{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LER2ZLNO5K2N2PST567XUNQINT","short_pith_number":"pith:LER2ZLNO","schema_version":"1.0","canonical_sha256":"5923acadaeeab4dd3e53efbf7a36086cc6f1709746094d53060655be186d7e98","source":{"kind":"arxiv","id":"2306.16902","version":2},"attestation_state":"computed","paper":{"title":"Integrating Large Language Model for Improved Causal Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Derui Lyu, Huanhuan Chen, Lyuzhou Chen, Qiang Tu, Qinrui Zhu, Taiyu Ban, Xiangyu Wang","submitted_at":"2023-06-29T12:48:00Z","abstract_excerpt":"Recovering the structure of causal graphical models from observational data is an essential yet challenging task for causal discovery in scientific scenarios. Domain-specific causal discovery usually relies on expert validation or prior analysis to improve the reliability of recovered causality, which is yet limited by the scarcity of expert resources. Recently, Large Language Models (LLM) have been used for causal analysis across various domain-specific scenarios, suggesting its potential as autonomous expert roles in guiding data-based structure learning. However, integrating LLMs into causa"},"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":"2306.16902","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-06-29T12:48:00Z","cross_cats_sorted":[],"title_canon_sha256":"f3682a6403a83d2b9ab3221e1e1efb136821015400ce90a138f10cc9bcc05be5","abstract_canon_sha256":"9c18e4947b7d174710aab2790b3ed10ca9cbd776684768400d8b2fbf781a04b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:03.237334Z","signature_b64":"S9Ex9n2cu7m7BG+Rkxi7Zwi4aEQI2r8A8X6zfMjPpG/3QFz5k0MO7lsjnAkkQHFCD0mozdt6+l6KbMWd2RaYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5923acadaeeab4dd3e53efbf7a36086cc6f1709746094d53060655be186d7e98","last_reissued_at":"2026-07-05T11:59:03.236842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:03.236842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrating Large Language Model for Improved Causal Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Derui Lyu, Huanhuan Chen, Lyuzhou Chen, Qiang Tu, Qinrui Zhu, Taiyu Ban, Xiangyu Wang","submitted_at":"2023-06-29T12:48:00Z","abstract_excerpt":"Recovering the structure of causal graphical models from observational data is an essential yet challenging task for causal discovery in scientific scenarios. Domain-specific causal discovery usually relies on expert validation or prior analysis to improve the reliability of recovered causality, which is yet limited by the scarcity of expert resources. Recently, Large Language Models (LLM) have been used for causal analysis across various domain-specific scenarios, suggesting its potential as autonomous expert roles in guiding data-based structure learning. However, integrating LLMs into causa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16902","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/2306.16902/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":"2306.16902","created_at":"2026-07-05T11:59:03.236901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.16902v2","created_at":"2026-07-05T11:59:03.236901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16902","created_at":"2026-07-05T11:59:03.236901+00:00"},{"alias_kind":"pith_short_12","alias_value":"LER2ZLNO5K2N","created_at":"2026-07-05T11:59:03.236901+00:00"},{"alias_kind":"pith_short_16","alias_value":"LER2ZLNO5K2N2PST","created_at":"2026-07-05T11:59:03.236901+00:00"},{"alias_kind":"pith_short_8","alias_value":"LER2ZLNO","created_at":"2026-07-05T11:59:03.236901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23741","citing_title":"A Survey on Federated Causal Discovery and Inference","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21928","citing_title":"CausalGuard: Conformal Inference under Graph Uncertainty","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16234","citing_title":"Sequential Causal Discovery with Noisy Language Model Priors","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01669","citing_title":"PRCD-MAP: Learning How Much to Trust Imperfect Priors in Causal Discovery","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LER2ZLNO5K2N2PST567XUNQINT","json":"https://pith.science/pith/LER2ZLNO5K2N2PST567XUNQINT.json","graph_json":"https://pith.science/api/pith-number/LER2ZLNO5K2N2PST567XUNQINT/graph.json","events_json":"https://pith.science/api/pith-number/LER2ZLNO5K2N2PST567XUNQINT/events.json","paper":"https://pith.science/paper/LER2ZLNO"},"agent_actions":{"view_html":"https://pith.science/pith/LER2ZLNO5K2N2PST567XUNQINT","download_json":"https://pith.science/pith/LER2ZLNO5K2N2PST567XUNQINT.json","view_paper":"https://pith.science/paper/LER2ZLNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.16902&json=true","fetch_graph":"https://pith.science/api/pith-number/LER2ZLNO5K2N2PST567XUNQINT/graph.json","fetch_events":"https://pith.science/api/pith-number/LER2ZLNO5K2N2PST567XUNQINT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LER2ZLNO5K2N2PST567XUNQINT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LER2ZLNO5K2N2PST567XUNQINT/action/storage_attestation","attest_author":"https://pith.science/pith/LER2ZLNO5K2N2PST567XUNQINT/action/author_attestation","sign_citation":"https://pith.science/pith/LER2ZLNO5K2N2PST567XUNQINT/action/citation_signature","submit_replication":"https://pith.science/pith/LER2ZLNO5K2N2PST567XUNQINT/action/replication_record"}},"created_at":"2026-07-05T11:59:03.236901+00:00","updated_at":"2026-07-05T11:59:03.236901+00:00"}