{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Z622OMEPRAIACURG7C2WF3Y3GU","short_pith_number":"pith:Z622OMEP","schema_version":"1.0","canonical_sha256":"cfb5a7308f8810015226f8b562ef1b3502b206c44f5248cb3cda64ad36c7f35e","source":{"kind":"arxiv","id":"2310.07018","version":1},"attestation_state":"computed","paper":{"title":"NEWTON: Are Large Language Models Capable of Physical Reasoning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CL","authors_text":"Dieter Fox, Jiafei Duan, Siddhartha Srinivasa, Yi Ru Wang","submitted_at":"2023-10-10T21:08:51Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.07018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-10T21:08:51Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"eebe459fd4c8046f7db53f5dec34e8238768d3d3be4be844f7f64c1b44d183c4","abstract_canon_sha256":"fbcd3a7586eef7dd5ced8fb8d31036927b895d0291d7152445d54332a740ea0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:39.673671Z","signature_b64":"ocuWzf4vmog7CmqbKyAjPHVOqux90pQjsdd0DEka9RBJiHxplnNUCFA7ALXqBnZo9q1AgB2k2/UCNI7MCNiqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfb5a7308f8810015226f8b562ef1b3502b206c44f5248cb3cda64ad36c7f35e","last_reissued_at":"2026-07-05T06:59:39.673028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:39.673028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NEWTON: Are Large Language Models Capable of Physical Reasoning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CL","authors_text":"Dieter Fox, Jiafei Duan, Siddhartha Srinivasa, Yi Ru Wang","submitted_at":"2023-10-10T21:08:51Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07018","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.07018/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.07018","created_at":"2026-07-05T06:59:39.673126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07018v1","created_at":"2026-07-05T06:59:39.673126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07018","created_at":"2026-07-05T06:59:39.673126+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z622OMEPRAIA","created_at":"2026-07-05T06:59:39.673126+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z622OMEPRAIACURG","created_at":"2026-07-05T06:59:39.673126+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z622OMEP","created_at":"2026-07-05T06:59:39.673126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.16120","citing_title":"LLM-Powered AI Agent Systems and Their Applications in Industry","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z622OMEPRAIACURG7C2WF3Y3GU","json":"https://pith.science/pith/Z622OMEPRAIACURG7C2WF3Y3GU.json","graph_json":"https://pith.science/api/pith-number/Z622OMEPRAIACURG7C2WF3Y3GU/graph.json","events_json":"https://pith.science/api/pith-number/Z622OMEPRAIACURG7C2WF3Y3GU/events.json","paper":"https://pith.science/paper/Z622OMEP"},"agent_actions":{"view_html":"https://pith.science/pith/Z622OMEPRAIACURG7C2WF3Y3GU","download_json":"https://pith.science/pith/Z622OMEPRAIACURG7C2WF3Y3GU.json","view_paper":"https://pith.science/paper/Z622OMEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07018&json=true","fetch_graph":"https://pith.science/api/pith-number/Z622OMEPRAIACURG7C2WF3Y3GU/graph.json","fetch_events":"https://pith.science/api/pith-number/Z622OMEPRAIACURG7C2WF3Y3GU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z622OMEPRAIACURG7C2WF3Y3GU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z622OMEPRAIACURG7C2WF3Y3GU/action/storage_attestation","attest_author":"https://pith.science/pith/Z622OMEPRAIACURG7C2WF3Y3GU/action/author_attestation","sign_citation":"https://pith.science/pith/Z622OMEPRAIACURG7C2WF3Y3GU/action/citation_signature","submit_replication":"https://pith.science/pith/Z622OMEPRAIACURG7C2WF3Y3GU/action/replication_record"}},"created_at":"2026-07-05T06:59:39.673126+00:00","updated_at":"2026-07-05T06:59:39.673126+00:00"}