{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XOLQAKSC6S2WC4UAPXEJMBTM47","short_pith_number":"pith:XOLQAKSC","schema_version":"1.0","canonical_sha256":"bb97002a42f4b56172807dc896066ce7ebc2601b6e549d822ed0bcee864a681a","source":{"kind":"arxiv","id":"2605.23660","version":1},"attestation_state":"computed","paper":{"title":"Using Large Language Models in Physics Education","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"physics.ed-ph","authors_text":"Aliya Navaz, Alysta Lim, Jonah R. Donaldson, Konstantinos Doran, Mario Campanelli","submitted_at":"2026-05-22T14:11:34Z","abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) has introduced new possibilities and challenges in physics education, necessitating rigorous evaluation of their capabilities as both problem solvers and automated assessors. This paper presents the results of three complementary studies that evaluated frontier models released between mid-2024 and late-2025. Models were assessed on their ability to generate accurate, step-by-step solutions to university-level physics problems in Classical Mechanics, Electromagnetism, and Quantum Mechanics, and subsequently on their reliability in grading st"},"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":"2605.23660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.ed-ph","submitted_at":"2026-05-22T14:11:34Z","cross_cats_sorted":[],"title_canon_sha256":"5ffb40abe10ba59fb486d9befa1e860abc5b772cfdbaf4f8f85210b5d31d3b6d","abstract_canon_sha256":"ac3d4e31f6f8b7b1d195ae718587de4c3c3b6b371d3ace71aef79693a9ec0e09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:24.635589Z","signature_b64":"yShAhVDHKcvr0SIlogMkrSFYW9RRbHqDQibXotyhOXIOjWV/tjfEYmrWBx8FqBnUg4Q2mdQbkxuVbbmGn0xmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb97002a42f4b56172807dc896066ce7ebc2601b6e549d822ed0bcee864a681a","last_reissued_at":"2026-05-25T02:02:24.634772Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:24.634772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Large Language Models in Physics Education","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"physics.ed-ph","authors_text":"Aliya Navaz, Alysta Lim, Jonah R. Donaldson, Konstantinos Doran, Mario Campanelli","submitted_at":"2026-05-22T14:11:34Z","abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) has introduced new possibilities and challenges in physics education, necessitating rigorous evaluation of their capabilities as both problem solvers and automated assessors. This paper presents the results of three complementary studies that evaluated frontier models released between mid-2024 and late-2025. Models were assessed on their ability to generate accurate, step-by-step solutions to university-level physics problems in Classical Mechanics, Electromagnetism, and Quantum Mechanics, and subsequently on their reliability in grading st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23660","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/2605.23660/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":"2605.23660","created_at":"2026-05-25T02:02:24.634901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23660v1","created_at":"2026-05-25T02:02:24.634901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23660","created_at":"2026-05-25T02:02:24.634901+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOLQAKSC6S2W","created_at":"2026-05-25T02:02:24.634901+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOLQAKSC6S2WC4UA","created_at":"2026-05-25T02:02:24.634901+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOLQAKSC","created_at":"2026-05-25T02:02:24.634901+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/XOLQAKSC6S2WC4UAPXEJMBTM47","json":"https://pith.science/pith/XOLQAKSC6S2WC4UAPXEJMBTM47.json","graph_json":"https://pith.science/api/pith-number/XOLQAKSC6S2WC4UAPXEJMBTM47/graph.json","events_json":"https://pith.science/api/pith-number/XOLQAKSC6S2WC4UAPXEJMBTM47/events.json","paper":"https://pith.science/paper/XOLQAKSC"},"agent_actions":{"view_html":"https://pith.science/pith/XOLQAKSC6S2WC4UAPXEJMBTM47","download_json":"https://pith.science/pith/XOLQAKSC6S2WC4UAPXEJMBTM47.json","view_paper":"https://pith.science/paper/XOLQAKSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23660&json=true","fetch_graph":"https://pith.science/api/pith-number/XOLQAKSC6S2WC4UAPXEJMBTM47/graph.json","fetch_events":"https://pith.science/api/pith-number/XOLQAKSC6S2WC4UAPXEJMBTM47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOLQAKSC6S2WC4UAPXEJMBTM47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOLQAKSC6S2WC4UAPXEJMBTM47/action/storage_attestation","attest_author":"https://pith.science/pith/XOLQAKSC6S2WC4UAPXEJMBTM47/action/author_attestation","sign_citation":"https://pith.science/pith/XOLQAKSC6S2WC4UAPXEJMBTM47/action/citation_signature","submit_replication":"https://pith.science/pith/XOLQAKSC6S2WC4UAPXEJMBTM47/action/replication_record"}},"created_at":"2026-05-25T02:02:24.634901+00:00","updated_at":"2026-05-25T02:02:24.634901+00:00"}