{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:T3EZ5B7VO25GOQSSTCIGVZVRFE","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":"f44dea0929b0e9f1d5468dff2ac5d017ece6a4308a4ea8bf23cc1b2716dfbfa0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T06:54:04Z","title_canon_sha256":"12789ad63bd6faa193c34297e06608548d1165b5179529a2e51704463ace03e0"},"schema_version":"1.0","source":{"id":"2212.10029","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10029","created_at":"2026-07-05T06:18:51Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10029v3","created_at":"2026-07-05T06:18:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10029","created_at":"2026-07-05T06:18:51Z"},{"alias_kind":"pith_short_12","alias_value":"T3EZ5B7VO25G","created_at":"2026-07-05T06:18:51Z"},{"alias_kind":"pith_short_16","alias_value":"T3EZ5B7VO25GOQSS","created_at":"2026-07-05T06:18:51Z"},{"alias_kind":"pith_short_8","alias_value":"T3EZ5B7V","created_at":"2026-07-05T06:18:51Z"}],"graph_snapshots":[{"event_id":"sha256:14f2f1b03632b4a3bb6afec49a2f17baee725e81c216cf4a35ae543d1810d629","target":"graph","created_at":"2026-07-05T06:18:51Z","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/2212.10029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When people think of everyday things like an egg, they typically have a mental image associated with it. This allows them to correctly judge, for example, that \"the yolk surrounds the shell\" is a false statement. Do language models similarly have a coherent picture of such everyday things? To investigate this, we propose a benchmark dataset consisting of 100 everyday things, their parts, and the relationships between these parts, expressed as 11,720 \"X relation Y?\" true/false questions. Using these questions as probes, we observe that state-of-the-art pre-trained language models (LMs) like GPT","authors_text":"Bhavana Dalvi Mishra, Peter Clark, Yuling Gu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T06:54:04Z","title":"Do language models have coherent mental models of everyday things?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10029","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":"sha256:0e4eca2f9c268558db01f79d5de2502bc1fecb72bcefaa736c1a7c313d71575d","target":"record","created_at":"2026-07-05T06:18:51Z","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":"f44dea0929b0e9f1d5468dff2ac5d017ece6a4308a4ea8bf23cc1b2716dfbfa0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T06:54:04Z","title_canon_sha256":"12789ad63bd6faa193c34297e06608548d1165b5179529a2e51704463ace03e0"},"schema_version":"1.0","source":{"id":"2212.10029","kind":"arxiv","version":3}},"canonical_sha256":"9ec99e87f576ba67425298906ae6b1291779a06bcb7ca3d3ab664e6ac27fe4d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ec99e87f576ba67425298906ae6b1291779a06bcb7ca3d3ab664e6ac27fe4d5","first_computed_at":"2026-07-05T06:18:51.983306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:51.983306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XaDoRFIdi8EqizDjDs1iD6dKUCV93mqf+mCGYT6xv7yk4zaAEBNAVeI+HgWbDFV3nvjuiimbqY2vRT0jVbEJAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:51.983753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10029","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e4eca2f9c268558db01f79d5de2502bc1fecb72bcefaa736c1a7c313d71575d","sha256:14f2f1b03632b4a3bb6afec49a2f17baee725e81c216cf4a35ae543d1810d629"],"state_sha256":"9c7d1935c7bf81fd10bff50fb0626c8913ee00257480e279bdee071b8371da6c"}