{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ATMZ2PWQTGWLVVSCF3EURTQ2XW","short_pith_number":"pith:ATMZ2PWQ","schema_version":"1.0","canonical_sha256":"04d99d3ed099acbad6422ec948ce1abd8f5e235cc4246799a739de433553b864","source":{"kind":"arxiv","id":"2412.13667","version":2},"attestation_state":"computed","paper":{"title":"Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ME"],"primary_cat":"cs.LG","authors_text":"ChengAo Shen, Dongkuan Xu, Dongsheng Luo, Haifeng Chen, Jingchao Ni, Zhengzhang Chen","submitted_at":"2024-12-18T09:50:00Z","abstract_excerpt":"Causal discovery is an imperative foundation for decision-making across domains, such as smart health, AI for drug discovery and AIOps. Traditional statistical causal discovery methods, while well-established, predominantly rely on observational data and often overlook the semantic cues inherent in cause-and-effect relationships. The advent of Large Language Models (LLMs) has ushered in an affordable way of leveraging the semantic cues for knowledge-driven causal discovery, but the development of LLMs for causal discovery lags behind other areas, particularly in the exploration of multi-modal "},"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":"2412.13667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T09:50:00Z","cross_cats_sorted":["cs.AI","stat.ME"],"title_canon_sha256":"865386efbd1e707f68fd316f0352c3f4a4c474fe983677a024f079713549c5df","abstract_canon_sha256":"d8f3aa7d3b1ce9d4f7df0d84d65d382b1ac4dc5f284e98aaedb5bd772370b87a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:17.320333Z","signature_b64":"UzG2igVo6XXgKolb4tBHf7BJD1Pb3AkfQqoajUA7fhlWRq5fG9TA8GUa1vhxkqGVrTDHZPOpp7fD20xVpdeqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04d99d3ed099acbad6422ec948ce1abd8f5e235cc4246799a739de433553b864","last_reissued_at":"2026-07-05T11:13:17.319817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:17.319817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ME"],"primary_cat":"cs.LG","authors_text":"ChengAo Shen, Dongkuan Xu, Dongsheng Luo, Haifeng Chen, Jingchao Ni, Zhengzhang Chen","submitted_at":"2024-12-18T09:50:00Z","abstract_excerpt":"Causal discovery is an imperative foundation for decision-making across domains, such as smart health, AI for drug discovery and AIOps. Traditional statistical causal discovery methods, while well-established, predominantly rely on observational data and often overlook the semantic cues inherent in cause-and-effect relationships. The advent of Large Language Models (LLMs) has ushered in an affordable way of leveraging the semantic cues for knowledge-driven causal discovery, but the development of LLMs for causal discovery lags behind other areas, particularly in the exploration of multi-modal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13667","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/2412.13667/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":"2412.13667","created_at":"2026-07-05T11:13:17.319871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13667v2","created_at":"2026-07-05T11:13:17.319871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13667","created_at":"2026-07-05T11:13:17.319871+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATMZ2PWQTGWL","created_at":"2026-07-05T11:13:17.319871+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATMZ2PWQTGWLVVSC","created_at":"2026-07-05T11:13:17.319871+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATMZ2PWQ","created_at":"2026-07-05T11:13:17.319871+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/ATMZ2PWQTGWLVVSCF3EURTQ2XW","json":"https://pith.science/pith/ATMZ2PWQTGWLVVSCF3EURTQ2XW.json","graph_json":"https://pith.science/api/pith-number/ATMZ2PWQTGWLVVSCF3EURTQ2XW/graph.json","events_json":"https://pith.science/api/pith-number/ATMZ2PWQTGWLVVSCF3EURTQ2XW/events.json","paper":"https://pith.science/paper/ATMZ2PWQ"},"agent_actions":{"view_html":"https://pith.science/pith/ATMZ2PWQTGWLVVSCF3EURTQ2XW","download_json":"https://pith.science/pith/ATMZ2PWQTGWLVVSCF3EURTQ2XW.json","view_paper":"https://pith.science/paper/ATMZ2PWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13667&json=true","fetch_graph":"https://pith.science/api/pith-number/ATMZ2PWQTGWLVVSCF3EURTQ2XW/graph.json","fetch_events":"https://pith.science/api/pith-number/ATMZ2PWQTGWLVVSCF3EURTQ2XW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATMZ2PWQTGWLVVSCF3EURTQ2XW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATMZ2PWQTGWLVVSCF3EURTQ2XW/action/storage_attestation","attest_author":"https://pith.science/pith/ATMZ2PWQTGWLVVSCF3EURTQ2XW/action/author_attestation","sign_citation":"https://pith.science/pith/ATMZ2PWQTGWLVVSCF3EURTQ2XW/action/citation_signature","submit_replication":"https://pith.science/pith/ATMZ2PWQTGWLVVSCF3EURTQ2XW/action/replication_record"}},"created_at":"2026-07-05T11:13:17.319871+00:00","updated_at":"2026-07-05T11:13:17.319871+00:00"}