{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WXT2UH52ZMMZ57PJSCJJLDZ3PQ","short_pith_number":"pith:WXT2UH52","schema_version":"1.0","canonical_sha256":"b5e7aa1fbacb199efde99092958f3b7c1d851cf35c6cf593768a104a35288d77","source":{"kind":"arxiv","id":"2505.16982","version":1},"attestation_state":"computed","paper":{"title":"Beyond Correlation: Towards Causal Large Language Model Agents in Biomedicine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.med-ph"],"primary_cat":"cs.AI","authors_text":"Adib Bazgir, Amir Habibdoust Lafmajani, Yuwen Zhang","submitted_at":"2025-05-22T17:52:59Z","abstract_excerpt":"Large Language Models (LLMs) show promise in biomedicine but lack true causal understanding, relying instead on correlations. This paper envisions causal LLM agents that integrate multimodal data (text, images, genomics, etc.) and perform intervention-based reasoning to infer cause-and-effect. Addressing this requires overcoming key challenges: designing safe, controllable agentic frameworks; developing rigorous benchmarks for causal evaluation; integrating heterogeneous data sources; and synergistically combining LLMs with structured knowledge (KGs) and formal causal inference tools. Such age"},"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":"2505.16982","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-22T17:52:59Z","cross_cats_sorted":["physics.med-ph"],"title_canon_sha256":"bcf22cd153e40e30686829a60bf332ceab40a5cc945e8b835d747476d126aae1","abstract_canon_sha256":"5e186a1a216f65140c58f76f8373a4d0ece318fa63dbea753b1da31795b0318a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:44.194643Z","signature_b64":"2N+qfSMncBJouU+JydKEnftDqzV/s8Fe27E943zLKjyXkkfmJAuNyWKnEIOoR7nNetmuQTVla1SSEXrgoMm8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5e7aa1fbacb199efde99092958f3b7c1d851cf35c6cf593768a104a35288d77","last_reissued_at":"2026-07-05T11:07:44.194150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:44.194150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Correlation: Towards Causal Large Language Model Agents in Biomedicine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.med-ph"],"primary_cat":"cs.AI","authors_text":"Adib Bazgir, Amir Habibdoust Lafmajani, Yuwen Zhang","submitted_at":"2025-05-22T17:52:59Z","abstract_excerpt":"Large Language Models (LLMs) show promise in biomedicine but lack true causal understanding, relying instead on correlations. This paper envisions causal LLM agents that integrate multimodal data (text, images, genomics, etc.) and perform intervention-based reasoning to infer cause-and-effect. Addressing this requires overcoming key challenges: designing safe, controllable agentic frameworks; developing rigorous benchmarks for causal evaluation; integrating heterogeneous data sources; and synergistically combining LLMs with structured knowledge (KGs) and formal causal inference tools. Such age"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16982","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/2505.16982/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":"2505.16982","created_at":"2026-07-05T11:07:44.194210+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16982v1","created_at":"2026-07-05T11:07:44.194210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16982","created_at":"2026-07-05T11:07:44.194210+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXT2UH52ZMMZ","created_at":"2026-07-05T11:07:44.194210+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXT2UH52ZMMZ57PJ","created_at":"2026-07-05T11:07:44.194210+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXT2UH52","created_at":"2026-07-05T11:07:44.194210+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/WXT2UH52ZMMZ57PJSCJJLDZ3PQ","json":"https://pith.science/pith/WXT2UH52ZMMZ57PJSCJJLDZ3PQ.json","graph_json":"https://pith.science/api/pith-number/WXT2UH52ZMMZ57PJSCJJLDZ3PQ/graph.json","events_json":"https://pith.science/api/pith-number/WXT2UH52ZMMZ57PJSCJJLDZ3PQ/events.json","paper":"https://pith.science/paper/WXT2UH52"},"agent_actions":{"view_html":"https://pith.science/pith/WXT2UH52ZMMZ57PJSCJJLDZ3PQ","download_json":"https://pith.science/pith/WXT2UH52ZMMZ57PJSCJJLDZ3PQ.json","view_paper":"https://pith.science/paper/WXT2UH52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16982&json=true","fetch_graph":"https://pith.science/api/pith-number/WXT2UH52ZMMZ57PJSCJJLDZ3PQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WXT2UH52ZMMZ57PJSCJJLDZ3PQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXT2UH52ZMMZ57PJSCJJLDZ3PQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXT2UH52ZMMZ57PJSCJJLDZ3PQ/action/storage_attestation","attest_author":"https://pith.science/pith/WXT2UH52ZMMZ57PJSCJJLDZ3PQ/action/author_attestation","sign_citation":"https://pith.science/pith/WXT2UH52ZMMZ57PJSCJJLDZ3PQ/action/citation_signature","submit_replication":"https://pith.science/pith/WXT2UH52ZMMZ57PJSCJJLDZ3PQ/action/replication_record"}},"created_at":"2026-07-05T11:07:44.194210+00:00","updated_at":"2026-07-05T11:07:44.194210+00:00"}