{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6XAH2AHXYI3E6FJVNJQ3MWY3EO","short_pith_number":"pith:6XAH2AHX","schema_version":"1.0","canonical_sha256":"f5c07d00f7c2364f15356a61b65b1b23b9a677e2765f5aeb61551dffa54b9f38","source":{"kind":"arxiv","id":"2507.01334","version":2},"attestation_state":"computed","paper":{"title":"Symbolic or Numerical? Understanding Physics Problem Solving in Reasoning LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nifu Dan, Yiwei Wang, Yujun Cai","submitted_at":"2025-07-02T03:51:16Z","abstract_excerpt":"Navigating the complexities of physics reasoning has long been a difficult task for Large Language Models (LLMs), requiring a synthesis of profound conceptual understanding and adept problem-solving techniques. In this study, we investigate the application of advanced instruction-tuned reasoning models, such as Deepseek-R1, to address a diverse spectrum of physics problems curated from the challenging SciBench benchmark. Our comprehensive experimental evaluation reveals the remarkable capabilities of reasoning models. Not only do they achieve state-of-the-art accuracy in answering intricate ph"},"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":"2507.01334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T03:51:16Z","cross_cats_sorted":[],"title_canon_sha256":"5f397167e78be9f62c9580eb518f4ffd0d8bc2902fd5c528521c0a53d6d0d7ba","abstract_canon_sha256":"da14e16a53128e6256576328c061ec1f23f4f67849caca9a4737c78698ec7599"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:29.330856Z","signature_b64":"pJ5ZlsOZWS6UQDTr4/Wtq+dyanj5BO+21VmJ6Y190qVFNMhbMOPkv24uKxF0nJ7mA6KJgELR9lbDWzUUnQTmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5c07d00f7c2364f15356a61b65b1b23b9a677e2765f5aeb61551dffa54b9f38","last_reissued_at":"2026-07-05T11:31:29.330406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:29.330406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbolic or Numerical? Understanding Physics Problem Solving in Reasoning LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nifu Dan, Yiwei Wang, Yujun Cai","submitted_at":"2025-07-02T03:51:16Z","abstract_excerpt":"Navigating the complexities of physics reasoning has long been a difficult task for Large Language Models (LLMs), requiring a synthesis of profound conceptual understanding and adept problem-solving techniques. In this study, we investigate the application of advanced instruction-tuned reasoning models, such as Deepseek-R1, to address a diverse spectrum of physics problems curated from the challenging SciBench benchmark. Our comprehensive experimental evaluation reveals the remarkable capabilities of reasoning models. Not only do they achieve state-of-the-art accuracy in answering intricate ph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01334","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/2507.01334/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":"2507.01334","created_at":"2026-07-05T11:31:29.330466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01334v2","created_at":"2026-07-05T11:31:29.330466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01334","created_at":"2026-07-05T11:31:29.330466+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XAH2AHXYI3E","created_at":"2026-07-05T11:31:29.330466+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XAH2AHXYI3E6FJV","created_at":"2026-07-05T11:31:29.330466+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XAH2AHX","created_at":"2026-07-05T11:31:29.330466+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/6XAH2AHXYI3E6FJVNJQ3MWY3EO","json":"https://pith.science/pith/6XAH2AHXYI3E6FJVNJQ3MWY3EO.json","graph_json":"https://pith.science/api/pith-number/6XAH2AHXYI3E6FJVNJQ3MWY3EO/graph.json","events_json":"https://pith.science/api/pith-number/6XAH2AHXYI3E6FJVNJQ3MWY3EO/events.json","paper":"https://pith.science/paper/6XAH2AHX"},"agent_actions":{"view_html":"https://pith.science/pith/6XAH2AHXYI3E6FJVNJQ3MWY3EO","download_json":"https://pith.science/pith/6XAH2AHXYI3E6FJVNJQ3MWY3EO.json","view_paper":"https://pith.science/paper/6XAH2AHX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01334&json=true","fetch_graph":"https://pith.science/api/pith-number/6XAH2AHXYI3E6FJVNJQ3MWY3EO/graph.json","fetch_events":"https://pith.science/api/pith-number/6XAH2AHXYI3E6FJVNJQ3MWY3EO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XAH2AHXYI3E6FJVNJQ3MWY3EO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XAH2AHXYI3E6FJVNJQ3MWY3EO/action/storage_attestation","attest_author":"https://pith.science/pith/6XAH2AHXYI3E6FJVNJQ3MWY3EO/action/author_attestation","sign_citation":"https://pith.science/pith/6XAH2AHXYI3E6FJVNJQ3MWY3EO/action/citation_signature","submit_replication":"https://pith.science/pith/6XAH2AHXYI3E6FJVNJQ3MWY3EO/action/replication_record"}},"created_at":"2026-07-05T11:31:29.330466+00:00","updated_at":"2026-07-05T11:31:29.330466+00:00"}