{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K2FBRLGI6LAW2FDWNEYZY7L3LB","short_pith_number":"pith:K2FBRLGI","schema_version":"1.0","canonical_sha256":"568a18acc8f2c16d147669319c7d7b58459509f2a2133a35386922f8833de296","source":{"kind":"arxiv","id":"2607.14303","version":1},"attestation_state":"computed","paper":{"title":"Assessing AI in Introductory Physics Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"physics.ed-ph","authors_text":"Amir Bralin, N. Sanjay Rebello","submitted_at":"2026-07-15T19:08:56Z","abstract_excerpt":"Reasoning or inference-scaling models are the new generation of Large Language Models (LLMs) capable of complex problem solving. To investigate their problem-solving capability in physics, we evaluated model o4-mini by OpenAI on solving traditional, end-of-chapter problems from Halliday and Resnick's \"Fundamentals of Physics,\" spanning core topics in the undergraduate physics curriculum. Performance was analyzed across modality and problem difficulty. The model solved the problems with overall accuracy of about 90%, but performance depended strongly on representation: accuracy was much higher "},"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":"2607.14303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.ed-ph","submitted_at":"2026-07-15T19:08:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"00a392ae5faa871f870bf4104fc793e0598da4e7ab60c59553279db3d7e0f224","abstract_canon_sha256":"73ad5876067b70667f0c4b97dca6660fbdad22a5f122b70b00c8815736517d82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:04.285036Z","signature_b64":"OEMDgunKv8AgmPs2yJC1DCJ+KSwF9VnyW9COB6vuGnxgmSAWxSH5EFN98kL8O1cFBnm2AIMaxq8j/ZL0yDaVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"568a18acc8f2c16d147669319c7d7b58459509f2a2133a35386922f8833de296","last_reissued_at":"2026-07-17T00:21:04.284160Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:04.284160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing AI in Introductory Physics Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"physics.ed-ph","authors_text":"Amir Bralin, N. Sanjay Rebello","submitted_at":"2026-07-15T19:08:56Z","abstract_excerpt":"Reasoning or inference-scaling models are the new generation of Large Language Models (LLMs) capable of complex problem solving. To investigate their problem-solving capability in physics, we evaluated model o4-mini by OpenAI on solving traditional, end-of-chapter problems from Halliday and Resnick's \"Fundamentals of Physics,\" spanning core topics in the undergraduate physics curriculum. Performance was analyzed across modality and problem difficulty. The model solved the problems with overall accuracy of about 90%, but performance depended strongly on representation: accuracy was much higher "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14303","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/2607.14303/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":"2607.14303","created_at":"2026-07-17T00:21:04.284626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14303v1","created_at":"2026-07-17T00:21:04.284626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14303","created_at":"2026-07-17T00:21:04.284626+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2FBRLGI6LAW","created_at":"2026-07-17T00:21:04.284626+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2FBRLGI6LAW2FDW","created_at":"2026-07-17T00:21:04.284626+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2FBRLGI","created_at":"2026-07-17T00:21:04.284626+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/K2FBRLGI6LAW2FDWNEYZY7L3LB","json":"https://pith.science/pith/K2FBRLGI6LAW2FDWNEYZY7L3LB.json","graph_json":"https://pith.science/api/pith-number/K2FBRLGI6LAW2FDWNEYZY7L3LB/graph.json","events_json":"https://pith.science/api/pith-number/K2FBRLGI6LAW2FDWNEYZY7L3LB/events.json","paper":"https://pith.science/paper/K2FBRLGI"},"agent_actions":{"view_html":"https://pith.science/pith/K2FBRLGI6LAW2FDWNEYZY7L3LB","download_json":"https://pith.science/pith/K2FBRLGI6LAW2FDWNEYZY7L3LB.json","view_paper":"https://pith.science/paper/K2FBRLGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14303&json=true","fetch_graph":"https://pith.science/api/pith-number/K2FBRLGI6LAW2FDWNEYZY7L3LB/graph.json","fetch_events":"https://pith.science/api/pith-number/K2FBRLGI6LAW2FDWNEYZY7L3LB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2FBRLGI6LAW2FDWNEYZY7L3LB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2FBRLGI6LAW2FDWNEYZY7L3LB/action/storage_attestation","attest_author":"https://pith.science/pith/K2FBRLGI6LAW2FDWNEYZY7L3LB/action/author_attestation","sign_citation":"https://pith.science/pith/K2FBRLGI6LAW2FDWNEYZY7L3LB/action/citation_signature","submit_replication":"https://pith.science/pith/K2FBRLGI6LAW2FDWNEYZY7L3LB/action/replication_record"}},"created_at":"2026-07-17T00:21:04.284626+00:00","updated_at":"2026-07-17T00:21:04.284626+00:00"}