{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:54BFGS3IZPTIMD55DGRSAYNAOY","short_pith_number":"pith:54BFGS3I","schema_version":"1.0","canonical_sha256":"ef02534b68cbe6860fbd19a32061a07620033026f67f166113fece2a1e79065e","source":{"kind":"arxiv","id":"2508.20941","version":1},"attestation_state":"computed","paper":{"title":"AI Reasoning Models for Problem Solving in Physics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.ed-ph","authors_text":"Amir Bralin, N. Sanjay Rebello","submitted_at":"2025-08-28T16:02:37Z","abstract_excerpt":"Reasoning models are the new generation of Large Language Models (LLMs) capable of complex problem solving. Their reliability in solving introductory physics problems was tested by evaluating a sample of n = 5 solutions generated by one such model -- OpenAI's o3-mini -- per each problem from 20 chapters of a standard undergraduate textbook. In total, N = 408 problems were given to the model and N x n = 2,040 generated solutions examined. The model successfully solved 94% of the problems posed, excelling at the beginning topics in mechanics but struggling with the later ones such as waves and t"},"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":"2508.20941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.ed-ph","submitted_at":"2025-08-28T16:02:37Z","cross_cats_sorted":[],"title_canon_sha256":"fd31897d0536eb5e887084dd546f20ae3bb1de9774c6bb32f502867cccc6c13d","abstract_canon_sha256":"a407c231f9322581ecf36063094b350516afd433d14bd2540b07262633ac0f02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:13.800220Z","signature_b64":"fVcmF/7yH0ErXqpnlL4/HAW+FIjurE8L+oEELduz8B6BNN4OHTpXWIOREtpq31aS9ZmEFNzG4KcHAMlsdaVjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef02534b68cbe6860fbd19a32061a07620033026f67f166113fece2a1e79065e","last_reissued_at":"2026-07-05T12:01:13.799594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:13.799594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Reasoning Models for Problem Solving in Physics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.ed-ph","authors_text":"Amir Bralin, N. Sanjay Rebello","submitted_at":"2025-08-28T16:02:37Z","abstract_excerpt":"Reasoning models are the new generation of Large Language Models (LLMs) capable of complex problem solving. Their reliability in solving introductory physics problems was tested by evaluating a sample of n = 5 solutions generated by one such model -- OpenAI's o3-mini -- per each problem from 20 chapters of a standard undergraduate textbook. In total, N = 408 problems were given to the model and N x n = 2,040 generated solutions examined. The model successfully solved 94% of the problems posed, excelling at the beginning topics in mechanics but struggling with the later ones such as waves and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20941","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/2508.20941/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":"2508.20941","created_at":"2026-07-05T12:01:13.799670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20941v1","created_at":"2026-07-05T12:01:13.799670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20941","created_at":"2026-07-05T12:01:13.799670+00:00"},{"alias_kind":"pith_short_12","alias_value":"54BFGS3IZPTI","created_at":"2026-07-05T12:01:13.799670+00:00"},{"alias_kind":"pith_short_16","alias_value":"54BFGS3IZPTIMD55","created_at":"2026-07-05T12:01:13.799670+00:00"},{"alias_kind":"pith_short_8","alias_value":"54BFGS3I","created_at":"2026-07-05T12:01:13.799670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54BFGS3IZPTIMD55DGRSAYNAOY","json":"https://pith.science/pith/54BFGS3IZPTIMD55DGRSAYNAOY.json","graph_json":"https://pith.science/api/pith-number/54BFGS3IZPTIMD55DGRSAYNAOY/graph.json","events_json":"https://pith.science/api/pith-number/54BFGS3IZPTIMD55DGRSAYNAOY/events.json","paper":"https://pith.science/paper/54BFGS3I"},"agent_actions":{"view_html":"https://pith.science/pith/54BFGS3IZPTIMD55DGRSAYNAOY","download_json":"https://pith.science/pith/54BFGS3IZPTIMD55DGRSAYNAOY.json","view_paper":"https://pith.science/paper/54BFGS3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20941&json=true","fetch_graph":"https://pith.science/api/pith-number/54BFGS3IZPTIMD55DGRSAYNAOY/graph.json","fetch_events":"https://pith.science/api/pith-number/54BFGS3IZPTIMD55DGRSAYNAOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54BFGS3IZPTIMD55DGRSAYNAOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54BFGS3IZPTIMD55DGRSAYNAOY/action/storage_attestation","attest_author":"https://pith.science/pith/54BFGS3IZPTIMD55DGRSAYNAOY/action/author_attestation","sign_citation":"https://pith.science/pith/54BFGS3IZPTIMD55DGRSAYNAOY/action/citation_signature","submit_replication":"https://pith.science/pith/54BFGS3IZPTIMD55DGRSAYNAOY/action/replication_record"}},"created_at":"2026-07-05T12:01:13.799670+00:00","updated_at":"2026-07-05T12:01:13.799670+00:00"}