{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DYKVTGU7QEZ2FSVTVOAVTX2BYE","short_pith_number":"pith:DYKVTGU7","schema_version":"1.0","canonical_sha256":"1e15599a9f8133a2cab3ab8159df41c1022997eb5e7336879ff4934c56e99d81","source":{"kind":"arxiv","id":"2607.09348","version":1},"attestation_state":"computed","paper":{"title":"DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fang Chen, Jin Li, Kun Yu, Shoujin Wang, Xin Li","submitted_at":"2026-07-10T12:28:50Z","abstract_excerpt":"Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise domains such as healthcare, finance, and education. Existing methods typically leverage the general knowledge of large language models (LLMs) to identify causal factors from unstructured data and annotate them into structured data for causal graph construction. However, they remain limited by two key challenges (CHs): (CH1) insufficient identification of latent factors, which are implicit in the data yet essential for causal discovery, due to the lack of domain-specific knowledge; and (CH2) unreli"},"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":"2607.09348","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T12:28:50Z","cross_cats_sorted":[],"title_canon_sha256":"95ff4956b8031e2b2c7860683e5897e4a393eb62275047270c7a1bb860629fe7","abstract_canon_sha256":"2fb3e2d0754bbddc19ed8fe7f6aea68b6c71b5f1126045950cf9953e29660f57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:19:04.600493Z","signature_b64":"Uqy1VFIWbS4TKQiiv2gh+QeFmAkcjnzzL6gYgKQvcBTL4AgnXv9/X3i7AhVO15aGdeU4z9SCSjTyJsqmMxg8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e15599a9f8133a2cab3ab8159df41c1022997eb5e7336879ff4934c56e99d81","last_reissued_at":"2026-07-13T01:19:04.599067Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:19:04.599067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fang Chen, Jin Li, Kun Yu, Shoujin Wang, Xin Li","submitted_at":"2026-07-10T12:28:50Z","abstract_excerpt":"Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise domains such as healthcare, finance, and education. Existing methods typically leverage the general knowledge of large language models (LLMs) to identify causal factors from unstructured data and annotate them into structured data for causal graph construction. However, they remain limited by two key challenges (CHs): (CH1) insufficient identification of latent factors, which are implicit in the data yet essential for causal discovery, due to the lack of domain-specific knowledge; and (CH2) unreli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09348","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/2607.09348/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":"2607.09348","created_at":"2026-07-13T01:19:04.599950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09348v1","created_at":"2026-07-13T01:19:04.599950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09348","created_at":"2026-07-13T01:19:04.599950+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYKVTGU7QEZ2","created_at":"2026-07-13T01:19:04.599950+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYKVTGU7QEZ2FSVT","created_at":"2026-07-13T01:19:04.599950+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYKVTGU7","created_at":"2026-07-13T01:19:04.599950+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/DYKVTGU7QEZ2FSVTVOAVTX2BYE","json":"https://pith.science/pith/DYKVTGU7QEZ2FSVTVOAVTX2BYE.json","graph_json":"https://pith.science/api/pith-number/DYKVTGU7QEZ2FSVTVOAVTX2BYE/graph.json","events_json":"https://pith.science/api/pith-number/DYKVTGU7QEZ2FSVTVOAVTX2BYE/events.json","paper":"https://pith.science/paper/DYKVTGU7"},"agent_actions":{"view_html":"https://pith.science/pith/DYKVTGU7QEZ2FSVTVOAVTX2BYE","download_json":"https://pith.science/pith/DYKVTGU7QEZ2FSVTVOAVTX2BYE.json","view_paper":"https://pith.science/paper/DYKVTGU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09348&json=true","fetch_graph":"https://pith.science/api/pith-number/DYKVTGU7QEZ2FSVTVOAVTX2BYE/graph.json","fetch_events":"https://pith.science/api/pith-number/DYKVTGU7QEZ2FSVTVOAVTX2BYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYKVTGU7QEZ2FSVTVOAVTX2BYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYKVTGU7QEZ2FSVTVOAVTX2BYE/action/storage_attestation","attest_author":"https://pith.science/pith/DYKVTGU7QEZ2FSVTVOAVTX2BYE/action/author_attestation","sign_citation":"https://pith.science/pith/DYKVTGU7QEZ2FSVTVOAVTX2BYE/action/citation_signature","submit_replication":"https://pith.science/pith/DYKVTGU7QEZ2FSVTVOAVTX2BYE/action/replication_record"}},"created_at":"2026-07-13T01:19:04.599950+00:00","updated_at":"2026-07-13T01:19:04.599950+00:00"}