{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UEEHPQ3XOVBIDLHN6MUG3UDQT3","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":"040c1e92be30f6859e52d3e30c41979ef68dee3253d244059a23c41ccdaa4422","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T04:11:19Z","title_canon_sha256":"d22173449970be3120026b8c5cd418545d834896b4139445ca2cc617d8d30713"},"schema_version":"1.0","source":{"id":"2310.10047","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10047","created_at":"2026-07-05T07:01:14Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10047v1","created_at":"2026-07-05T07:01:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10047","created_at":"2026-07-05T07:01:14Z"},{"alias_kind":"pith_short_12","alias_value":"UEEHPQ3XOVBI","created_at":"2026-07-05T07:01:14Z"},{"alias_kind":"pith_short_16","alias_value":"UEEHPQ3XOVBIDLHN","created_at":"2026-07-05T07:01:14Z"},{"alias_kind":"pith_short_8","alias_value":"UEEHPQ3X","created_at":"2026-07-05T07:01:14Z"}],"graph_snapshots":[{"event_id":"sha256:bd2d58ee745cc77003a2c9604023d0656d30bd77d19680008a5c562c24d76fa0","target":"graph","created_at":"2026-07-05T07:01:14Z","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/2310.10047/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Avi Singh, C. Daniel Freeman, John D. Co-Reyes, Peter J. Liu, Yixin Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T04:11:19Z","title":"Improving Large Language Model Fine-tuning for Solving Math Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10047","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":"sha256:3a745bcdaf4b9a6fabe29198fbee8b49fc12e62f474bc447d6e4573be1c7fe9d","target":"record","created_at":"2026-07-05T07:01:14Z","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":"040c1e92be30f6859e52d3e30c41979ef68dee3253d244059a23c41ccdaa4422","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T04:11:19Z","title_canon_sha256":"d22173449970be3120026b8c5cd418545d834896b4139445ca2cc617d8d30713"},"schema_version":"1.0","source":{"id":"2310.10047","kind":"arxiv","version":1}},"canonical_sha256":"a10877c377754281acedf3286dd0709ef7da2a386d4269ae9ec3ce5414278521","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a10877c377754281acedf3286dd0709ef7da2a386d4269ae9ec3ce5414278521","first_computed_at":"2026-07-05T07:01:14.461962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:14.461962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"klaIJaOD51GdLnumoeW0cLkZxcrwrH3Q6iC8SXLb1wuwGPVvOsQEvb9MnClay0OHh3zO3TcnScLwbMzPr5CkBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:14.462412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10047","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a745bcdaf4b9a6fabe29198fbee8b49fc12e62f474bc447d6e4573be1c7fe9d","sha256:bd2d58ee745cc77003a2c9604023d0656d30bd77d19680008a5c562c24d76fa0"],"state_sha256":"db6d1748c9dc9769c2cd224e51aca6fb37d8a5015849f0cbdd1a867594b2aac7"}