{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A52PLTW4OYUDT7O26WIY5JDXBS","short_pith_number":"pith:A52PLTW4","schema_version":"1.0","canonical_sha256":"0774f5cedc762839fddaf5918ea4770c80450dd0412445e229986a9cabb1df70","source":{"kind":"arxiv","id":"2503.04556","version":4},"attestation_state":"computed","paper":{"title":"Compositional Causal Reasoning Evaluation in Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya V. Nori, Alihan H\\\"uy\\\"uk, Jacqueline R. M. A. Maasch, Javier Gonzalez, Xinnuo Xu","submitted_at":"2025-03-06T15:47:19Z","abstract_excerpt":"Causal reasoning and compositional reasoning are two core aspirations in AI. Measuring the extent of these behaviors requires principled evaluation methods. We explore a unified perspective that considers both behaviors simultaneously, termed compositional causal reasoning (CCR): the ability to infer how causal measures compose and, equivalently, how causal quantities propagate through graphs. We instantiate a framework for the systematic evaluation of CCR for the average treatment effect and the probability of necessity and sufficiency. As proof of concept, we demonstrate CCR evaluation for l"},"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":"2503.04556","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T15:47:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9f384ff48e9ef8671a4d64b6e6a1e14ed60b3422145b9a4f53d6e18eeb68c535","abstract_canon_sha256":"5815cda5274ffd9055d5c1bc300f1eefbd8cc1ee8e036a68b299c06aa30d0f57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:04.203969Z","signature_b64":"itXOAMEtpE5HxbnJDFbCcGRvkge9davvcSgwiMXxzAQh33cZW0GGINcq1W6S7AI5kPhmiIIOuQUCnQJhSR9hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0774f5cedc762839fddaf5918ea4770c80450dd0412445e229986a9cabb1df70","last_reissued_at":"2026-07-05T11:19:04.203493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:04.203493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Causal Reasoning Evaluation in Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya V. Nori, Alihan H\\\"uy\\\"uk, Jacqueline R. M. A. Maasch, Javier Gonzalez, Xinnuo Xu","submitted_at":"2025-03-06T15:47:19Z","abstract_excerpt":"Causal reasoning and compositional reasoning are two core aspirations in AI. Measuring the extent of these behaviors requires principled evaluation methods. We explore a unified perspective that considers both behaviors simultaneously, termed compositional causal reasoning (CCR): the ability to infer how causal measures compose and, equivalently, how causal quantities propagate through graphs. We instantiate a framework for the systematic evaluation of CCR for the average treatment effect and the probability of necessity and sufficiency. As proof of concept, we demonstrate CCR evaluation for l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04556","kind":"arxiv","version":4},"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/2503.04556/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":"2503.04556","created_at":"2026-07-05T11:19:04.203555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04556v4","created_at":"2026-07-05T11:19:04.203555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04556","created_at":"2026-07-05T11:19:04.203555+00:00"},{"alias_kind":"pith_short_12","alias_value":"A52PLTW4OYUD","created_at":"2026-07-05T11:19:04.203555+00:00"},{"alias_kind":"pith_short_16","alias_value":"A52PLTW4OYUDT7O2","created_at":"2026-07-05T11:19:04.203555+00:00"},{"alias_kind":"pith_short_8","alias_value":"A52PLTW4","created_at":"2026-07-05T11:19:04.203555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26655","citing_title":"Why Prompt Optimization Works, and Why It Sometimes Doesn't: A Causal-Inspired Edit-Level Analysis","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27589","citing_title":"What-If World: A Causal Benchmark for General World Models in Embodied Scenarios","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09079","citing_title":"CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulators","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A52PLTW4OYUDT7O26WIY5JDXBS","json":"https://pith.science/pith/A52PLTW4OYUDT7O26WIY5JDXBS.json","graph_json":"https://pith.science/api/pith-number/A52PLTW4OYUDT7O26WIY5JDXBS/graph.json","events_json":"https://pith.science/api/pith-number/A52PLTW4OYUDT7O26WIY5JDXBS/events.json","paper":"https://pith.science/paper/A52PLTW4"},"agent_actions":{"view_html":"https://pith.science/pith/A52PLTW4OYUDT7O26WIY5JDXBS","download_json":"https://pith.science/pith/A52PLTW4OYUDT7O26WIY5JDXBS.json","view_paper":"https://pith.science/paper/A52PLTW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04556&json=true","fetch_graph":"https://pith.science/api/pith-number/A52PLTW4OYUDT7O26WIY5JDXBS/graph.json","fetch_events":"https://pith.science/api/pith-number/A52PLTW4OYUDT7O26WIY5JDXBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A52PLTW4OYUDT7O26WIY5JDXBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A52PLTW4OYUDT7O26WIY5JDXBS/action/storage_attestation","attest_author":"https://pith.science/pith/A52PLTW4OYUDT7O26WIY5JDXBS/action/author_attestation","sign_citation":"https://pith.science/pith/A52PLTW4OYUDT7O26WIY5JDXBS/action/citation_signature","submit_replication":"https://pith.science/pith/A52PLTW4OYUDT7O26WIY5JDXBS/action/replication_record"}},"created_at":"2026-07-05T11:19:04.203555+00:00","updated_at":"2026-07-05T11:19:04.203555+00:00"}