{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q32ISLAPEY7CR6MZSTWWJBY5AO","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":"70d1f877ccd7f190c6c633fd1eef420dd9df99fd2340f79d2625531155151408","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-22T11:46:04Z","title_canon_sha256":"5a6cc2ab3dbbc963f2c49e924582879764368e85f598ad58afa025f60c114b8d"},"schema_version":"1.0","source":{"id":"2406.15823","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15823","created_at":"2026-07-05T09:58:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15823v3","created_at":"2026-07-05T09:58:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15823","created_at":"2026-07-05T09:58:21Z"},{"alias_kind":"pith_short_12","alias_value":"Q32ISLAPEY7C","created_at":"2026-07-05T09:58:21Z"},{"alias_kind":"pith_short_16","alias_value":"Q32ISLAPEY7CR6MZ","created_at":"2026-07-05T09:58:21Z"},{"alias_kind":"pith_short_8","alias_value":"Q32ISLAP","created_at":"2026-07-05T09:58:21Z"}],"graph_snapshots":[{"event_id":"sha256:b3890eb4c13951168eaa1ea01076cca475512c7cfc9534daf8ee149d011ae0f9","target":"graph","created_at":"2026-07-05T09:58:21Z","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/2406.15823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the abilities of LLMs to reason about natural language plans, such as instructional text and recipes, is critical to reliably using them in decision-making systems. A fundamental aspect of plans is the temporal order in which their steps needs to be executed, which reflects the underlying causal dependencies between them. We introduce CaT-Bench, a benchmark of Step Order Prediction questions, which test whether a step must necessarily occur before or after another in cooking recipe plans. We use this to evaluate how well frontier LLMs understand causal and temporal dependencies. ","authors_text":"Nathanael Chambers, Niranjan Balasubramanian, Raymond Mooney, Vanya Cohen, Yash Kumar Lal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-22T11:46:04Z","title":"CaT-BENCH: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Plans"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15823","kind":"arxiv","version":3},"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:aa080b8430d067dd52e9bc1d6389d6ede8578a9ef18ce998fcd5d1b708298bbd","target":"record","created_at":"2026-07-05T09:58:21Z","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":"70d1f877ccd7f190c6c633fd1eef420dd9df99fd2340f79d2625531155151408","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-22T11:46:04Z","title_canon_sha256":"5a6cc2ab3dbbc963f2c49e924582879764368e85f598ad58afa025f60c114b8d"},"schema_version":"1.0","source":{"id":"2406.15823","kind":"arxiv","version":3}},"canonical_sha256":"86f4892c0f263e28f99994ed64871d039fda883f8c3be4aa56ed564986356eec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86f4892c0f263e28f99994ed64871d039fda883f8c3be4aa56ed564986356eec","first_computed_at":"2026-07-05T09:58:21.841490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:21.841490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aes2Z1AXC1+1lgqkMy1/ihvqvL4FTrSNtCFpddxpdFn9SLsjcF4GhJBQOz14Je/uRu1DlnKCAhJEU2KGP8CdDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:21.842011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15823","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa080b8430d067dd52e9bc1d6389d6ede8578a9ef18ce998fcd5d1b708298bbd","sha256:b3890eb4c13951168eaa1ea01076cca475512c7cfc9534daf8ee149d011ae0f9"],"state_sha256":"94edb82d1e9826d88924974b39f2281566c6cdc9ce3ecccf7408f9573714641b"}