{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4FCW7KVRDLDJNFDSSVESUARVPE","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":"d71a5a27549b2b9d335be6c37dad6cb190c6f581eb9ac3292e8be0dc178d340c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-01T16:43:21Z","title_canon_sha256":"777b14c5e8c65a8a1171ccfc37f98a5b39e57872508c7d275fda05ecec650308"},"schema_version":"1.0","source":{"id":"2405.00622","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00622","created_at":"2026-07-05T08:14:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00622v1","created_at":"2026-07-05T08:14:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00622","created_at":"2026-07-05T08:14:15Z"},{"alias_kind":"pith_short_12","alias_value":"4FCW7KVRDLDJ","created_at":"2026-07-05T08:14:15Z"},{"alias_kind":"pith_short_16","alias_value":"4FCW7KVRDLDJNFDS","created_at":"2026-07-05T08:14:15Z"},{"alias_kind":"pith_short_8","alias_value":"4FCW7KVR","created_at":"2026-07-05T08:14:15Z"}],"graph_snapshots":[{"event_id":"sha256:34a23ad9f87c5a66c2222458c8aa56adda8ae53951cdc6bf23d3fac906ad1201","target":"graph","created_at":"2026-07-05T08:14:15Z","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/2405.00622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Causal reasoning is viewed as crucial for achieving human-level machine intelligence. Recent advances in language models have expanded the horizons of artificial intelligence across various domains, sparking inquiries into their potential for causal reasoning. In this work, we introduce Causal evaluation of Language Models (CaLM), which, to the best of our knowledge, is the first comprehensive benchmark for evaluating the causal reasoning capabilities of language models. First, we propose the CaLM framework, which establishes a foundational taxonomy consisting of four modules: causal target (i","authors_text":"Bo Peng, Chaochao Lu, Meiqi Chen, Mengying Xu, Ruiqi Wang, Rui Zhao, Shengjie Zhao, Sirui Chen, Xingyu Zeng, Yu Qiao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-01T16:43:21Z","title":"Causal Evaluation of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00622","kind":"arxiv","version":1},"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":"sha256:85fe5ff5f2a991b7aca5295fe3bb2baefded270e923c3d67f007f74772b5f334","target":"record","created_at":"2026-07-05T08:14:15Z","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":"d71a5a27549b2b9d335be6c37dad6cb190c6f581eb9ac3292e8be0dc178d340c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-01T16:43:21Z","title_canon_sha256":"777b14c5e8c65a8a1171ccfc37f98a5b39e57872508c7d275fda05ecec650308"},"schema_version":"1.0","source":{"id":"2405.00622","kind":"arxiv","version":1}},"canonical_sha256":"e1456faab11ac696947295492a02357939dd9fb3cee0182d78d748f06f6eb2b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1456faab11ac696947295492a02357939dd9fb3cee0182d78d748f06f6eb2b7","first_computed_at":"2026-07-05T08:14:15.529275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:15.529275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vrCWDKdbibF6ImcNek9Sqx0jp2kQ2mZbodnrAthqLiz5R3jQMkBYI5GbhkNMl1uUQ15segIA0iYcmCwnIJIJAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:15.529784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.00622","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85fe5ff5f2a991b7aca5295fe3bb2baefded270e923c3d67f007f74772b5f334","sha256:34a23ad9f87c5a66c2222458c8aa56adda8ae53951cdc6bf23d3fac906ad1201"],"state_sha256":"410d13b8f9492874426ca986f5036f2c0ec56b3c58b57ccc5882efae0bbd5700"}