Benjamin Admin de542633e2 feat(controls): Zitierfaehigkeit — Embedding-Re-Link + Atom-Vererbung ...

citation_backfill Tier-1 von totem sha256-Hash auf Semantik-Suche gegen die
re-ingestierten, article_label-tragenden Chunks umgestellt (Fundstelle aus
article_label); rag_client reicht article_label durch (additiv, Default-Feld).
NEU: scripts/atom_citation_inheritance.py vererbt source_citation parent->atom
(license_rule != 3), iterativ. macmini-Apply verifiziert: Zitierfaehigkeit
6.9%->61.3% (+171.765 Atome), Stichprobe korrekt (Atom == Parent-Fundstelle).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-06-21 14:17:57 +02:00

..

apply_quaidal_to_db.py

feat(control-pipeline): BSI QUAIDAL Clean-Room ingestion (AI Act Art. 10)

2026-05-19 13:02:49 +02:00

atom_citation_inheritance.py

feat(controls): Zitierfaehigkeit — Embedding-Re-Link + Atom-Vererbung

2026-06-21 14:17:57 +02:00

audit_license_classification.py

docs(licenses): freeze 3-rule license mapping + audit script

2026-05-21 11:29:38 +02:00

backfill_license_rule.py

feat(licenses): postgres + qdrant license_rule backfill scripts

2026-05-21 18:46:57 +02:00

backfill_qdrant_license_payload.py

feat(licenses): postgres + qdrant license_rule backfill scripts

2026-05-21 18:46:57 +02:00

d6_citation_backfill.py

feat(pipeline): D6 citation backfill + E2/E3 law ingestion scripts

2026-05-03 13:19:27 +02:00

derive_doc_check_controls.py

feat(pipeline): derive 1,874 doc_check_controls from Master Controls

2026-05-10 20:56:23 +02:00

derive_quaidal_mcs.py

feat(control-pipeline): BSI QUAIDAL Clean-Room ingestion (AI Act Art. 10)

2026-05-19 13:02:49 +02:00

extract_and_upload_nist.py

fix(embedding): add NIST control IDs to _SECTION_NUMBER_RE

2026-05-03 07:42:06 +02:00

extract_ce_obligations.py

feat(pipeline): MC Quality Overhaul — 74.5% → 92.8% accuracy, 5.3K → 13.6K MCs

2026-05-10 15:08:15 +02:00

f1_migrate_regulation_registry.py

feat(pipeline): F1 regulation registry — DB-backed license/source-type lookup

2026-05-03 23:14:06 +02:00

f2_migrate_actions.py

feat(pipeline): F2+F3 action/object ontology — DB-backed normalization

2026-05-03 23:47:53 +02:00

f3_migrate_objects.py

feat(pipeline): F2+F3 action/object ontology — DB-backed normalization

2026-05-03 23:47:53 +02:00

f4_llm_enrich_synonyms.py

feat(pipeline): F4 LLM synonym enrichment script

2026-05-05 15:45:43 +02:00

gpre0_add_subtopics.py

feat(pipeline): MC Quality Overhaul — 74.5% → 92.8% accuracy, 5.3K → 13.6K MCs

2026-05-10 15:08:15 +02:00

gpre0_apply_corrections.py

feat(pipeline): MC Quality Overhaul — 74.5% → 92.8% accuracy, 5.3K → 13.6K MCs

2026-05-10 15:08:15 +02:00

gpre0_fix_bad_subtopics.py

feat(pipeline): MC Quality Overhaul — 74.5% → 92.8% accuracy, 5.3K → 13.6K MCs

2026-05-10 15:08:15 +02:00

gpre0_fix_generic_tokens.py

feat(pipeline): MC Quality Overhaul — 74.5% → 92.8% accuracy, 5.3K → 13.6K MCs

2026-05-10 15:08:15 +02:00

gpre0_run_all.sh

feat(pipeline): MC Quality Overhaul — 74.5% → 92.8% accuracy, 5.3K → 13.6K MCs

2026-05-10 15:08:15 +02:00

gpre0_validate_hints.py

feat(pipeline): MC Quality Overhaul — 74.5% → 92.8% accuracy, 5.3K → 13.6K MCs

2026-05-10 15:08:15 +02:00

gpre1_analyze.py

docs: session handover — Block F complete, pipeline done, G-pre1 analysis

2026-05-05 18:02:10 +02:00

gpre1_object_clustering.py

feat(pipeline): G-pre1/2/3 — Object Clustering + Master Controls + API

2026-05-06 15:11:38 +02:00

gpre1_object_groups_incremental.py

feat(control-pipeline): incremental dedup + ENISA CRA ingestion

2026-05-18 18:21:46 +02:00

gpre1_refine_large.py

feat(pipeline): G-pre1 refinement script for large object groups

2026-05-06 20:41:49 +02:00

gpre1_subcluster.py

feat(pipeline): G-pre1/2/3 — Object Clustering + Master Controls + API

2026-05-06 15:11:38 +02:00

gpre2_direct_mc.py

feat(pipeline): MC Quality Overhaul — 74.5% → 92.8% accuracy, 5.3K → 13.6K MCs

2026-05-10 15:08:15 +02:00

gpre2_master_controls_incremental.py

feat(control-pipeline): incremental dedup + ENISA CRA ingestion

2026-05-18 18:21:46 +02:00

gpre2_master_controls.py

feat(pipeline): G-pre1/2/3 — Object Clustering + Master Controls + API

2026-05-06 15:11:38 +02:00

gpre3_regulation_split.py

feat(pipeline): MC Quality Overhaul — 74.5% → 92.8% accuracy, 5.3K → 13.6K MCs

2026-05-10 15:08:15 +02:00

gpre_quality_audit.py

feat(pipeline): MC Quality Overhaul — 74.5% → 92.8% accuracy, 5.3K → 13.6K MCs

2026-05-10 15:08:15 +02:00

import_backup.py

…

ingest_bag_urteile.py

…

ingest_bsi_quaidal.py

feat(control-pipeline): BSI QUAIDAL Clean-Room ingestion (AI Act Art. 10)

2026-05-19 13:02:49 +02:00

ingest_de_laws.py

feat(pipeline): D6 citation backfill + E2/E3 law ingestion scripts

2026-05-03 13:19:27 +02:00

ingest_enisa_cra.py

feat(control-pipeline): incremental dedup + ENISA CRA ingestion

2026-05-18 18:21:46 +02:00

ingest_eu_regulations.py

feat(pipeline): D6 citation backfill + E2/E3 law ingestion scripts

2026-05-03 13:19:27 +02:00

migrate_jsonb.py

…

quality_report.py

docs: session handover — D2-D5 complete, quality report, NIST plan

2026-05-02 22:22:55 +02:00

reingest_d5_config.py

fix(rag): strip HTML tags before chunking + D5 re-ingestion scripts

2026-05-02 08:18:25 +02:00

reingest_d5.py

feat(embedding): NIST PDF text normalization + safe re-ingest script

2026-05-03 06:42:46 +02:00

reingest_nist.py

feat(embedding): NIST PDF text normalization + safe re-ingest script

2026-05-03 06:42:46 +02:00

replace_eu_pdfs_with_html.py

feat(embedding): add NIST/ENISA/standard section numbering to chunker

2026-05-02 19:24:10 +02:00

reupload_legal_strategy.py

feat(pipeline): Block D5+-E complete session — 20k+ new chunks

2026-05-03 22:31:57 +02:00

test_d4_integration.py

feat(pipeline): structural metadata end-to-end (Blocks D2-D4)

2026-05-01 20:34:00 +02:00

test_qwen_backfill.py

perf(pipeline): switch to v3 prompt for generation, v4 fields via Haiku backfill

2026-04-27 00:14:47 +02:00