{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GCWJXQZN6DNIBLBL5N44Q2NWJJ","short_pith_number":"pith:GCWJXQZN","schema_version":"1.0","canonical_sha256":"30ac9bc32df0da80ac2beb79c869b64a657ad008b32b5654b50999b4431716ef","source":{"kind":"arxiv","id":"2605.29742","version":1},"attestation_state":"computed","paper":{"title":"Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Seong-Whan Lee, Yeong-Joon Ju","submitted_at":"2026-05-28T10:38:38Z","abstract_excerpt":"Deploying Large Language Models (LLMs) for regulatory compliance demands rigorous traceability via comprehensive citations across multi-tiered authority structures. Unlike traditional multi-hop or legal QA, this task requires structured procedural lookups and evidence-set closure rather than entity resolution or case-law reasoning. Existing RAG systems struggle here due to flattened citation edges, fragmented retrieval expansions, and fragile post-hoc attribution. We formalize Regulatory Compliance QA with RegOps-Bench, a novel benchmark featuring an Operational Knowledge Graph derived from co"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.29742","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T10:38:38Z","cross_cats_sorted":[],"title_canon_sha256":"d37d18ac544008ed11d2dd113ff083763f41d85feb9fd6df00135a08dac170d2","abstract_canon_sha256":"3773133e381cd96b3c34ab2df115efd47e27e2a070c6c116a9ee52e15cecb6c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:57.590058Z","signature_b64":"gLZhGbcKeHYS/8sl5y+VMAEOjxgBdkGhC8Cwf9QOQh4s4d7K8Foh+1huJIEQwDfoRl+fxgyRH7/XokkIpiUjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30ac9bc32df0da80ac2beb79c869b64a657ad008b32b5654b50999b4431716ef","last_reissued_at":"2026-05-29T01:05:57.589633Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:57.589633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Seong-Whan Lee, Yeong-Joon Ju","submitted_at":"2026-05-28T10:38:38Z","abstract_excerpt":"Deploying Large Language Models (LLMs) for regulatory compliance demands rigorous traceability via comprehensive citations across multi-tiered authority structures. Unlike traditional multi-hop or legal QA, this task requires structured procedural lookups and evidence-set closure rather than entity resolution or case-law reasoning. Existing RAG systems struggle here due to flattened citation edges, fragmented retrieval expansions, and fragile post-hoc attribution. We formalize Regulatory Compliance QA with RegOps-Bench, a novel benchmark featuring an Operational Knowledge Graph derived from co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29742","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.29742/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.29742","created_at":"2026-05-29T01:05:57.589693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29742v1","created_at":"2026-05-29T01:05:57.589693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29742","created_at":"2026-05-29T01:05:57.589693+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCWJXQZN6DNI","created_at":"2026-05-29T01:05:57.589693+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCWJXQZN6DNIBLBL","created_at":"2026-05-29T01:05:57.589693+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCWJXQZN","created_at":"2026-05-29T01:05:57.589693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCWJXQZN6DNIBLBL5N44Q2NWJJ","json":"https://pith.science/pith/GCWJXQZN6DNIBLBL5N44Q2NWJJ.json","graph_json":"https://pith.science/api/pith-number/GCWJXQZN6DNIBLBL5N44Q2NWJJ/graph.json","events_json":"https://pith.science/api/pith-number/GCWJXQZN6DNIBLBL5N44Q2NWJJ/events.json","paper":"https://pith.science/paper/GCWJXQZN"},"agent_actions":{"view_html":"https://pith.science/pith/GCWJXQZN6DNIBLBL5N44Q2NWJJ","download_json":"https://pith.science/pith/GCWJXQZN6DNIBLBL5N44Q2NWJJ.json","view_paper":"https://pith.science/paper/GCWJXQZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29742&json=true","fetch_graph":"https://pith.science/api/pith-number/GCWJXQZN6DNIBLBL5N44Q2NWJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GCWJXQZN6DNIBLBL5N44Q2NWJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCWJXQZN6DNIBLBL5N44Q2NWJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCWJXQZN6DNIBLBL5N44Q2NWJJ/action/storage_attestation","attest_author":"https://pith.science/pith/GCWJXQZN6DNIBLBL5N44Q2NWJJ/action/author_attestation","sign_citation":"https://pith.science/pith/GCWJXQZN6DNIBLBL5N44Q2NWJJ/action/citation_signature","submit_replication":"https://pith.science/pith/GCWJXQZN6DNIBLBL5N44Q2NWJJ/action/replication_record"}},"created_at":"2026-05-29T01:05:57.589693+00:00","updated_at":"2026-05-29T01:05:57.589693+00:00"}