140 kB

Ctrl+K

1 contributor

History: 78 commits

Sravanth18

v0.4: Add filter_supported_claims_by_relevance to normalize extraction across model sizes

31a0dbf verified 27 days ago

__init__.py

24 Bytes
v0.3: fix all reviewed issues (bugs #1-3, issues #4-8, 125 tests pass) 28 days ago
baseline_runner.py

4.53 kB
v0.3: fix all reviewed issues (bugs #1-3, issues #4-8, 125 tests pass) 28 days ago
calibration.py

4.37 kB
v0.3: fix all reviewed issues (bugs #1-3, issues #4-8, 125 tests pass) 28 days ago
claim_filter.py

12.4 kB
v0.4: Add filter_supported_claims_by_relevance to normalize extraction across model sizes 27 days ago
config.py

2.02 kB
Upload src/config.py 27 days ago
constants.py

1.32 kB
v0.3: add shared constants module (unified STOP_WORDS) 28 days ago
contradiction_checks.py

7.38 kB
Upload src/contradiction_checks.py 27 days ago
diagnose_contradictions.py

2.69 kB
Upload src/diagnose_contradictions.py 28 days ago
diagnose_not_in_evidence.py

2.62 kB
Upload src/diagnose_not_in_evidence.py 28 days ago
evidence_spans.py

4.4 kB
v0.3.2: add Ph.D., M.D., B.A., B.S., M.S., M.B.A., J.D., D.V.M., D.Phil abbreviations 28 days ago
gate.py

15.4 kB
Upload src/gate.py 27 days ago
inference_detector.py

9.88 kB
v0.3.1: inference detector (4-tier), contradiction question-fallback, improved batch prompt (154 tests pass) 28 days ago
llm_client.py

5.9 kB
Upload src/llm_client.py 28 days ago
metrics.py

15.9 kB
v0.3.2: metric denominator fix, among_accepts metric 28 days ago
pipeline_runner.py

7.22 kB
Upload src/pipeline_runner.py 27 days ago
report.py

8.79 kB
v0.3.2: per-category breakdown, dataset version in report 28 days ago
schemas.py

4.36 kB
v0.3.2: code-quality patch — dedup fix, filter_stats, schema validation, tighter prompt (167 tests) 28 days ago
span_matcher.py

8.45 kB
v0.3.1: inference detector (4-tier), contradiction question-fallback, improved batch prompt (154 tests pass) 28 days ago
validate_gold_cases.py

5.89 kB
v0.3.2: dataset version in validation output 28 days ago
verifier.py

16.3 kB
v0.4: Add filter_supported_claims_by_relevance to normalize extraction across model sizes 27 days ago