{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ESCC4IKRILPYVWD2R6Z2LRJYVK","short_pith_number":"pith:ESCC4IKR","schema_version":"1.0","canonical_sha256":"24842e215142df8ad87a8fb3a5c538aa92318991f617e9a6ecec39fea6c4291f","source":{"kind":"arxiv","id":"2502.12054","version":2},"attestation_state":"computed","paper":{"title":"PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Basura Fernando, Chengyou Jia, Jiaxing Huang, Jun Liu, Lingling Zhang, Mike Zheng Shou, Xinyu Zhang, Yanrui Wu, Yuxuan Dong","submitted_at":"2025-02-17T17:24:14Z","abstract_excerpt":"Large language models demonstrate remarkable capabilities across various domains, especially mathematics and logic reasoning. However, current evaluations overlook physics-based reasoning - a complex task requiring physics theorems and constraints. We present PhysReason, a 1,200-problem benchmark comprising knowledge-based (25%) and reasoning-based (75%) problems, where the latter are divided into three difficulty levels (easy, medium, hard). Notably, problems require an average of 8.1 solution steps, with hard requiring 15.6, reflecting the complexity of physics-based reasoning. We propose th"},"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":"2502.12054","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T17:24:14Z","cross_cats_sorted":[],"title_canon_sha256":"5b941e87aa6b66da51b7eeda79df5e3e947b69a61a79be3b7e0995aa8f2118e7","abstract_canon_sha256":"552acb01ab157a07bd8b8fb1877fb90cc44ae21af2bcfc6866a3fb9efbadf22b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:45.310083Z","signature_b64":"ElBT6f3K7i3Rwyzp26bQRR0pAPdBDBbyl111c+TwYePl8eeRRYkmsWStm1cqBCFwVhJskVukTguz7nww4S2GAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24842e215142df8ad87a8fb3a5c538aa92318991f617e9a6ecec39fea6c4291f","last_reissued_at":"2026-07-05T11:09:45.309570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:45.309570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Basura Fernando, Chengyou Jia, Jiaxing Huang, Jun Liu, Lingling Zhang, Mike Zheng Shou, Xinyu Zhang, Yanrui Wu, Yuxuan Dong","submitted_at":"2025-02-17T17:24:14Z","abstract_excerpt":"Large language models demonstrate remarkable capabilities across various domains, especially mathematics and logic reasoning. However, current evaluations overlook physics-based reasoning - a complex task requiring physics theorems and constraints. We present PhysReason, a 1,200-problem benchmark comprising knowledge-based (25%) and reasoning-based (75%) problems, where the latter are divided into three difficulty levels (easy, medium, hard). Notably, problems require an average of 8.1 solution steps, with hard requiring 15.6, reflecting the complexity of physics-based reasoning. We propose th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12054","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/2502.12054/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":"2502.12054","created_at":"2026-07-05T11:09:45.309635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12054v2","created_at":"2026-07-05T11:09:45.309635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12054","created_at":"2026-07-05T11:09:45.309635+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESCC4IKRILPY","created_at":"2026-07-05T11:09:45.309635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESCC4IKRILPYVWD2","created_at":"2026-07-05T11:09:45.309635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESCC4IKR","created_at":"2026-07-05T11:09:45.309635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08034","citing_title":"Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05966","citing_title":"Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06226","citing_title":"GeoLaux: A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20374","citing_title":"CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24443","citing_title":"PhysNote: Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18936","citing_title":"Fine-Tuning Small Reasoning Models for Quantum Field Theory","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESCC4IKRILPYVWD2R6Z2LRJYVK","json":"https://pith.science/pith/ESCC4IKRILPYVWD2R6Z2LRJYVK.json","graph_json":"https://pith.science/api/pith-number/ESCC4IKRILPYVWD2R6Z2LRJYVK/graph.json","events_json":"https://pith.science/api/pith-number/ESCC4IKRILPYVWD2R6Z2LRJYVK/events.json","paper":"https://pith.science/paper/ESCC4IKR"},"agent_actions":{"view_html":"https://pith.science/pith/ESCC4IKRILPYVWD2R6Z2LRJYVK","download_json":"https://pith.science/pith/ESCC4IKRILPYVWD2R6Z2LRJYVK.json","view_paper":"https://pith.science/paper/ESCC4IKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12054&json=true","fetch_graph":"https://pith.science/api/pith-number/ESCC4IKRILPYVWD2R6Z2LRJYVK/graph.json","fetch_events":"https://pith.science/api/pith-number/ESCC4IKRILPYVWD2R6Z2LRJYVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESCC4IKRILPYVWD2R6Z2LRJYVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESCC4IKRILPYVWD2R6Z2LRJYVK/action/storage_attestation","attest_author":"https://pith.science/pith/ESCC4IKRILPYVWD2R6Z2LRJYVK/action/author_attestation","sign_citation":"https://pith.science/pith/ESCC4IKRILPYVWD2R6Z2LRJYVK/action/citation_signature","submit_replication":"https://pith.science/pith/ESCC4IKRILPYVWD2R6Z2LRJYVK/action/replication_record"}},"created_at":"2026-07-05T11:09:45.309635+00:00","updated_at":"2026-07-05T11:09:45.309635+00:00"}