{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FCRSSLX2BWMANINBOKGINWEQOR","short_pith_number":"pith:FCRSSLX2","schema_version":"1.0","canonical_sha256":"28a3292efa0d9806a1a1728c86d8907466015eb74573f06e5c02d077da9cea4e","source":{"kind":"arxiv","id":"2607.00276","version":1},"attestation_state":"computed","paper":{"title":"Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Dong Zhang","submitted_at":"2026-06-30T23:52:15Z","abstract_excerpt":"Current large-language-model (LLM) physics benchmarks are usually scored by answer accuracy, which cannot distinguish genuine reasoning from recall of familiar problem patterns and reveals little about where a model's reasoning breaks down. We introduce an auditable four-stage diagnostic that evaluates whether an LLM can reason inside an unfamiliar physics framework through induction, formulation, prediction, and review. The diagnostic combines locked pre-registrations, fresh sessions between stages, dual-LLM judging, and a human-audit pathway, and we apply it to three parallel physics worlds:"},"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":"2607.00276","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T23:52:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0b69646f84e49c72ddb87f088346a5c1c87003ad83940314bf4672fbf3e72806","abstract_canon_sha256":"a6a7b221015878d2f284474802b5328eeadcee1deb6f333ab912961b92ed47dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:42.483216Z","signature_b64":"oRJoFkHmVxwTGsd+mb+GOF3ZDFB/6Ks0bF77E12GJdfiZPLe+uVGKM2ZHiNcVTxrLW78SMYur+yv61YIMeoyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28a3292efa0d9806a1a1728c86d8907466015eb74573f06e5c02d077da9cea4e","last_reissued_at":"2026-07-02T00:18:42.482479Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:42.482479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Dong Zhang","submitted_at":"2026-06-30T23:52:15Z","abstract_excerpt":"Current large-language-model (LLM) physics benchmarks are usually scored by answer accuracy, which cannot distinguish genuine reasoning from recall of familiar problem patterns and reveals little about where a model's reasoning breaks down. We introduce an auditable four-stage diagnostic that evaluates whether an LLM can reason inside an unfamiliar physics framework through induction, formulation, prediction, and review. The diagnostic combines locked pre-registrations, fresh sessions between stages, dual-LLM judging, and a human-audit pathway, and we apply it to three parallel physics worlds:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00276","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/2607.00276/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":"2607.00276","created_at":"2026-07-02T00:18:42.482586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00276v1","created_at":"2026-07-02T00:18:42.482586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00276","created_at":"2026-07-02T00:18:42.482586+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCRSSLX2BWMA","created_at":"2026-07-02T00:18:42.482586+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCRSSLX2BWMANINB","created_at":"2026-07-02T00:18:42.482586+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCRSSLX2","created_at":"2026-07-02T00:18:42.482586+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/FCRSSLX2BWMANINBOKGINWEQOR","json":"https://pith.science/pith/FCRSSLX2BWMANINBOKGINWEQOR.json","graph_json":"https://pith.science/api/pith-number/FCRSSLX2BWMANINBOKGINWEQOR/graph.json","events_json":"https://pith.science/api/pith-number/FCRSSLX2BWMANINBOKGINWEQOR/events.json","paper":"https://pith.science/paper/FCRSSLX2"},"agent_actions":{"view_html":"https://pith.science/pith/FCRSSLX2BWMANINBOKGINWEQOR","download_json":"https://pith.science/pith/FCRSSLX2BWMANINBOKGINWEQOR.json","view_paper":"https://pith.science/paper/FCRSSLX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00276&json=true","fetch_graph":"https://pith.science/api/pith-number/FCRSSLX2BWMANINBOKGINWEQOR/graph.json","fetch_events":"https://pith.science/api/pith-number/FCRSSLX2BWMANINBOKGINWEQOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCRSSLX2BWMANINBOKGINWEQOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCRSSLX2BWMANINBOKGINWEQOR/action/storage_attestation","attest_author":"https://pith.science/pith/FCRSSLX2BWMANINBOKGINWEQOR/action/author_attestation","sign_citation":"https://pith.science/pith/FCRSSLX2BWMANINBOKGINWEQOR/action/citation_signature","submit_replication":"https://pith.science/pith/FCRSSLX2BWMANINBOKGINWEQOR/action/replication_record"}},"created_at":"2026-07-02T00:18:42.482586+00:00","updated_at":"2026-07-02T00:18:42.482586+00:00"}