooling", "security_gates", "cost_latency_tradeoffs"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5752fbcd3793911cf195d52ac1ef91756fac9149"} +{"id": "val_00924", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: intermediate\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["auditability", "evaluation_metrics", "tooling", "ci_integration"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "afad5f6f483ae21944de9ab65904b836a5b0c357"} +{"id": "val_00925", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: Python\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "cost_latency_tradeoffs", "auditability", "security_gates"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "aa451e077559708cd3d7b9dae0dee3eb7bbfa2a3"} +{"id": "val_00926", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["cost_latency_tradeoffs", "tests_are_truth", "repo_scale_reasoning", "evaluation_metrics"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "537594a4e36ca12869b79b837b715dc7972c39d0"} +{"id": "val_00927", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["auditability", "evaluation_metrics", "reproducibility", "cost_latency_tradeoffs"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "40512d3b4ba04bce731a49ae664c29305fae2651"} +{"id": "val_00928", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["governance", "security_gates", "repo_scale_reasoning", "documentation"], "moe_experts": ["data_curation_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7216f9a197dbe5f35347ab7e11b99330bb083ca7"} +{"id": "val_00929", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: Go\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "tests_are_truth", "tooling"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "56a798059c23d7a4d300fc26020330bd549711e8"} +{"id": "val_00930", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "tests_are_truth", "reproducibility", "ci_integration"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0cb13ce8d15420f9eb018b0f4a5c70ade7a8b07d"} +{"id": "val_00931", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Self-improving agents and feedback loops\nDifficulty: advanced\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["cost_latency_tradeoffs", "evaluation_metrics", "repo_scale_reasoning", "governance"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4241a6dbfdc7e074d3eaff72b055d8968c6a18df"} +{"id": "val_00932", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "repo_scale_reasoning", "tooling", "reproducibility"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6eae90485645bff855410b838a0239c26fc2b25f"} +{"id": "val_00933", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "ci_integration", "tests_are_truth", "governance"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "7ada061021d94e5b805fdb57cbed064e130b686d"} +{"id": "val_00934", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["tests_are_truth", "documentation", "auditability", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "18b8a6cd6e976e370749dab790005ddfdb0fc6fb"} +{"id": "val_00935", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Go\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "documentation", "repo_scale_reasoning", "evaluation_metrics"], "moe_experts": ["performance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "48bcbd8c8999f54fa649a62e898d480932b3cbe3"} +{"id": "val_00936", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: intermediate\nTarget language: SQL\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["governance", "reproducibility", "ci_integration", "tooling"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "edcd5fe162b95ff34b5d2154b9e53581491c6817"} +{"id": "val_00937", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "evaluation_metrics", "cost_latency_tradeoffs", "tooling"], "moe_experts": ["evaluation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b0af11fa482f772ae419c241e167094171b09c89"} +{"id": "val_00938", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "documentation", "auditability", "tooling"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0a339fd28ce799b38b149aa2c32565fc2aa7d378"} +{"id": "val_00939", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "explain", "difficulty": "expert", "instruction": "Task: explain\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "ci_integration", "security_gates"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1e4ed37d728068041876c146683531eed5a613fd"} +{"id": "val_00940", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: C#\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "evaluation_metrics", "reproducibility"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "08af8efd783aeb7b7de77cb205ba09fa35855f34"} +{"id": "val_00941", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: Bash\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "evaluation_metrics", "governance", "ci_integration"], "moe_experts": ["performance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "1435a7e553ad2f468b5d7bbe26defc44c72f00b9"} +{"id": "val_00942", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: advanced\nTarget language: Go\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["governance", "ci_integration", "documentation", "evaluation_metrics"], "moe_experts": ["coding_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "0df5059ea3bcd89f44e894a02048ae6bccf40ca5"} +{"id": "val_00943", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["evaluation_metrics", "cost_latency_tradeoffs", "tooling", "ci_integration"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b0e68631065654b259e69c195790834cdca7ce0a"} +{"id": "val_00944", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "documentation", "tooling"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "d071f1bf0f32c7c554373ccd1d8b1ac6a90e1b16"} +{"id": "val_00945", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "governance", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["evaluation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "35df75918789d838fb46bf2616ba8b07abb77ac0"} +{"id": "val_00946", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["reproducibility", "ci_integration", "security_gates", "evaluation_metrics"], "moe_experts": ["coding_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "498453613423d9a197c377119b88731ef1f32b91"} +{"id": "val_00947", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["repo_scale_reasoning", "tooling", "governance", "reproducibility"], "moe_experts": ["governance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6259155f769d9ac7330b5fffc72c1b254ec9bbe5"} +{"id": "val_00948", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: expert\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "documentation", "auditability", "governance"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4331de68332cecd2ea0f0cc2d0f5b7ded1b17841"} +{"id": "val_00949", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Python\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["tooling", "reproducibility", "documentation", "tests_are_truth"], "moe_experts": ["performance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ade457347bf1f1f5a7994c5523cbcf29b5c32b85"} +{"id": "val_00950", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Java\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "ci_integration", "documentation", "security_gates"], "moe_experts": ["coding_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a0bf0c5bcc7d2472ebaefd1b811dbe3082321637"} +{"id": "val_00951", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Governance, provenance, and licensing for code data\nDifficulty: advanced\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["repo_scale_reasoning", "evaluation_metrics", "ci_integration", "cost_latency_tradeoffs"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "5cb8e9030f84e1f099c5a273b1d0f03e479b9e32"} +{"id": "val_00952", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: JavaScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "ci_integration", "tests_are_truth", "repo_scale_reasoning"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "16791bbb3017908aa7221f9d97a896d3e425ef46"} +{"id": "val_00953", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "patch_diff", "difficulty": "intermediate", "instruction": "Task: patch_diff\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: SQL\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "SQL", "developer_needs": ["documentation", "tooling", "evaluation_metrics", "auditability"], "moe_experts": ["evaluation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "97282068b17440043416189e4ef7dcedab40c3e5"} +{"id": "val_00954", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: Rust\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "governance", "tests_are_truth", "reproducibility"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "9762443951d03bb05c2ce971e259b7d96bf59d05"} +{"id": "val_00955", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Python\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "documentation", "governance", "repo_scale_reasoning"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "29a841c02be961e67a9f5206ea31a26f20b71000"} +{"id": "val_00956", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "auditability", "evaluation_metrics"], "moe_experts": ["governance_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b0a1ed613cc474eb3c6205201bd4efef1ce9e12f"} +{"id": "val_00957", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "eval", "difficulty": "intermediate", "instruction": "Task: eval\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: C#\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "evaluation_metrics", "documentation", "tests_are_truth"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c4d70c3494b2cf0c929137834d23a699420d2219"} +{"id": "val_00958", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "review", "difficulty": "expert", "instruction": "Task: review\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["documentation", "auditability", "reproducibility", "repo_scale_reasoning"], "moe_experts": ["coding_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f3875f0f0aa729e265dbe052eaf28a236fa938ed"} +{"id": "val_00959", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["governance", "security_gates", "tests_are_truth", "tooling"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "964251bcb2ec9dd3d931752262d0cb0264abd797"} +{"id": "val_00960", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "auditability", "security_gates", "documentation"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "353a7540b7e0761baa39a29e11baf300fc6f732f"} +{"id": "val_00961", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Self-improving agents and feedback loops\nDifficulty: expert\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tooling", "tests_are_truth", "evaluation_metrics", "auditability"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c01c64c7d004d93c47b9ec5bdfb7052eb07184e2"} +{"id": "val_00962", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Go", "developer_needs": ["auditability", "repo_scale_reasoning", "tests_are_truth", "evaluation_metrics"], "moe_experts": ["security_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "a6965227db9f47b5ae5a2ad843aa201195e75f8f"} +{"id": "val_00963", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Latency, cost, and reliability optimization\nDifficulty: expert\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["ci_integration", "repo_scale_reasoning", "security_gates", "tests_are_truth"], "moe_experts": ["agentic_systems_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "90b4d48959fb65baa9c4851ba3d066960f8c7653"} +{"id": "val_00964", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "design", "difficulty": "advanced", "instruction": "Task: design\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: TypeScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "TypeScript", "developer_needs": ["evaluation_metrics", "reproducibility", "governance", "documentation"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2a9dd9940c14063f603b3875313ce534a5403817"} +{"id": "val_00965", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["security_gates", "ci_integration", "tests_are_truth", "cost_latency_tradeoffs"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "050c05c66c51c640ed4e6a4834740f5f65736aaf"} +{"id": "val_00966", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: advanced\nTarget language: SQL\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "documentation", "ci_integration", "evaluation_metrics"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4a6b90254db202dfc67336b385eff18b1e288d3e"} +{"id": "val_00967", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Governance, provenance, and licensing for code data\nDifficulty: expert\nTarget language: TypeScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["tests_are_truth", "tooling", "documentation", "repo_scale_reasoning"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "569ac8b73773cf411997774267d47d4f073d0f4e"} +{"id": "val_00968", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "failure_analysis", "difficulty": "advanced", "instruction": "Task: failure_analysis\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: SQL\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": [], "metadata": {"target_language": "SQL", "developer_needs": ["ci_integration", "tests_are_truth", "reproducibility", "security_gates"], "moe_experts": ["data_curation_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4ed09ed9d82fdff1d7324a1856308c1213dc1779"} +{"id": "val_00969", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Rust\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "ci_integration", "evaluation_metrics", "documentation"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "01683b2c8e578911b44b187cad2a377a75a8b46d"} +{"id": "val_00970", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: Java\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["documentation", "cost_latency_tradeoffs", "auditability", "security_gates"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "eff39c3e451942da81f0bc0f1923f1ff175a3be8"} +{"id": "val_00971", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Java\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nEval:\npass@k, time-to-green, regressions, diff size\n", "reasoning_steps": [], "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "governance", "evaluation_metrics", "documentation"], "moe_experts": ["security_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "ca8c968dbe7e5d50af8145879e2a3d7c856cd161"} +{"id": "val_00972", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["evaluation_metrics", "tests_are_truth", "documentation", "governance"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8804f586605f7ce8ff06c20c3c68502783ca8bb1"} +{"id": "val_00973", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Bash\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "documentation", "ci_integration", "tests_are_truth"], "moe_experts": ["evaluation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "099de112c837fc24ea9f1833cb7b73c84c7b077b"} +{"id": "val_00974", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: C#\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "C#", "developer_needs": ["tests_are_truth", "ci_integration", "repo_scale_reasoning", "cost_latency_tradeoffs"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "bf0499219bdc82449d26c3affb0e9d837fa9bbdc"} +{"id": "val_00975", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "data_pipeline", "difficulty": "intermediate", "instruction": "Task: data_pipeline\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Java\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "reproducibility", "tooling"], "moe_experts": ["evaluation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2dd22705658ca5ede0b0af7a006fdadfa1e02a4f"} +{"id": "val_00976", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "evaluation_metrics", "documentation", "security_gates"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e8d9cb1da200d672fa508e3df6ff66beba9f8968"} +{"id": "val_00977", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "code", "difficulty": "advanced", "instruction": "Task: code\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: advanced\nTarget language: C#\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "C#", "developer_needs": ["tooling", "reproducibility", "auditability", "documentation"], "moe_experts": ["data_curation_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "139f04465553fffc3c2878e32ef3ee017a88b7c9"} +{"id": "val_00978", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "documentation", "tooling", "reproducibility"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "b90a38cd5aa10fa9d4af00339667f9d2c2965bae"} +{"id": "val_00979", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Python\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nReview: correctness, security, performance, governance\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["governance", "ci_integration", "tooling", "cost_latency_tradeoffs"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "8a1abf72feffe963e6596a6c5d39983fa8af62a6"} +{"id": "val_00980", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: SWE-bench style real-repo evaluation\nDifficulty: intermediate\nTarget language: TypeScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["auditability", "documentation", "governance", "security_gates"], "moe_experts": ["data_curation_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "326564256dab910302cb068a3c964315e39a8025"} +{"id": "val_00981", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "repo_scale_reasoning", "documentation", "reproducibility"], "moe_experts": ["data_curation_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e2a9678e81ab5a565feb92a1fe84152363d315cc"} +{"id": "val_00982", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: Java\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Java", "developer_needs": ["documentation", "ci_integration", "security_gates", "tooling"], "moe_experts": ["evaluation_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "14bb69e3e35ee4ec2fca70f6d3bab5504369ef22"} +{"id": "val_00983", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "failure_analysis", "difficulty": "expert", "instruction": "Task: failure_analysis\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Rust\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "documentation", "evaluation_metrics", "tooling"], "moe_experts": ["governance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "858fcb83a80143cbf70c1e05cc675de61d72d7d4"} +{"id": "val_00984", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Go\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["repo_scale_reasoning", "documentation", "tests_are_truth", "reproducibility"], "moe_experts": ["agentic_systems_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "cb76e16184c1905922b362bc24618566c01513da"} +{"id": "val_00985", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "failure_analysis", "difficulty": "intermediate", "instruction": "Task: failure_analysis\nTopic: Secure code generation and policy gates\nDifficulty: intermediate\nTarget language: Bash\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nFailure:\n- Initial patch broke edge case\nReflection:\n- Missing zero-input guard\nCorrection:\n- Add explicit validation + test\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "tooling", "auditability", "cost_latency_tradeoffs"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f4f1124af2cb28dcdd57e9184e6cca00368aac67"} +{"id": "val_00986", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Rust\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "documentation", "cost_latency_tradeoffs", "ci_integration"], "moe_experts": ["coding_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "666224b83856cc29651ee76820c7a79dc30017d4"} +{"id": "val_00987", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "expert", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: expert\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["reproducibility", "security_gates", "tests_are_truth", "repo_scale_reasoning"], "moe_experts": ["security_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "98f92aec0523a1a55fc0983937841ca72ec35a3c"} +{"id": "val_00988", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: advanced\nTarget language: TypeScript\nContext: Large monorepo with flaky tests and strict CI.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "auditability", "security_gates", "repo_scale_reasoning"], "moe_experts": ["security_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3aa6afaa163b3df5914f8afc9324d2bb216ad644"} +{"id": "val_00989", "created": "2026-01-01", "topic": "Latency, cost, and reliability optimization", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Latency, cost, and reliability optimization\nDifficulty: advanced\nTarget language: Python\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Python", "developer_needs": ["documentation", "auditability", "governance", "reproducibility"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "f733e1f98bd72e5f5bebb1795dde93fbd1fbafd6"} +{"id": "val_00990", "created": "2026-01-01", "topic": "Self-improving agents and feedback loops", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Self-improving agents and feedback loops\nDifficulty: intermediate\nTarget language: Go\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Go", "developer_needs": ["governance", "cost_latency_tradeoffs", "auditability", "reproducibility"], "moe_experts": ["performance_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "c1c150e80fbb86479ef98f40d784a2cbd8f6aeb8"} +{"id": "val_00991", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Secure code generation and policy gates\nDifficulty: expert\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["cost_latency_tradeoffs", "tooling", "security_gates", "reproducibility"], "moe_experts": ["agentic_systems_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "edb31a1ae309af83bd5c331f671187505e04b277"} +{"id": "val_00992", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "compare", "difficulty": "advanced", "instruction": "Task: compare\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: TypeScript\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nCompare: capability, cost, latency, reliability\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "evaluation_metrics", "auditability", "security_gates"], "moe_experts": ["performance_expert", "security_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "704dbfd79d4d3a7c04c97906159cbc2c97ae705a"} +{"id": "val_00993", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: expert\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "repo_scale_reasoning", "auditability", "reproducibility"], "moe_experts": ["data_curation_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "65f70240018793ceb0e3b55670c5e102e0fd2556"} +{"id": "val_00994", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "explain", "difficulty": "intermediate", "instruction": "Task: explain\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: intermediate\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["documentation", "tests_are_truth", "repo_scale_reasoning", "security_gates"], "moe_experts": ["security_expert", "data_curation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "e911852999c1d30f9a5f4cedfebd8e8bf3a05fb7"} +{"id": "val_00995", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "agent_loop", "difficulty": "intermediate", "instruction": "Task: agent_loop\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: JavaScript\nContext: Regulated environment requiring audit trails.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nLoop: Plan \u2192 Edit \u2192 Test \u2192 Reflect \u2192 Human gate\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "repo_scale_reasoning", "cost_latency_tradeoffs", "reproducibility"], "moe_experts": ["performance_expert", "agentic_systems_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "3c1676ec5579cf4e63ffcd466b7efa8f5af9cb59"} +{"id": "val_00996", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "patch_diff", "difficulty": "advanced", "instruction": "Task: patch_diff\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: advanced\nTarget language: JavaScript\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "repo_scale_reasoning", "evaluation_metrics", "auditability"], "moe_experts": ["agentic_systems_expert", "performance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "6e08f6538fe459adf36f00b7a59a6922213d9686"} +{"id": "val_00997", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "data_pipeline", "difficulty": "advanced", "instruction": "Task: data_pipeline\nTopic: SWE-bench style real-repo evaluation\nDifficulty: advanced\nTarget language: JavaScript\nContext: Research team validating claims against real repos.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPipeline:\nIngest \u2192 Normalize \u2192 Filter \u2192 Dedupe \u2192 Quality \u2192 Mix \u2192 Audit\n", "reasoning_steps": [], "metadata": {"target_language": "JavaScript", "developer_needs": ["auditability", "cost_latency_tradeoffs", "tooling", "reproducibility"], "moe_experts": ["governance_expert", "coding_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "893ea222cb98d3c7de447c2c61457944a418dcd0"} +{"id": "val_00998", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "patch_diff", "difficulty": "expert", "instruction": "Task: patch_diff\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: expert\nTarget language: Bash\nContext: High-traffic service with latency SLOs.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nPatch (diff-style):\n```diff\n- if x == 0:\n- return 1/x\n+ if x == 0:\n+ raise ValueError('division by zero')\n```\nAcceptance:\n- Tests pass\n- No new regressions\n", "reasoning_steps": [], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "tests_are_truth", "reproducibility", "evaluation_metrics"], "moe_experts": ["governance_expert", "evaluation_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "2e3e71f24b5d30cc9cc704855c9e90ced253569f"} +{"id": "val_00999", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "explain", "difficulty": "advanced", "instruction": "Task: explain\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: advanced\nTarget language: Bash\nContext: Offline/local deployment with limited compute.\nProduce expert-level, production-ready artifacts.", "input": "", "output": "Facts:\n- Modern AI coding prioritizes correctness, evaluation, and governance.\n- Agentic loops with test gates outperform single-pass generation.\n\nDesign with risks, metrics, acceptance criteria\n", "reasoning_steps": ["Identify failing behavior via tests", "Minimize change surface", "Apply patch", "Run targeted + full suite", "Verify no regressions"], "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "evaluation_metrics", "auditability", "repo_scale_reasoning"], "moe_experts": ["security_expert", "governance_expert"], "governance": {"audit_required": true, "tests_required": true}}, "hash": "4c3823c8228dc2395ec6a57f2cd570f00f5500c6"}