{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UX7H5747DE3ZA7FDNZ6USKQ5PP","short_pith_number":"pith:UX7H5747","schema_version":"1.0","canonical_sha256":"a5fe7eff9f1937907ca36e7d492a1d7bfa7de1dab170710826e539c0cb870099","source":{"kind":"arxiv","id":"2602.05143","version":2},"attestation_state":"computed","paper":{"title":"CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Chaoda Song, Jagdip Singh, Jing Ma, Nengbo Wang, Tuo Liang, Van Yang, Vikash Singh, Vipin Chaudhary, Yu Yin","submitted_at":"2026-02-04T23:59:02Z","abstract_excerpt":"Retrieval augmented generation (RAG) has enhanced large language models by enabling access to external knowledge, with graph-based RAG emerging as a powerful paradigm for structured retrieval and reasoning. However, existing graph-based methods often over-rely on entity-centric node matching and lack explicit causal modeling, leading to unfaithful or spurious answers. Prior attempts to incorporate causality are typically limited to local or single-document contexts and also suffer from information isolation that arises from modular graph structures, which hinders scalability and cross-module c"},"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":"2602.05143","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-04T23:59:02Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"88bd2cfd8617828996284caede50628d3b5ff6eae4e3bc7ff73f3f7eac9b3d2a","abstract_canon_sha256":"4f7e1ab616282b2f1a03fb54105272352ba35b33a0d3ced0fc94bf017fc1163f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:17:50.077768Z","signature_b64":"0h633IzZhvb3JKsur1kCQ9qhx6OmuurJTtvFz26Gg5ryPCAUFFRXpbjm1iyutWww5X2gqo2GJeyKAqNTl0PvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5fe7eff9f1937907ca36e7d492a1d7bfa7de1dab170710826e539c0cb870099","last_reissued_at":"2026-06-25T01:17:50.077183Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:17:50.077183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Chaoda Song, Jagdip Singh, Jing Ma, Nengbo Wang, Tuo Liang, Van Yang, Vikash Singh, Vipin Chaudhary, Yu Yin","submitted_at":"2026-02-04T23:59:02Z","abstract_excerpt":"Retrieval augmented generation (RAG) has enhanced large language models by enabling access to external knowledge, with graph-based RAG emerging as a powerful paradigm for structured retrieval and reasoning. However, existing graph-based methods often over-rely on entity-centric node matching and lack explicit causal modeling, leading to unfaithful or spurious answers. Prior attempts to incorporate causality are typically limited to local or single-document contexts and also suffer from information isolation that arises from modular graph structures, which hinders scalability and cross-module c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.05143","kind":"arxiv","version":2},"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/2602.05143/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":"2602.05143","created_at":"2026-06-25T01:17:50.077246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.05143v2","created_at":"2026-06-25T01:17:50.077246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.05143","created_at":"2026-06-25T01:17:50.077246+00:00"},{"alias_kind":"pith_short_12","alias_value":"UX7H5747DE3Z","created_at":"2026-06-25T01:17:50.077246+00:00"},{"alias_kind":"pith_short_16","alias_value":"UX7H5747DE3ZA7FD","created_at":"2026-06-25T01:17:50.077246+00:00"},{"alias_kind":"pith_short_8","alias_value":"UX7H5747","created_at":"2026-06-25T01:17:50.077246+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.21928","citing_title":"CausalGuard: Conformal Inference under Graph Uncertainty","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14063","citing_title":"Reliability-Gated Source Anchoring for Continual Test-Time Adaptation","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14063","citing_title":"Reliability-Gated Source Anchoring for Continual Test-Time Adaptation","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UX7H5747DE3ZA7FDNZ6USKQ5PP","json":"https://pith.science/pith/UX7H5747DE3ZA7FDNZ6USKQ5PP.json","graph_json":"https://pith.science/api/pith-number/UX7H5747DE3ZA7FDNZ6USKQ5PP/graph.json","events_json":"https://pith.science/api/pith-number/UX7H5747DE3ZA7FDNZ6USKQ5PP/events.json","paper":"https://pith.science/paper/UX7H5747"},"agent_actions":{"view_html":"https://pith.science/pith/UX7H5747DE3ZA7FDNZ6USKQ5PP","download_json":"https://pith.science/pith/UX7H5747DE3ZA7FDNZ6USKQ5PP.json","view_paper":"https://pith.science/paper/UX7H5747","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.05143&json=true","fetch_graph":"https://pith.science/api/pith-number/UX7H5747DE3ZA7FDNZ6USKQ5PP/graph.json","fetch_events":"https://pith.science/api/pith-number/UX7H5747DE3ZA7FDNZ6USKQ5PP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UX7H5747DE3ZA7FDNZ6USKQ5PP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UX7H5747DE3ZA7FDNZ6USKQ5PP/action/storage_attestation","attest_author":"https://pith.science/pith/UX7H5747DE3ZA7FDNZ6USKQ5PP/action/author_attestation","sign_citation":"https://pith.science/pith/UX7H5747DE3ZA7FDNZ6USKQ5PP/action/citation_signature","submit_replication":"https://pith.science/pith/UX7H5747DE3ZA7FDNZ6USKQ5PP/action/replication_record"}},"created_at":"2026-06-25T01:17:50.077246+00:00","updated_at":"2026-06-25T01:17:50.077246+00:00"}