Datasets:
File size: 169,046 Bytes
72498e9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 |
{"id": "val_00000", "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: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Bash", "developer_needs": ["security_gates", "repo_scale_reasoning", "evaluation_metrics"]}}
{"id": "val_00001", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "review", "difficulty": "foundation", "instruction": "Task: review\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: Bash\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Bash", "developer_needs": ["tests_are_truth", "security_gates", "repo_scale_reasoning"]}}
{"id": "val_00002", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "eval", "difficulty": "foundation", "instruction": "Task: eval\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: SQL\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "SQL", "developer_needs": ["evaluation_metrics", "reproducibility", "cost_latency_tradeoffs"]}}
{"id": "val_00003", "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: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "SQL", "developer_needs": ["governance", "tests_are_truth", "security_gates"]}}
{"id": "val_00004", "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: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "tests_are_truth", "security_gates"]}}
{"id": "val_00005", "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: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "C#", "developer_needs": ["documentation", "tests_are_truth", "repo_scale_reasoning"]}}
{"id": "val_00006", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "code", "difficulty": "intermediate", "instruction": "Task: code\nTopic: Governance, provenance, and licensing for code data\nDifficulty: intermediate\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Go", "developer_needs": ["tests_are_truth", "evaluation_metrics", "tooling"]}}
{"id": "val_00007", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "eval", "difficulty": "advanced", "instruction": "Task: eval\nTopic: Secure code generation and policy gates\nDifficulty: advanced\nTarget language: C#\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "C#", "developer_needs": ["documentation", "governance", "cost_latency_tradeoffs"]}}
{"id": "val_00008", "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: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Python", "developer_needs": ["governance", "security_gates", "reproducibility"]}}
{"id": "val_00009", "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: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Rust", "developer_needs": ["governance", "security_gates", "cost_latency_tradeoffs"]}}
{"id": "val_00010", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "explain", "difficulty": "foundation", "instruction": "Task: explain\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: SQL\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "SQL", "developer_needs": ["evaluation_metrics", "tests_are_truth", "governance"]}}
{"id": "val_00011", "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: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Python", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "ci_integration"]}}
{"id": "val_00012", "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: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "security_gates", "ci_integration"]}}
{"id": "val_00013", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "eval", "difficulty": "foundation", "instruction": "Task: eval\nTopic: Governance, provenance, and licensing for code data\nDifficulty: foundation\nTarget language: Rust\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "evaluation_metrics"]}}
{"id": "val_00014", "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: Rust\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "repo_scale_reasoning", "governance"]}}
{"id": "val_00015", "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: Rust\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "tests_are_truth", "governance"]}}
{"id": "val_00016", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "agent_loop", "difficulty": "foundation", "instruction": "Task: agent_loop\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: foundation\nTarget language: TypeScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "security_gates", "evaluation_metrics"]}}
{"id": "val_00017", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "agent_loop", "difficulty": "foundation", "instruction": "Task: agent_loop\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: foundation\nTarget language: TypeScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "governance", "cost_latency_tradeoffs"]}}
{"id": "val_00018", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "compare", "difficulty": "foundation", "instruction": "Task: compare\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: foundation\nTarget language: Rust\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "reproducibility", "repo_scale_reasoning"]}}
{"id": "val_00019", "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: Python\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Python", "developer_needs": ["documentation", "tests_are_truth", "evaluation_metrics"]}}
{"id": "val_00020", "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: SQL\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "SQL", "developer_needs": ["repo_scale_reasoning", "documentation", "evaluation_metrics"]}}
{"id": "val_00021", "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: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "governance", "ci_integration"]}}
{"id": "val_00022", "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: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Go", "developer_needs": ["tests_are_truth", "tooling", "evaluation_metrics"]}}
{"id": "val_00023", "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: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "SQL", "developer_needs": ["governance", "ci_integration", "documentation"]}}
{"id": "val_00024", "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: Bash\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Bash", "developer_needs": ["tests_are_truth", "documentation", "reproducibility"]}}
{"id": "val_00025", "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: Java\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Java", "developer_needs": ["governance", "security_gates", "tooling"]}}
{"id": "val_00026", "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: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Rust", "developer_needs": ["reproducibility", "governance", "tests_are_truth"]}}
{"id": "val_00027", "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: Java\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Java", "developer_needs": ["tooling", "cost_latency_tradeoffs", "reproducibility"]}}
{"id": "val_00028", "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: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "C#", "developer_needs": ["cost_latency_tradeoffs", "evaluation_metrics", "reproducibility"]}}
{"id": "val_00029", "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: Java\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Java", "developer_needs": ["ci_integration", "cost_latency_tradeoffs", "tooling"]}}
{"id": "val_00030", "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: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["ci_integration", "reproducibility", "tooling"]}}
{"id": "val_00031", "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: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["repo_scale_reasoning", "security_gates", "reproducibility"]}}
{"id": "val_00032", "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: TypeScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["tooling", "cost_latency_tradeoffs", "reproducibility"]}}
{"id": "val_00033", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "code", "difficulty": "foundation", "instruction": "Task: code\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: foundation\nTarget language: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "evaluation_metrics", "repo_scale_reasoning"]}}
{"id": "val_00034", "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: JavaScript\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "security_gates", "tooling"]}}
{"id": "val_00035", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "eval", "difficulty": "foundation", "instruction": "Task: eval\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: foundation\nTarget language: Rust\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "evaluation_metrics", "tooling"]}}
{"id": "val_00036", "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: Python\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Python", "developer_needs": ["tooling", "tests_are_truth", "governance"]}}
{"id": "val_00037", "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: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "governance", "repo_scale_reasoning"]}}
{"id": "val_00038", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "agent_loop", "difficulty": "foundation", "instruction": "Task: agent_loop\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: Python\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Python", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "ci_integration"]}}
{"id": "val_00039", "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: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "ci_integration", "security_gates"]}}
{"id": "val_00040", "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: Rust\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Rust", "developer_needs": ["ci_integration", "security_gates", "repo_scale_reasoning"]}}
{"id": "val_00041", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "agent_loop", "difficulty": "advanced", "instruction": "Task: agent_loop\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: advanced\nTarget language: JavaScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "reproducibility", "documentation"]}}
{"id": "val_00042", "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: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "tests_are_truth"]}}
{"id": "val_00043", "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: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "tooling", "governance"]}}
{"id": "val_00044", "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: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "ci_integration", "repo_scale_reasoning"]}}
{"id": "val_00045", "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: Go\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "governance", "cost_latency_tradeoffs"]}}
{"id": "val_00046", "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: TypeScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "ci_integration"]}}
{"id": "val_00047", "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: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["ci_integration", "security_gates", "tooling"]}}
{"id": "val_00048", "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: Rust\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "tooling", "documentation"]}}
{"id": "val_00049", "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: Bash\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "governance", "evaluation_metrics"]}}
{"id": "val_00050", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "code", "difficulty": "foundation", "instruction": "Task: code\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: foundation\nTarget language: Java\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Java", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "documentation"]}}
{"id": "val_00051", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "design", "difficulty": "foundation", "instruction": "Task: design\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: foundation\nTarget language: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "reproducibility"]}}
{"id": "val_00052", "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: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "cost_latency_tradeoffs", "security_gates"]}}
{"id": "val_00053", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "data_pipeline", "difficulty": "foundation", "instruction": "Task: data_pipeline\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: foundation\nTarget language: JavaScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "tests_are_truth", "evaluation_metrics"]}}
{"id": "val_00054", "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: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Python", "developer_needs": ["governance", "documentation", "reproducibility"]}}
{"id": "val_00055", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "eval", "difficulty": "foundation", "instruction": "Task: eval\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: foundation\nTarget language: Java\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Java", "developer_needs": ["documentation", "tests_are_truth", "evaluation_metrics"]}}
{"id": "val_00056", "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: Go\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "governance", "repo_scale_reasoning"]}}
{"id": "val_00057", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "agent_loop", "difficulty": "foundation", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: JavaScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "security_gates", "evaluation_metrics"]}}
{"id": "val_00058", "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: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "security_gates", "tests_are_truth"]}}
{"id": "val_00059", "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: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["tests_are_truth", "repo_scale_reasoning", "tooling"]}}
{"id": "val_00060", "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: Go\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "ci_integration", "documentation"]}}
{"id": "val_00061", "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: Bash\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "ci_integration", "tooling"]}}
{"id": "val_00062", "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: Bash\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Bash", "developer_needs": ["documentation", "security_gates", "evaluation_metrics"]}}
{"id": "val_00063", "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: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["ci_integration", "tooling", "repo_scale_reasoning"]}}
{"id": "val_00064", "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: Java\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Java", "developer_needs": ["cost_latency_tradeoffs", "repo_scale_reasoning", "tooling"]}}
{"id": "val_00065", "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: Rust\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "governance", "security_gates"]}}
{"id": "val_00066", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "design", "difficulty": "foundation", "instruction": "Task: design\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: Java\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "documentation", "ci_integration"]}}
{"id": "val_00067", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "eval", "difficulty": "foundation", "instruction": "Task: eval\nTopic: SWE-bench style real-repo evaluation\nDifficulty: foundation\nTarget language: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Rust", "developer_needs": ["evaluation_metrics", "cost_latency_tradeoffs", "tooling"]}}
{"id": "val_00068", "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: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "documentation", "ci_integration"]}}
{"id": "val_00069", "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: C#\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["cost_latency_tradeoffs", "documentation", "tests_are_truth"]}}
{"id": "val_00070", "created": "2026-01-01", "topic": "Dataset curation pipelines (filter, dedupe, quality)", "task_type": "eval", "difficulty": "foundation", "instruction": "Task: eval\nTopic: Dataset curation pipelines (filter, dedupe, quality)\nDifficulty: foundation\nTarget language: JavaScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["ci_integration", "repo_scale_reasoning", "tests_are_truth"]}}
{"id": "val_00071", "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: Rust\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "cost_latency_tradeoffs", "repo_scale_reasoning"]}}
{"id": "val_00072", "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: Java\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "tooling", "evaluation_metrics"]}}
{"id": "val_00073", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "agent_loop", "difficulty": "foundation", "instruction": "Task: agent_loop\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: C#\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "evaluation_metrics", "repo_scale_reasoning"]}}
{"id": "val_00074", "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: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["repo_scale_reasoning", "ci_integration", "reproducibility"]}}
{"id": "val_00075", "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: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "documentation", "cost_latency_tradeoffs"]}}
{"id": "val_00076", "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: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "security_gates", "reproducibility"]}}
{"id": "val_00077", "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: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["reproducibility", "documentation", "evaluation_metrics"]}}
{"id": "val_00078", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "code", "difficulty": "expert", "instruction": "Task: code\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: expert\nTarget language: Java\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "tests_are_truth", "cost_latency_tradeoffs"]}}
{"id": "val_00079", "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: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "repo_scale_reasoning", "governance"]}}
{"id": "val_00080", "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: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Go", "developer_needs": ["ci_integration", "documentation", "governance"]}}
{"id": "val_00081", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "review", "difficulty": "foundation", "instruction": "Task: review\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "C#", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "tests_are_truth"]}}
{"id": "val_00082", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "compare", "difficulty": "intermediate", "instruction": "Task: compare\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: Java\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "evaluation_metrics", "ci_integration"]}}
{"id": "val_00083", "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: Python\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Python", "developer_needs": ["tooling", "cost_latency_tradeoffs", "ci_integration"]}}
{"id": "val_00084", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "governance", "tooling"]}}
{"id": "val_00085", "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: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "tooling", "governance"]}}
{"id": "val_00086", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "compare", "difficulty": "foundation", "instruction": "Task: compare\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: foundation\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Go", "developer_needs": ["tests_are_truth", "cost_latency_tradeoffs", "tooling"]}}
{"id": "val_00087", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "review", "difficulty": "foundation", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: foundation\nTarget language: Python\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Python", "developer_needs": ["repo_scale_reasoning", "ci_integration", "cost_latency_tradeoffs"]}}
{"id": "val_00088", "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: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Python", "developer_needs": ["ci_integration", "evaluation_metrics", "governance"]}}
{"id": "val_00089", "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: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "ci_integration"]}}
{"id": "val_00090", "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: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "ci_integration", "reproducibility"]}}
{"id": "val_00091", "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: Bash\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Bash", "developer_needs": ["documentation", "reproducibility", "tests_are_truth"]}}
{"id": "val_00092", "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: Java\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "security_gates", "cost_latency_tradeoffs"]}}
{"id": "val_00093", "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: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Go", "developer_needs": ["ci_integration", "cost_latency_tradeoffs", "evaluation_metrics"]}}
{"id": "val_00094", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "foundation", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: Rust\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Rust", "developer_needs": ["repo_scale_reasoning", "governance", "ci_integration"]}}
{"id": "val_00095", "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: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "security_gates", "tests_are_truth"]}}
{"id": "val_00096", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "design", "difficulty": "expert", "instruction": "Task: design\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: expert\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Go", "developer_needs": ["tooling", "evaluation_metrics", "repo_scale_reasoning"]}}
{"id": "val_00097", "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: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "C#", "developer_needs": ["cost_latency_tradeoffs", "tests_are_truth", "governance"]}}
{"id": "val_00098", "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: Python\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "tests_are_truth", "repo_scale_reasoning"]}}
{"id": "val_00099", "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: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["governance", "security_gates", "reproducibility"]}}
{"id": "val_00100", "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: SQL\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "documentation", "tests_are_truth"]}}
{"id": "val_00101", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "code", "difficulty": "foundation", "instruction": "Task: code\nTopic: Governance, provenance, and licensing for code data\nDifficulty: foundation\nTarget language: Go\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Go", "developer_needs": ["ci_integration", "repo_scale_reasoning", "tooling"]}}
{"id": "val_00102", "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: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "SQL", "developer_needs": ["reproducibility", "cost_latency_tradeoffs", "repo_scale_reasoning"]}}
{"id": "val_00103", "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: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["evaluation_metrics", "ci_integration", "cost_latency_tradeoffs"]}}
{"id": "val_00104", "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: Python\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Python", "developer_needs": ["governance", "repo_scale_reasoning", "evaluation_metrics"]}}
{"id": "val_00105", "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: C#\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["governance", "documentation", "tests_are_truth"]}}
{"id": "val_00106", "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: Java\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Java", "developer_needs": ["governance", "reproducibility", "security_gates"]}}
{"id": "val_00107", "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: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Bash", "developer_needs": ["evaluation_metrics", "reproducibility", "security_gates"]}}
{"id": "val_00108", "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: Rust\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Rust", "developer_needs": ["documentation", "governance", "security_gates"]}}
{"id": "val_00109", "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: C#\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "repo_scale_reasoning", "tests_are_truth"]}}
{"id": "val_00110", "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: Bash\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Bash", "developer_needs": ["cost_latency_tradeoffs", "governance", "repo_scale_reasoning"]}}
{"id": "val_00111", "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: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "cost_latency_tradeoffs", "evaluation_metrics"]}}
{"id": "val_00112", "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: Go\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Go", "developer_needs": ["ci_integration", "tests_are_truth", "repo_scale_reasoning"]}}
{"id": "val_00113", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "design", "difficulty": "foundation", "instruction": "Task: design\nTopic: Governance, provenance, and licensing for code data\nDifficulty: foundation\nTarget language: Rust\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Rust", "developer_needs": ["tooling", "ci_integration", "governance"]}}
{"id": "val_00114", "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: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "security_gates", "governance"]}}
{"id": "val_00115", "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: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "security_gates", "documentation"]}}
{"id": "val_00116", "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: Go\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Go", "developer_needs": ["cost_latency_tradeoffs", "reproducibility", "repo_scale_reasoning"]}}
{"id": "val_00117", "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: C#\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["repo_scale_reasoning", "security_gates", "tooling"]}}
{"id": "val_00118", "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: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "reproducibility", "cost_latency_tradeoffs"]}}
{"id": "val_00119", "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: Java\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "repo_scale_reasoning", "documentation"]}}
{"id": "val_00120", "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: TypeScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "tooling", "cost_latency_tradeoffs"]}}
{"id": "val_00121", "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: Python\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReference scaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=3):\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, \"passed\": ok, \"report\": report[:200]})\n if ok:\n return patch, history\n p = p + \" | refine from failures\"\n return patch, history\n\n```\nOperational notes: sandbox, pinned deps, human gate.", "metadata": {"target_language": "Python", "developer_needs": ["tooling", "repo_scale_reasoning", "reproducibility"]}}
{"id": "val_00122", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "data_pipeline", "difficulty": "foundation", "instruction": "Task: data_pipeline\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: foundation\nTarget language: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "cost_latency_tradeoffs", "security_gates"]}}
{"id": "val_00123", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "agent_loop", "difficulty": "foundation", "instruction": "Task: agent_loop\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: Go\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "governance", "repo_scale_reasoning"]}}
{"id": "val_00124", "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: TypeScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "repo_scale_reasoning", "security_gates"]}}
{"id": "val_00125", "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: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Rust", "developer_needs": ["evaluation_metrics", "ci_integration", "security_gates"]}}
{"id": "val_00126", "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: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "security_gates", "evaluation_metrics"]}}
{"id": "val_00127", "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: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "documentation", "ci_integration"]}}
{"id": "val_00128", "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: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "ci_integration"]}}
{"id": "val_00129", "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: Python\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Python", "developer_needs": ["governance", "reproducibility", "evaluation_metrics"]}}
{"id": "val_00130", "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: Rust\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Rust", "developer_needs": ["tests_are_truth", "documentation", "reproducibility"]}}
{"id": "val_00131", "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: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Java", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "tests_are_truth"]}}
{"id": "val_00132", "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: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["documentation", "cost_latency_tradeoffs", "tooling"]}}
{"id": "val_00133", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "explain", "difficulty": "foundation", "instruction": "Task: explain\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: SQL\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "tests_are_truth"]}}
{"id": "val_00134", "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: JavaScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["repo_scale_reasoning", "reproducibility", "ci_integration"]}}
{"id": "val_00135", "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: TypeScript\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "repo_scale_reasoning", "tests_are_truth"]}}
{"id": "val_00136", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "compare", "difficulty": "foundation", "instruction": "Task: compare\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: JavaScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "documentation", "ci_integration"]}}
{"id": "val_00137", "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: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["documentation", "cost_latency_tradeoffs", "reproducibility"]}}
{"id": "val_00138", "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: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Go", "developer_needs": ["governance", "ci_integration", "cost_latency_tradeoffs"]}}
{"id": "val_00139", "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: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["tooling", "tests_are_truth", "governance"]}}
{"id": "val_00140", "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: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "tooling", "tests_are_truth"]}}
{"id": "val_00141", "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: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "ci_integration", "documentation"]}}
{"id": "val_00142", "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: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "C#", "developer_needs": ["documentation", "evaluation_metrics", "reproducibility"]}}
{"id": "val_00143", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "design", "difficulty": "foundation", "instruction": "Task: design\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["cost_latency_tradeoffs", "documentation", "tests_are_truth"]}}
{"id": "val_00144", "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: TypeScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["cost_latency_tradeoffs", "repo_scale_reasoning", "evaluation_metrics"]}}
{"id": "val_00145", "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: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "C#", "developer_needs": ["repo_scale_reasoning", "documentation", "evaluation_metrics"]}}
{"id": "val_00146", "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: Python\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Python", "developer_needs": ["tooling", "repo_scale_reasoning", "security_gates"]}}
{"id": "val_00147", "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: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "security_gates", "repo_scale_reasoning"]}}
{"id": "val_00148", "created": "2026-01-01", "topic": "Reasoning-first coding models and tunable deliberation", "task_type": "review", "difficulty": "foundation", "instruction": "Task: review\nTopic: Reasoning-first coding models and tunable deliberation\nDifficulty: foundation\nTarget language: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Go", "developer_needs": ["governance", "cost_latency_tradeoffs", "security_gates"]}}
{"id": "val_00149", "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: TypeScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "cost_latency_tradeoffs", "reproducibility"]}}
{"id": "val_00150", "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: Bash\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Bash", "developer_needs": ["ci_integration", "documentation", "reproducibility"]}}
{"id": "val_00151", "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: Java\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Java", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "security_gates"]}}
{"id": "val_00152", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "foundation", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: Java\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Java", "developer_needs": ["tests_are_truth", "governance", "repo_scale_reasoning"]}}
{"id": "val_00153", "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: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Python", "developer_needs": ["tests_are_truth", "security_gates", "governance"]}}
{"id": "val_00154", "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: Python\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Python", "developer_needs": ["cost_latency_tradeoffs", "documentation", "tests_are_truth"]}}
{"id": "val_00155", "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: Bash\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "ci_integration", "documentation"]}}
{"id": "val_00156", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "explain", "difficulty": "foundation", "instruction": "Task: explain\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: foundation\nTarget language: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["ci_integration", "security_gates", "governance"]}}
{"id": "val_00157", "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: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Go", "developer_needs": ["tooling", "evaluation_metrics", "cost_latency_tradeoffs"]}}
{"id": "val_00158", "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: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "evaluation_metrics", "tooling"]}}
{"id": "val_00159", "created": "2026-01-01", "topic": "Multimodal dev workflows (docs, diagrams, traces)", "task_type": "design", "difficulty": "foundation", "instruction": "Task: design\nTopic: Multimodal dev workflows (docs, diagrams, traces)\nDifficulty: foundation\nTarget language: Rust\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Rust", "developer_needs": ["ci_integration", "documentation", "tooling"]}}
{"id": "val_00160", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "agent_loop", "difficulty": "foundation", "instruction": "Task: agent_loop\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: foundation\nTarget language: Java\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Java", "developer_needs": ["evaluation_metrics", "cost_latency_tradeoffs", "documentation"]}}
{"id": "val_00161", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "code", "difficulty": "foundation", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: Java\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Java", "developer_needs": ["documentation", "cost_latency_tradeoffs", "reproducibility"]}}
{"id": "val_00162", "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: JavaScript\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["cost_latency_tradeoffs", "security_gates", "evaluation_metrics"]}}
{"id": "val_00163", "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: JavaScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["governance", "reproducibility", "tests_are_truth"]}}
{"id": "val_00164", "created": "2026-01-01", "topic": "Governance, provenance, and licensing for code data", "task_type": "data_pipeline", "difficulty": "foundation", "instruction": "Task: data_pipeline\nTopic: Governance, provenance, and licensing for code data\nDifficulty: foundation\nTarget language: Java\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Java", "developer_needs": ["cost_latency_tradeoffs", "governance", "tooling"]}}
{"id": "val_00165", "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: Go\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Go", "developer_needs": ["security_gates", "governance", "ci_integration"]}}
{"id": "val_00166", "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: Bash\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Bash", "developer_needs": ["cost_latency_tradeoffs", "evaluation_metrics", "reproducibility"]}}
{"id": "val_00167", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "code", "difficulty": "foundation", "instruction": "Task: code\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: foundation\nTarget language: Python\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReference scaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=3):\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, \"passed\": ok, \"report\": report[:200]})\n if ok:\n return patch, history\n p = p + \" | refine from failures\"\n return patch, history\n\n```\nOperational notes: sandbox, pinned deps, human gate.", "metadata": {"target_language": "Python", "developer_needs": ["cost_latency_tradeoffs", "documentation", "ci_integration"]}}
{"id": "val_00168", "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: Bash\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Bash", "developer_needs": ["repo_scale_reasoning", "reproducibility", "tooling"]}}
{"id": "val_00169", "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: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["tests_are_truth", "reproducibility", "repo_scale_reasoning"]}}
{"id": "val_00170", "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: Rust\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Rust", "developer_needs": ["repo_scale_reasoning", "governance", "evaluation_metrics"]}}
{"id": "val_00171", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "foundation", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: Bash\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Bash", "developer_needs": ["tooling", "reproducibility", "ci_integration"]}}
{"id": "val_00172", "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: Go\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Go", "developer_needs": ["documentation", "tooling", "repo_scale_reasoning"]}}
{"id": "val_00173", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "foundation", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: SQL\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "SQL", "developer_needs": ["security_gates", "cost_latency_tradeoffs", "evaluation_metrics"]}}
{"id": "val_00174", "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: TypeScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["reproducibility", "governance", "documentation"]}}
{"id": "val_00175", "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: Rust\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Rust", "developer_needs": ["ci_integration", "documentation", "tests_are_truth"]}}
{"id": "val_00176", "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: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "governance", "tests_are_truth"]}}
{"id": "val_00177", "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: Rust\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Rust", "developer_needs": ["cost_latency_tradeoffs", "ci_integration", "evaluation_metrics"]}}
{"id": "val_00178", "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: Bash\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Bash", "developer_needs": ["reproducibility", "evaluation_metrics", "ci_integration"]}}
{"id": "val_00179", "created": "2026-01-01", "topic": "Code-specialized model families and sizing tradeoffs", "task_type": "compare", "difficulty": "foundation", "instruction": "Task: compare\nTopic: Code-specialized model families and sizing tradeoffs\nDifficulty: foundation\nTarget language: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nCompare: capability, cost, latency, reliability, governance\n", "metadata": {"target_language": "Go", "developer_needs": ["tooling", "documentation", "evaluation_metrics"]}}
{"id": "val_00180", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "explain", "difficulty": "foundation", "instruction": "Task: explain\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: C#\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["governance", "tooling", "tests_are_truth"]}}
{"id": "val_00181", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "code", "difficulty": "foundation", "instruction": "Task: code\nTopic: SWE-bench style real-repo evaluation\nDifficulty: foundation\nTarget language: SQL\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "SQL", "developer_needs": ["tooling", "evaluation_metrics", "repo_scale_reasoning"]}}
{"id": "val_00182", "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: TypeScript\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["governance", "documentation", "reproducibility"]}}
{"id": "val_00183", "created": "2026-01-01", "topic": "Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)", "task_type": "data_pipeline", "difficulty": "foundation", "instruction": "Task: data_pipeline\nTopic: Agentic coding systems (plan\u2192edit\u2192test\u2192reflect)\nDifficulty: foundation\nTarget language: Java\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "Java", "developer_needs": ["reproducibility", "evaluation_metrics", "documentation"]}}
{"id": "val_00184", "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: Go\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Go", "developer_needs": ["reproducibility", "tests_are_truth", "security_gates"]}}
{"id": "val_00185", "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: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Go", "developer_needs": ["evaluation_metrics", "reproducibility", "ci_integration"]}}
{"id": "val_00186", "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: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Rust", "developer_needs": ["security_gates", "repo_scale_reasoning", "tests_are_truth"]}}
{"id": "val_00187", "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: C#\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nPipeline:\n1) Ingest\n2) Normalize\n3) Filter\n4) Dedupe\n5) Quality score\n6) Sample\n7) Audit\n", "metadata": {"target_language": "C#", "developer_needs": ["reproducibility", "tests_are_truth", "security_gates"]}}
{"id": "val_00188", "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: JavaScript\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["evaluation_metrics", "ci_integration", "cost_latency_tradeoffs"]}}
{"id": "val_00189", "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: Python\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "Python", "developer_needs": ["reproducibility", "repo_scale_reasoning", "tests_are_truth"]}}
{"id": "val_00190", "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: JavaScript\nContext: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "JavaScript", "developer_needs": ["security_gates", "ci_integration", "cost_latency_tradeoffs"]}}
{"id": "val_00191", "created": "2026-01-01", "topic": "Model merging, distillation, and continued pretraining", "task_type": "explain", "difficulty": "foundation", "instruction": "Task: explain\nTopic: Model merging, distillation, and continued pretraining\nDifficulty: foundation\nTarget language: C#\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["security_gates", "documentation", "repo_scale_reasoning"]}}
{"id": "val_00192", "created": "2026-01-01", "topic": "Tool calling, sandboxes, and CI integration", "task_type": "agent_loop", "difficulty": "foundation", "instruction": "Task: agent_loop\nTopic: Tool calling, sandboxes, and CI integration\nDifficulty: foundation\nTarget language: Go\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nAgent loop: Plan \u2192 Edit (diff) \u2192 Test \u2192 Reflect \u2192 Human gate\n", "metadata": {"target_language": "Go", "developer_needs": ["tests_are_truth", "governance", "repo_scale_reasoning"]}}
{"id": "val_00193", "created": "2026-01-01", "topic": "Secure code generation and policy gates", "task_type": "code", "difficulty": "foundation", "instruction": "Task: code\nTopic: Secure code generation and policy gates\nDifficulty: foundation\nTarget language: SQL\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "SQL", "developer_needs": ["governance", "ci_integration", "documentation"]}}
{"id": "val_00194", "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: Design a data pipeline for continued pretraining with auditability.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "Bash", "developer_needs": ["tooling", "repo_scale_reasoning", "tests_are_truth"]}}
{"id": "val_00195", "created": "2026-01-01", "topic": "Extended context and repo-scale understanding", "task_type": "code", "difficulty": "foundation", "instruction": "Task: code\nTopic: Extended context and repo-scale understanding\nDifficulty: foundation\nTarget language: TypeScript\nContext: Evaluate two coding models for internal rollout under strict governance.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "TypeScript", "developer_needs": ["security_gates", "tests_are_truth", "reproducibility"]}}
{"id": "val_00196", "created": "2026-01-01", "topic": "Mixture-of-Experts (MoE) for code", "task_type": "review", "difficulty": "intermediate", "instruction": "Task: review\nTopic: Mixture-of-Experts (MoE) for code\nDifficulty: intermediate\nTarget language: SQL\nContext: Create an eval harness that reflects real developer workflows.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReview: correctness, security, performance, governance\n", "metadata": {"target_language": "SQL", "developer_needs": ["cost_latency_tradeoffs", "tooling", "ci_integration"]}}
{"id": "val_00197", "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: C#\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nDesign guidance with risks, metrics, acceptance criteria\n", "metadata": {"target_language": "C#", "developer_needs": ["cost_latency_tradeoffs", "tests_are_truth", "reproducibility"]}}
{"id": "val_00198", "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: Python\nContext: Integrate an LLM agent into CI for a large monorepo.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nReference scaffold:\n```python\ndef agent_loop(plan, edit, test, issue, max_iters=3):\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, \"passed\": ok, \"report\": report[:200]})\n if ok:\n return patch, history\n p = p + \" | refine from failures\"\n return patch, history\n\n```\nOperational notes: sandbox, pinned deps, human gate.", "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "governance", "tests_are_truth"]}}
{"id": "val_00199", "created": "2026-01-01", "topic": "SWE-bench style real-repo evaluation", "task_type": "eval", "difficulty": "expert", "instruction": "Task: eval\nTopic: SWE-bench style real-repo evaluation\nDifficulty: expert\nTarget language: Python\nContext: Fix a failing issue with tests as the oracle and produce a safe patch.\nDeliver production-grade guidance or artifacts.", "input": "", "output": "Key facts:\n- Modern AI coding emphasizes correctness via tests, agentic loops, and real-repo evaluation.\n- Reasoning-first and MoE approaches improve capability-per-compute when paired with tools.\n\nEval:\n- Tasks: real issues\n- Metrics: pass@k, time-to-green\n- Gates: lint/security\n", "metadata": {"target_language": "Python", "developer_needs": ["security_gates", "tooling", "ci_integration"]}}
|