Spaces:

SooryaKi
/

ScamSentry

Running

App Files Files Community

ScamSentry / eval

209 kB

Ctrl+K

2 contributors

History: 4 commits

SooryaKiranKakkarayil

Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts

6b6557c 4 months ago

cases
Day 4 complete: 3-layer injection defense, 15/15 on adversarial suite, transient-error retry hardening 4 months ago
RESULTS.md

4.84 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
diagnose_rpd_flag.py

3.29 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
fix_batch2_labels.py

2.34 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
golden_eval_results.jsonl

10.9 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
golden_sample.csv

103 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
injection_suite_results.json

12.2 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
inspect_misses.py

548 Bytes
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
inspect_rows.py

865 Bytes
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
llm_judge_results.jsonl

2 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
prepare_golden_sample.py

1.01 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
prepare_golden_sample_batch2.py

3.44 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
run_eval.py

8.57 kB
Day 3 complete: fix url_reputation_agent output_schema+tools bug, fix eval harness suffix bug, switch to gemini-3.1-flash-lite, all 9 EDD cases + full smoke test pass 4 months ago
run_golden_eval.py

6.72 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
run_injection_suite.py

6.3 kB
Day 4 complete: 3-layer injection defense, 15/15 on adversarial suite, transient-error retry hardening 4 months ago
run_llm_judge.py

8.25 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
run_pass_k.py

8.02 kB
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago
score_golden_eval.py

601 Bytes
Day 6: fix batch2 labels, fix LLM-judge verdict bug, add pass_k and rpd diagnostic scripts 4 months ago