Spaces:

GonzaViss
/

Judge

Running

App Files Files Community

Judge / backend /scripts

152 kB

Ctrl+K

Ctrl+K

3 contributors

History: 39 commits

GonzaViss's picture

fix(eval): remove erroneous await on synchronous answer_question

3ff865a 2 days ago

__init__.py

0 Bytes
feat: repo structure, corpus pipeline scripts, and PDF parser about 2 months ago
add_corpus_v1_2_0.py

862 Bytes
feat(rag): re-chunk rulebook by rule number for precise retrieval about 2 months ago
authority_boost_probe.py

4.12 kB
docs(scripts): aclara que la probe modela solo el brazo raw, no fuse_eq completo 13 days ago
backup_corpus.py

1.85 kB
chore(scripts): backup de corpus_chunks a CSV restaurable previo a re-ingest 14 days ago
build_corpus.py

4.43 kB
feat(corpus): parse errata y build_corpus por expansion about 1 month ago
card_presence_probe.py

9.23 kB
test(rag): probe determinístico de presencia de cartas (guard del fix entity-aware) 8 days ago
create_test_fixtures.py

2.79 kB
feat: repo structure, corpus pipeline scripts, and PDF parser about 2 months ago
eval.py

17.7 kB
fix(eval): remove erroneous await on synchronous answer_question 2 days ago
eval_judge.py

10.3 kB
fix(eval): endurece el harness del juez (5 findings del code-review #17) 11 days ago
extract_keywords.py

1.75 kB
feat(rag): add @tag system and per-keyword chunks for precise retrieval about 2 months ago
fts_keyword_probe.py

6.74 kB
perf(retrieval): probe Lever 1 FTS-keyword — medido PERDEDOR (regresa 59->47@5, no rescata semantic-gap misses) 13 days ago
ingest.py

14.4 kB
feat(ingest): budget de chunk chico para el rulebook (estrategia A) 14 days ago
keyword_eviction_probe.py

5.14 kB
fix(rag): auto-keywords no desplazan chunks semánticos en el contexto 9 days ago
lineage_offline_probe.py

10.2 kB
perf(retrieval): probe Lever 2 lineage offline — medido NO gana @5 (59->53), solo rescata 1 miss a rank9 @10 13 days ago
migrate_corpus_version.py

691 Bytes
chore(corpus): add parser and migration scripts for v1.3.0 about 2 months ago
miss_diagnosis.py

7.42 kB
perf(retrieval): miss_diagnosis script clasifica chunking-misses en granularidad vs gap semantico (Phase 0, LLM-free) 13 days ago
parse_cards.py

10.5 kB
fix(cards): collapse cosmetic card variants by shared artwork about 1 month ago
parse_errata.py

4.8 kB
feat(corpus): parse errata y build_corpus por expansion about 1 month ago
parse_faq.py

3.08 kB
feat: add errata parser (parse_faq.py) about 2 months ago
parse_patch_notes.py

3.48 kB
chore(corpus): add parser and migration scripts for v1.3.0 about 2 months ago
parse_rulebook.py

2.94 kB
feat(rag): re-chunk rulebook by rule number for precise retrieval about 2 months ago
parse_rules_faq.py

8.99 kB
feat(corpus): add Unleashed Rules FAQ as corpus source v1.3.0 about 2 months ago
parse_tournament_rules.py

618 Bytes
chore(corpus): add parser and migration scripts for v1.3.0 about 2 months ago
recall_probe.py

2.18 kB
test(scripts): smoke v2.0.0 y medicion de recall del indice about 1 month ago
retrieval_probe.py

8.15 kB
feat(eval): sonda de retrieval recall por rank y fuente 15 days ago
rewrite_experiment.py

5.87 kB
feat(retrieval): RRF fusion raw+HyDE lifts recall@5 41%->59% 14 days ago
smoke_v2.py

1.83 kB
test(scripts): smoke v2.0.0 y medicion de recall del indice about 1 month ago
validate_query.py

1.61 kB
feat: add validate_query script for retrieval validation about 2 months ago