Spaces:

crazycrazypete
/

Masters-four-Tab-OpenAI

Running

App Files Files Community

Masters-four-Tab-OpenAI / docs /evals

4.32 MB

Ctrl+K

Ctrl+K

2 contributors

History: 57 commits

Pete Dunn

router tab pass-check cleanup

931691a 2 months ago

latest_eval25_guarded_gpt_check
Standardize app runtime on gpt-5-mini 3 months ago
latest_eval50_guarded_gpt_check
Optimize guarded assistant routing and eval coverage 3 months ago
latest_eval6_concept_check
Add guarded assistant concept fallback flow 3 months ago
release_gate
router tab pass-check cleanup 2 months ago
README.md

1.44 kB
Prune non-canonical eval artifacts 3 months ago
all_eval_questions_answers.csv

2.7 MB
Sync pending app, RAG, and evaluation updates 4 months ago
masters_retrieval_cases.json

453 Bytes
Improve Masters retrieval scoring and tighten RAG quality thresholds 4 months ago
pots_retrieval_cases.json

247 Bytes
feat: ship auth0 integration, router data updates, and ui refresh 4 months ago
pots_top100_questions_draft.md

26.9 kB
feat: ship auth0 integration, router data updates, and ui refresh 4 months ago
rag_quality_gate.md

1.96 kB
Strengthen RAG quality gate with hard-fail policy checks and router web-assisted coverage 4 months ago
rag_quality_latest.json

9.87 kB
Fail soft on invalid Masters source files 3 months ago
rag_quality_thresholds.json

667 Bytes
Strengthen RAG quality gate with hard-fail policy checks and router web-assisted coverage 4 months ago
rag_response_cases.json

2.98 kB
Strengthen RAG quality gate with hard-fail policy checks and router web-assisted coverage 4 months ago
release_gate_baseline.json

153 Bytes
Add release preflight, baseline gates, and review-queue observability 4 months ago
router_kb_confusing_questions_v1.md

4.9 kB
Improve router knowledgebase reliability, disambiguation, and output quality 4 months ago
router_kb_confusing_run_after.json

12.8 kB
Improve router knowledgebase reliability, disambiguation, and output quality 4 months ago
router_kb_confusing_run_before.json

13.8 kB
Improve router knowledgebase reliability, disambiguation, and output quality 4 months ago
router_kb_eval_latest.json

52.2 kB
Sync canonical Router KB corpus, Router RAG module, eval harness, and app updates 4 months ago
router_kb_eval_latest.md

39.7 kB
Sync canonical Router KB corpus, Router RAG module, eval harness, and app updates 4 months ago
router_kb_response_cases.json

4.4 kB
Sync canonical Router KB corpus, Router RAG module, eval harness, and app updates 4 months ago
unified_kb_eval150_cases.json

61.1 kB
Add unified KB eval150 runner, reports, and nightly CI 4 months ago
unified_kb_eval150_latest.json

11 kB
router stabilization pass 2 months ago
unified_kb_eval150_latest.md

2.01 kB
router stabilization pass 2 months ago
unified_kb_eval150_trend.json

422 kB
router tab pass-check cleanup 2 months ago
unified_kb_eval25_guarded_gpt_cases.json

10.7 kB
Standardize app runtime on gpt-5-mini 3 months ago
unified_kb_eval50_guarded_gpt_cases.json

22.6 kB
Optimize guarded assistant routing and eval coverage 3 months ago
unified_kb_eval6_concept_fallback_cases.json

1.9 kB
Add guarded assistant concept fallback flow 3 months ago