{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AYTLSQJ66G7DC5JTCZIMPKSXJ5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c529773490e5c9969d3785d4d48d23a146fcb31e38f86b7dbb06351844523f17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-26T06:21:56Z","title_canon_sha256":"7de518dc8b95f80a224b41c6e3aaae72b95a07bc7c57cb701ad37a1213fd1040"},"schema_version":"1.0","source":{"id":"2503.21821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21821","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21821v1","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21821","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"AYTLSQJ66G7D","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"AYTLSQJ66G7DC5JT","created_at":"2026-05-22T01:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"AYTLSQJ6","created_at":"2026-05-22T01:03:42Z"}],"graph_snapshots":[{"event_id":"sha256:7d21e6d920d47be8bfc02d443b871bcae3541b749daccacee55c66d505762b07","target":"graph","created_at":"2026-05-22T01:03:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.21821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce PHYSICS, a comprehensive benchmark for university-level physics problem solving. It contains 1297 expert-annotated problems covering six core areas: classical mechanics, quantum mechanics, thermodynamics and statistical mechanics, electromagnetism, atomic physics, and optics. Each problem requires advanced physics knowledge and mathematical reasoning. We develop a robust automated evaluation system for precise and reliable validation. Our evaluation of leading foundation models reveals substantial limitations. Even the most advanced model, o3-mini, achieves only 59.9% accuracy, hi","authors_text":"Arman Cohan, Chen Zhao, John Sous, Kaiyue Feng, Tianyu Yang, Yilun Zhao, Yixin Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-26T06:21:56Z","title":"PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21821","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ba433a68a712126e0e4f1e6ed501db436a06c89c30b71265d7e858fbfaf148c6","target":"record","created_at":"2026-05-22T01:03:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c529773490e5c9969d3785d4d48d23a146fcb31e38f86b7dbb06351844523f17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-26T06:21:56Z","title_canon_sha256":"7de518dc8b95f80a224b41c6e3aaae72b95a07bc7c57cb701ad37a1213fd1040"},"schema_version":"1.0","source":{"id":"2503.21821","kind":"arxiv","version":1}},"canonical_sha256":"0626b9413ef1be3175331650c7aa574f7620a6456bc7277b85ef2cb459a5f734","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0626b9413ef1be3175331650c7aa574f7620a6456bc7277b85ef2cb459a5f734","first_computed_at":"2026-05-22T01:03:42.355303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:42.355303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RbGoaWmpOI66gO0zFoiB7Hv51b0tvzxk9nrtBLf492IDfUrPN0mKPaSGWBil7npSCeZoo4Vp8+3B1WGI0afYCg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:42.356140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.21821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba433a68a712126e0e4f1e6ed501db436a06c89c30b71265d7e858fbfaf148c6","sha256:7d21e6d920d47be8bfc02d443b871bcae3541b749daccacee55c66d505762b07"],"state_sha256":"0bfbc917098bee1bd9bb097259f4ace5dc714cbb73baba67df58da75444f85f0"}