{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VK4PM4LBGCUJFZOBDXVMSPAT6U","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":"49543badac9ededac0454c92a8354315500b7e886eaaea2757f58a90447f3932","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T20:34:32Z","title_canon_sha256":"26e4136e86dcf935745cdfe7a4e1fe49c7ac22fa52e89435e422a0488297e52b"},"schema_version":"1.0","source":{"id":"2412.17970","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17970","created_at":"2026-07-05T09:53:31Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17970v1","created_at":"2026-07-05T09:53:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17970","created_at":"2026-07-05T09:53:31Z"},{"alias_kind":"pith_short_12","alias_value":"VK4PM4LBGCUJ","created_at":"2026-07-05T09:53:31Z"},{"alias_kind":"pith_short_16","alias_value":"VK4PM4LBGCUJFZOB","created_at":"2026-07-05T09:53:31Z"},{"alias_kind":"pith_short_8","alias_value":"VK4PM4LB","created_at":"2026-07-05T09:53:31Z"}],"graph_snapshots":[{"event_id":"sha256:8d618ba20c4e88a3845a1a709bae70fce82f8a9bb2ec8447a1c97d08863cfb53","target":"graph","created_at":"2026-07-05T09:53:31Z","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/2412.17970/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Causal reasoning capabilities are essential for large language models (LLMs) in a wide range of applications, such as education and healthcare. But there is still a lack of benchmarks for a better understanding of such capabilities. Current LLM benchmarks are mainly based on conversational tasks, academic math tests, and coding tests. Such benchmarks evaluate LLMs in well-regularized settings, but they are limited in assessing the skills and abilities to solve real-world problems. In this work, we provide a benchmark, named by CARL-GT, which evaluates CAusal Reasoning capabilities of large Lan","authors_text":"Cheng Zhang, Gustav Eje Henter, Hedvig Kjellstr\\\"om, Ruibo Tu","cross_cats":["cs.LG","stat.ME"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T20:34:32Z","title":"CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17970","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:dc80c16813ed142ee5470cddc441a5ba655dae1c7e11bc8d64a9efdab916aa04","target":"record","created_at":"2026-07-05T09:53:31Z","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":"49543badac9ededac0454c92a8354315500b7e886eaaea2757f58a90447f3932","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T20:34:32Z","title_canon_sha256":"26e4136e86dcf935745cdfe7a4e1fe49c7ac22fa52e89435e422a0488297e52b"},"schema_version":"1.0","source":{"id":"2412.17970","kind":"arxiv","version":1}},"canonical_sha256":"aab8f6716130a892e5c11deac93c13f52329a5b110e3659ed4ab19ffacc60426","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aab8f6716130a892e5c11deac93c13f52329a5b110e3659ed4ab19ffacc60426","first_computed_at":"2026-07-05T09:53:31.657084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:31.657084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+wKyuqYNdVJ8QYgasZjJ1es6ZZEE+fJEXUJDoGKcoN8i/dIL28kC9W+YNalmAV0HKAJHpq9a75oboD1gAVKhCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:31.657546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17970","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc80c16813ed142ee5470cddc441a5ba655dae1c7e11bc8d64a9efdab916aa04","sha256:8d618ba20c4e88a3845a1a709bae70fce82f8a9bb2ec8447a1c97d08863cfb53"],"state_sha256":"12570e8e343f97f3e881dfbd8a04976d98ec95cef30e36b26b1254ca747cf428"}