{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UEEHPQ3XOVBIDLHN6MUG3UDQT3","short_pith_number":"pith:UEEHPQ3X","schema_version":"1.0","canonical_sha256":"a10877c377754281acedf3286dd0709ef7da2a386d4269ae9ec3ce5414278521","source":{"kind":"arxiv","id":"2310.10047","version":1},"attestation_state":"computed","paper":{"title":"Improving Large Language Model Fine-tuning for Solving Math Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avi Singh, C. Daniel Freeman, John D. Co-Reyes, Peter J. Liu, Yixin Liu","submitted_at":"2023-10-16T04:11:19Z","abstract_excerpt":"Despite their success in many natural language tasks, solving math problems remains a significant challenge for large language models (LLMs). A large gap exists between LLMs' pass-at-one and pass-at-N performance in solving math problems, suggesting LLMs might be close to finding correct solutions, motivating our exploration of fine-tuning methods to unlock LLMs' performance. Using the challenging MATH dataset, we investigate three fine-tuning strategies: (1) solution fine-tuning, where we fine-tune to generate a detailed solution for a given math problem; (2) solution-cluster re-ranking, wher"},"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":"2310.10047","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T04:11:19Z","cross_cats_sorted":[],"title_canon_sha256":"d22173449970be3120026b8c5cd418545d834896b4139445ca2cc617d8d30713","abstract_canon_sha256":"040c1e92be30f6859e52d3e30c41979ef68dee3253d244059a23c41ccdaa4422"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:14.462412Z","signature_b64":"klaIJaOD51GdLnumoeW0cLkZxcrwrH3Q6iC8SXLb1wuwGPVvOsQEvb9MnClay0OHh3zO3TcnScLwbMzPr5CkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a10877c377754281acedf3286dd0709ef7da2a386d4269ae9ec3ce5414278521","last_reissued_at":"2026-07-05T07:01:14.461962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:14.461962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Large Language Model Fine-tuning for Solving Math Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avi Singh, C. Daniel Freeman, John D. Co-Reyes, Peter J. Liu, Yixin Liu","submitted_at":"2023-10-16T04:11:19Z","abstract_excerpt":"Despite their success in many natural language tasks, solving math problems remains a significant challenge for large language models (LLMs). A large gap exists between LLMs' pass-at-one and pass-at-N performance in solving math problems, suggesting LLMs might be close to finding correct solutions, motivating our exploration of fine-tuning methods to unlock LLMs' performance. Using the challenging MATH dataset, we investigate three fine-tuning strategies: (1) solution fine-tuning, where we fine-tune to generate a detailed solution for a given math problem; (2) solution-cluster re-ranking, wher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10047","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/2310.10047/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":"2310.10047","created_at":"2026-07-05T07:01:14.462018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10047v1","created_at":"2026-07-05T07:01:14.462018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10047","created_at":"2026-07-05T07:01:14.462018+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEEHPQ3XOVBI","created_at":"2026-07-05T07:01:14.462018+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEEHPQ3XOVBIDLHN","created_at":"2026-07-05T07:01:14.462018+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEEHPQ3X","created_at":"2026-07-05T07:01:14.462018+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.18629","citing_title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05893","citing_title":"Logic-Regularized Verifier Elicits Reasoning from LLMs","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UEEHPQ3XOVBIDLHN6MUG3UDQT3","json":"https://pith.science/pith/UEEHPQ3XOVBIDLHN6MUG3UDQT3.json","graph_json":"https://pith.science/api/pith-number/UEEHPQ3XOVBIDLHN6MUG3UDQT3/graph.json","events_json":"https://pith.science/api/pith-number/UEEHPQ3XOVBIDLHN6MUG3UDQT3/events.json","paper":"https://pith.science/paper/UEEHPQ3X"},"agent_actions":{"view_html":"https://pith.science/pith/UEEHPQ3XOVBIDLHN6MUG3UDQT3","download_json":"https://pith.science/pith/UEEHPQ3XOVBIDLHN6MUG3UDQT3.json","view_paper":"https://pith.science/paper/UEEHPQ3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10047&json=true","fetch_graph":"https://pith.science/api/pith-number/UEEHPQ3XOVBIDLHN6MUG3UDQT3/graph.json","fetch_events":"https://pith.science/api/pith-number/UEEHPQ3XOVBIDLHN6MUG3UDQT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEEHPQ3XOVBIDLHN6MUG3UDQT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEEHPQ3XOVBIDLHN6MUG3UDQT3/action/storage_attestation","attest_author":"https://pith.science/pith/UEEHPQ3XOVBIDLHN6MUG3UDQT3/action/author_attestation","sign_citation":"https://pith.science/pith/UEEHPQ3XOVBIDLHN6MUG3UDQT3/action/citation_signature","submit_replication":"https://pith.science/pith/UEEHPQ3XOVBIDLHN6MUG3UDQT3/action/replication_record"}},"created_at":"2026-07-05T07:01:14.462018+00:00","updated_at":"2026-07-05T07:01:14.462018+00:00"}