{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Z622OMEPRAIACURG7C2WF3Y3GU","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":"fbcd3a7586eef7dd5ced8fb8d31036927b895d0291d7152445d54332a740ea0d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T21:08:51Z","title_canon_sha256":"eebe459fd4c8046f7db53f5dec34e8238768d3d3be4be844f7f64c1b44d183c4"},"schema_version":"1.0","source":{"id":"2310.07018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07018","created_at":"2026-07-05T06:59:39Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07018v1","created_at":"2026-07-05T06:59:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07018","created_at":"2026-07-05T06:59:39Z"},{"alias_kind":"pith_short_12","alias_value":"Z622OMEPRAIA","created_at":"2026-07-05T06:59:39Z"},{"alias_kind":"pith_short_16","alias_value":"Z622OMEPRAIACURG","created_at":"2026-07-05T06:59:39Z"},{"alias_kind":"pith_short_8","alias_value":"Z622OMEP","created_at":"2026-07-05T06:59:39Z"}],"graph_snapshots":[{"event_id":"sha256:a15598b29dd23746a2f822aefff7b0fdbfc16ecb867cfbb8fc2ca87c3c7afe18","target":"graph","created_at":"2026-07-05T06:59:39Z","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/2310.07018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), through their contextualized representations, have been empirically proven to encapsulate syntactic, semantic, word sense, and common-sense knowledge. However, there has been limited exploration of their physical reasoning abilities, specifically concerning the crucial attributes for comprehending everyday objects. To address this gap, we introduce NEWTON, a repository and benchmark for evaluating the physics reasoning skills of LLMs. Further, to enable domain-specific adaptation of this benchmark, we present a pipeline to enable researchers to generate a variant ","authors_text":"Dieter Fox, Jiafei Duan, Siddhartha Srinivasa, Yi Ru Wang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T21:08:51Z","title":"NEWTON: Are Large Language Models Capable of Physical Reasoning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07018","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":"sha256:06d03e466fe29b313a64466f08ef962691119797d9cced9528eadff2df4d2c5e","target":"record","created_at":"2026-07-05T06:59:39Z","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":"fbcd3a7586eef7dd5ced8fb8d31036927b895d0291d7152445d54332a740ea0d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T21:08:51Z","title_canon_sha256":"eebe459fd4c8046f7db53f5dec34e8238768d3d3be4be844f7f64c1b44d183c4"},"schema_version":"1.0","source":{"id":"2310.07018","kind":"arxiv","version":1}},"canonical_sha256":"cfb5a7308f8810015226f8b562ef1b3502b206c44f5248cb3cda64ad36c7f35e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfb5a7308f8810015226f8b562ef1b3502b206c44f5248cb3cda64ad36c7f35e","first_computed_at":"2026-07-05T06:59:39.673028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:39.673028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ocuWzf4vmog7CmqbKyAjPHVOqux90pQjsdd0DEka9RBJiHxplnNUCFA7ALXqBnZo9q1AgB2k2/UCNI7MCNiqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:39.673671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06d03e466fe29b313a64466f08ef962691119797d9cced9528eadff2df4d2c5e","sha256:a15598b29dd23746a2f822aefff7b0fdbfc16ecb867cfbb8fc2ca87c3c7afe18"],"state_sha256":"bc9f94ea6f1840bb0fd0c3106f0d1de679188091d8dfd01c180e2b4a6f959fbb"}