{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A52PLTW4OYUDT7O26WIY5JDXBS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5815cda5274ffd9055d5c1bc300f1eefbd8cc1ee8e036a68b299c06aa30d0f57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T15:47:19Z","title_canon_sha256":"9f384ff48e9ef8671a4d64b6e6a1e14ed60b3422145b9a4f53d6e18eeb68c535"},"schema_version":"1.0","source":{"id":"2503.04556","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04556","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04556v4","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04556","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"A52PLTW4OYUD","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"pith_short_16","alias_value":"A52PLTW4OYUDT7O2","created_at":"2026-07-05T11:19:04Z"},{"alias_kind":"pith_short_8","alias_value":"A52PLTW4","created_at":"2026-07-05T11:19:04Z"}],"graph_snapshots":[{"event_id":"sha256:2d432679770523160f419f8c2ce2956156a116058c6d42c258e183f0b8dc83e3","target":"graph","created_at":"2026-07-05T11:19:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.04556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aditya V. Nori, Alihan H\\\"uy\\\"uk, Jacqueline R. M. A. Maasch, Javier Gonzalez, Xinnuo Xu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T15:47:19Z","title":"Compositional Causal Reasoning Evaluation in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04556","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:32fa3d52da56bd77b99826e272fa17efc92dfddf773b10986cb3b1f566d50130","target":"record","created_at":"2026-07-05T11:19:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5815cda5274ffd9055d5c1bc300f1eefbd8cc1ee8e036a68b299c06aa30d0f57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T15:47:19Z","title_canon_sha256":"9f384ff48e9ef8671a4d64b6e6a1e14ed60b3422145b9a4f53d6e18eeb68c535"},"schema_version":"1.0","source":{"id":"2503.04556","kind":"arxiv","version":4}},"canonical_sha256":"0774f5cedc762839fddaf5918ea4770c80450dd0412445e229986a9cabb1df70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0774f5cedc762839fddaf5918ea4770c80450dd0412445e229986a9cabb1df70","first_computed_at":"2026-07-05T11:19:04.203493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:04.203493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"itXOAMEtpE5HxbnJDFbCcGRvkge9davvcSgwiMXxzAQh33cZW0GGINcq1W6S7AI5kPhmiIIOuQUCnQJhSR9hCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:04.203969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04556","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32fa3d52da56bd77b99826e272fa17efc92dfddf773b10986cb3b1f566d50130","sha256:2d432679770523160f419f8c2ce2956156a116058c6d42c258e183f0b8dc83e3"],"state_sha256":"c7b2df3b0f12c979cfc170bc43910f6758fed5cd765e08d447eec2d5ba71a30e"}