{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T44ENWPLFR5FBPBWGG6LLY2DPT","short_pith_number":"pith:T44ENWPL","schema_version":"1.0","canonical_sha256":"9f3846d9eb2c7a50bc3631bcb5e3437ce5c39b4d8d3317480f1db278a8f69957","source":{"kind":"arxiv","id":"2504.13263","version":2},"attestation_state":"computed","paper":{"title":"Causal-Copilot: An Autonomous Causal Analysis Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aryan Philip, Biwei Huang, Fang Nan, Har Simrat Singh, Hou Zhu, Kun Zhou, Parjanya Prashant, Qian Shen, Saloni Patnaik, Shivam Singh, Songyao Jin, Wenyi Wu, Xinyue Wang","submitted_at":"2025-04-17T18:05:39Z","abstract_excerpt":"Causal analysis plays a foundational role in scientific discovery and reliable decision-making, yet it remains largely inaccessible to domain experts due to its conceptual and algorithmic complexity. This disconnect between causal methodology and practical usability presents a dual challenge: domain experts are unable to leverage recent advances in causal learning, while causal researchers lack broad, real-world deployment to test and refine their methods. To address this, we introduce Causal-Copilot, an autonomous agent that operationalizes expert-level causal analysis within a large language"},"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":"2504.13263","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-17T18:05:39Z","cross_cats_sorted":[],"title_canon_sha256":"1391dd4877b58a7d8ed403e8979b66bc1b727f747f00a86de7cad8abd4b15638","abstract_canon_sha256":"695fcdb654b75859bed3f47cb19d83bf48f1e091adb0b1bdb80a7ecac694f9f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:38.840133Z","signature_b64":"zLqG5H/6elTMaIQZovdK7lmP0ANbDkIU0i8q+thCrf1a8nYSr+MNem+eUaJEuBYUJYRxtwP0hHuegpEsJis+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f3846d9eb2c7a50bc3631bcb5e3437ce5c39b4d8d3317480f1db278a8f69957","last_reissued_at":"2026-07-05T10:51:38.839646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:38.839646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal-Copilot: An Autonomous Causal Analysis Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aryan Philip, Biwei Huang, Fang Nan, Har Simrat Singh, Hou Zhu, Kun Zhou, Parjanya Prashant, Qian Shen, Saloni Patnaik, Shivam Singh, Songyao Jin, Wenyi Wu, Xinyue Wang","submitted_at":"2025-04-17T18:05:39Z","abstract_excerpt":"Causal analysis plays a foundational role in scientific discovery and reliable decision-making, yet it remains largely inaccessible to domain experts due to its conceptual and algorithmic complexity. This disconnect between causal methodology and practical usability presents a dual challenge: domain experts are unable to leverage recent advances in causal learning, while causal researchers lack broad, real-world deployment to test and refine their methods. To address this, we introduce Causal-Copilot, an autonomous agent that operationalizes expert-level causal analysis within a large language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13263","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/2504.13263/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":"2504.13263","created_at":"2026-07-05T10:51:38.839703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13263v2","created_at":"2026-07-05T10:51:38.839703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13263","created_at":"2026-07-05T10:51:38.839703+00:00"},{"alias_kind":"pith_short_12","alias_value":"T44ENWPLFR5F","created_at":"2026-07-05T10:51:38.839703+00:00"},{"alias_kind":"pith_short_16","alias_value":"T44ENWPLFR5FBPBW","created_at":"2026-07-05T10:51:38.839703+00:00"},{"alias_kind":"pith_short_8","alias_value":"T44ENWPL","created_at":"2026-07-05T10:51:38.839703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04505","citing_title":"Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision Making","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27022","citing_title":"ORCA: An End-to-End Interactive Copilot for Optimized Root Cause Analysis","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T44ENWPLFR5FBPBWGG6LLY2DPT","json":"https://pith.science/pith/T44ENWPLFR5FBPBWGG6LLY2DPT.json","graph_json":"https://pith.science/api/pith-number/T44ENWPLFR5FBPBWGG6LLY2DPT/graph.json","events_json":"https://pith.science/api/pith-number/T44ENWPLFR5FBPBWGG6LLY2DPT/events.json","paper":"https://pith.science/paper/T44ENWPL"},"agent_actions":{"view_html":"https://pith.science/pith/T44ENWPLFR5FBPBWGG6LLY2DPT","download_json":"https://pith.science/pith/T44ENWPLFR5FBPBWGG6LLY2DPT.json","view_paper":"https://pith.science/paper/T44ENWPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13263&json=true","fetch_graph":"https://pith.science/api/pith-number/T44ENWPLFR5FBPBWGG6LLY2DPT/graph.json","fetch_events":"https://pith.science/api/pith-number/T44ENWPLFR5FBPBWGG6LLY2DPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T44ENWPLFR5FBPBWGG6LLY2DPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T44ENWPLFR5FBPBWGG6LLY2DPT/action/storage_attestation","attest_author":"https://pith.science/pith/T44ENWPLFR5FBPBWGG6LLY2DPT/action/author_attestation","sign_citation":"https://pith.science/pith/T44ENWPLFR5FBPBWGG6LLY2DPT/action/citation_signature","submit_replication":"https://pith.science/pith/T44ENWPLFR5FBPBWGG6LLY2DPT/action/replication_record"}},"created_at":"2026-07-05T10:51:38.839703+00:00","updated_at":"2026-07-05T10:51:38.839703+00:00"}