{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NCBN2BYMCNJBNG3YN4X45B5GFF","short_pith_number":"pith:NCBN2BYM","schema_version":"1.0","canonical_sha256":"6882dd070c1352169b786f2fce87a62956596aabc720aab1a39e7a26a142fb5a","source":{"kind":"arxiv","id":"2309.08182","version":2},"attestation_state":"computed","paper":{"title":"Using Large Language Model to Solve and Explain Physics Word Problems Approaching Human Level","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jingzhe Ding, Xinyuan Wei, Yan Cen","submitted_at":"2023-09-15T06:13:06Z","abstract_excerpt":"Our work demonstrates that large language model (LLM) pre-trained on texts can not only solve pure math word problems, but also physics word problems, whose solution requires calculation and inference based on prior physical knowledge. We collect and annotate the first physics word problem dataset-PhysQA, which contains over 1000 junior high school physics word problems (covering Kinematics, Mass&Density, Mechanics, Heat, Electricity). Then we use OpenAI' s GPT3.5 to generate the answer of these problems and found that GPT3.5 could automatically solve 49.3% of the problems through zero-shot le"},"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":"2309.08182","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-15T06:13:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"afa32b6d856b62ef26f5629d5f405d773f4816f2c585ad4ebc6e9a304dd1e791","abstract_canon_sha256":"cbe14033b59be34b81bc471d5531b6d8e7dea93b8c815370cb3bf6dae59929fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:26.342249Z","signature_b64":"T05xpeJwXlMgCcSiAhWDstxIFoVrStd6kyyRj7NSIbNzL61COw8FQ01F60z2KJD+4UYHPJhz6V//zh21U75xBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6882dd070c1352169b786f2fce87a62956596aabc720aab1a39e7a26a142fb5a","last_reissued_at":"2026-07-05T06:52:26.341782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:26.341782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Large Language Model to Solve and Explain Physics Word Problems Approaching Human Level","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jingzhe Ding, Xinyuan Wei, Yan Cen","submitted_at":"2023-09-15T06:13:06Z","abstract_excerpt":"Our work demonstrates that large language model (LLM) pre-trained on texts can not only solve pure math word problems, but also physics word problems, whose solution requires calculation and inference based on prior physical knowledge. We collect and annotate the first physics word problem dataset-PhysQA, which contains over 1000 junior high school physics word problems (covering Kinematics, Mass&Density, Mechanics, Heat, Electricity). Then we use OpenAI' s GPT3.5 to generate the answer of these problems and found that GPT3.5 could automatically solve 49.3% of the problems through zero-shot le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08182","kind":"arxiv","version":2},"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/2309.08182/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":"2309.08182","created_at":"2026-07-05T06:52:26.341838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08182v2","created_at":"2026-07-05T06:52:26.341838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08182","created_at":"2026-07-05T06:52:26.341838+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCBN2BYMCNJB","created_at":"2026-07-05T06:52:26.341838+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCBN2BYMCNJBNG3Y","created_at":"2026-07-05T06:52:26.341838+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCBN2BYM","created_at":"2026-07-05T06:52:26.341838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10920","citing_title":"Use of a genetic algorithm to find solutions to introductory physics problems","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCBN2BYMCNJBNG3YN4X45B5GFF","json":"https://pith.science/pith/NCBN2BYMCNJBNG3YN4X45B5GFF.json","graph_json":"https://pith.science/api/pith-number/NCBN2BYMCNJBNG3YN4X45B5GFF/graph.json","events_json":"https://pith.science/api/pith-number/NCBN2BYMCNJBNG3YN4X45B5GFF/events.json","paper":"https://pith.science/paper/NCBN2BYM"},"agent_actions":{"view_html":"https://pith.science/pith/NCBN2BYMCNJBNG3YN4X45B5GFF","download_json":"https://pith.science/pith/NCBN2BYMCNJBNG3YN4X45B5GFF.json","view_paper":"https://pith.science/paper/NCBN2BYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08182&json=true","fetch_graph":"https://pith.science/api/pith-number/NCBN2BYMCNJBNG3YN4X45B5GFF/graph.json","fetch_events":"https://pith.science/api/pith-number/NCBN2BYMCNJBNG3YN4X45B5GFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCBN2BYMCNJBNG3YN4X45B5GFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCBN2BYMCNJBNG3YN4X45B5GFF/action/storage_attestation","attest_author":"https://pith.science/pith/NCBN2BYMCNJBNG3YN4X45B5GFF/action/author_attestation","sign_citation":"https://pith.science/pith/NCBN2BYMCNJBNG3YN4X45B5GFF/action/citation_signature","submit_replication":"https://pith.science/pith/NCBN2BYMCNJBNG3YN4X45B5GFF/action/replication_record"}},"created_at":"2026-07-05T06:52:26.341838+00:00","updated_at":"2026-07-05T06:52:26.341838+00:00"}