{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FJZ27UICRMJRJ3WZJ6QYFBPXFM","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":"c130a0357072acabdbb75a6a72d274d83ee5c2d271aa8e4858adf889fb28aefa","cross_cats_sorted":["cs.AI","cs.LG","cs.SC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-11T18:14:33Z","title_canon_sha256":"17b3a185651b088645aa67f2c3c56bdbc99ee0895bd6c9aa7babfb82edab21c0"},"schema_version":"1.0","source":{"id":"2205.05718","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05718","created_at":"2026-07-05T04:22:29Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05718v1","created_at":"2026-07-05T04:22:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05718","created_at":"2026-07-05T04:22:29Z"},{"alias_kind":"pith_short_12","alias_value":"FJZ27UICRMJR","created_at":"2026-07-05T04:22:29Z"},{"alias_kind":"pith_short_16","alias_value":"FJZ27UICRMJRJ3WZ","created_at":"2026-07-05T04:22:29Z"},{"alias_kind":"pith_short_8","alias_value":"FJZ27UIC","created_at":"2026-07-05T04:22:29Z"}],"graph_snapshots":[{"event_id":"sha256:06d86a333914f6ccdf5cc4ddd5f6e5d0f6e07f6fab9d7b877cfd7c193e64c4cb","target":"graph","created_at":"2026-07-05T04:22:29Z","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/2205.05718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human language offers a powerful window into our thoughts -- we tell stories, give explanations, and express our beliefs and goals through words. Abundant evidence also suggests that language plays a developmental role in structuring our learning. Here, we ask: how much of human-like thinking can be captured by learning statistical patterns in language alone? We first contribute a new challenge benchmark for comparing humans and distributional large language models (LLMs). Our benchmark contains two problem-solving domains (planning and explanation generation) and is designed to require genera","authors_text":"Catherine Wong, Jiahai Feng, Joshua B. Tenenbaum, Katherine M. Collins, Megan Wei","cross_cats":["cs.AI","cs.LG","cs.SC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-11T18:14:33Z","title":"Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05718","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:e3bc3c3037943bfd4ce9a7d82d67b5c13ac95c1d9284a8bea3fa952743c50498","target":"record","created_at":"2026-07-05T04:22:29Z","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":"c130a0357072acabdbb75a6a72d274d83ee5c2d271aa8e4858adf889fb28aefa","cross_cats_sorted":["cs.AI","cs.LG","cs.SC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-11T18:14:33Z","title_canon_sha256":"17b3a185651b088645aa67f2c3c56bdbc99ee0895bd6c9aa7babfb82edab21c0"},"schema_version":"1.0","source":{"id":"2205.05718","kind":"arxiv","version":1}},"canonical_sha256":"2a73afd1028b1314eed94fa18285f72b186ba335c0d9dbf85b35f3a4ad55db42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a73afd1028b1314eed94fa18285f72b186ba335c0d9dbf85b35f3a4ad55db42","first_computed_at":"2026-07-05T04:22:29.547720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:29.547720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8rlk8bzIolt/E24F5RV9PIdly671yiGlfOOFc0X2G1jScRTKwGFYaitbRFzbCk3kc/Fvr8kVN0K66xI7bnuDDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:29.548209Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.05718","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3bc3c3037943bfd4ce9a7d82d67b5c13ac95c1d9284a8bea3fa952743c50498","sha256:06d86a333914f6ccdf5cc4ddd5f6e5d0f6e07f6fab9d7b877cfd7c193e64c4cb"],"state_sha256":"7714a759e3580c07bc17da8b9bf99799c26ac86bd4074c0876cda05c27793799"}