{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:74ZB5UNA7IGYDELU5HCGFQF57Z","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":"6af52ed7799d1524c021b06ef479f26100a6445a8987146a601d2acd69ee04b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T05:43:50Z","title_canon_sha256":"ec258769838e10f7446c767f5b608bcd29b5a2d3cf886a804b656d3b8aa2b62c"},"schema_version":"1.0","source":{"id":"2412.16871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16871","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16871v1","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16871","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"pith_short_12","alias_value":"74ZB5UNA7IGY","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"pith_short_16","alias_value":"74ZB5UNA7IGYDELU","created_at":"2026-07-05T09:53:13Z"},{"alias_kind":"pith_short_8","alias_value":"74ZB5UNA","created_at":"2026-07-05T09:53:13Z"}],"graph_snapshots":[{"event_id":"sha256:3ff53f96094d68a7d28330841e814fcf4ee7f7145a3bac3e6603624bfd83da59","target":"graph","created_at":"2026-07-05T09:53:13Z","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/2412.16871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) can refine their responses based on feedback, enabling self-improvement through iterative training or test-time refinement. However, existing methods predominantly focus on refinement within the same reasoning format, which may lead to non-correcting behaviors. We propose CaP, a novel approach that uses external tools to refine chain-of-thought (CoT) responses generated by the same or other LLMs. CaP employs a two-stage training process: supervised fine-tuning followed by preference optimization with DPO variants. Our observations highlight the critical role of pre","authors_text":"Dian Yu, Dong Yu, Haitao Mi, Jiahao Xu, Linfeng Song, Tian Liang, Yuheng Zhang, Zhaopeng Tu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T05:43:50Z","title":"Teaching LLMs to Refine with Tools"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16871","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":"sha256:5d4b29dec76c6dc96e083a207cbf999d9c25f46bcac82bd4a96c45e5e9ce2db9","target":"record","created_at":"2026-07-05T09:53:13Z","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":"6af52ed7799d1524c021b06ef479f26100a6445a8987146a601d2acd69ee04b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T05:43:50Z","title_canon_sha256":"ec258769838e10f7446c767f5b608bcd29b5a2d3cf886a804b656d3b8aa2b62c"},"schema_version":"1.0","source":{"id":"2412.16871","kind":"arxiv","version":1}},"canonical_sha256":"ff321ed1a0fa0d819174e9c462c0bdfe5e34252af2e62140df767275542e957f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff321ed1a0fa0d819174e9c462c0bdfe5e34252af2e62140df767275542e957f","first_computed_at":"2026-07-05T09:53:13.982934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:13.982934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"trQ/hxyscUyO48/X2IB7jdulhDnlewZtYTOc3RTPI7VIXFZQawUktOVWrGtqQQnH9CNoCKEaMEoDAoZWia5OBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:13.983416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d4b29dec76c6dc96e083a207cbf999d9c25f46bcac82bd4a96c45e5e9ce2db9","sha256:3ff53f96094d68a7d28330841e814fcf4ee7f7145a3bac3e6603624bfd83da59"],"state_sha256":"4ce2e2a7607fea0d46af4a68be5fbd1199f8497bd808f4e7680b841151d335f2"}