{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WTGFSDP2TC7HF3ESY7CSGJREF3","short_pith_number":"pith:WTGFSDP2","canonical_record":{"source":{"id":"2501.17703","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T15:20:30Z","cross_cats_sorted":[],"title_canon_sha256":"dad1a929e5c0182287d20e595e17062b2f802a52cc6ecc77c530b9df508f1b9c","abstract_canon_sha256":"e6f8a81cd7ea9d444b7509293b530c0687151bf1a66b02e450b96f26bbdaa706"},"schema_version":"1.0"},"canonical_sha256":"b4cc590dfa98be72ec92c7c52326242ec69008d000cf27f5c8a86464c5a6e486","source":{"kind":"arxiv","id":"2501.17703","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17703","created_at":"2026-07-05T10:41:20Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17703v4","created_at":"2026-07-05T10:41:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17703","created_at":"2026-07-05T10:41:20Z"},{"alias_kind":"pith_short_12","alias_value":"WTGFSDP2TC7H","created_at":"2026-07-05T10:41:20Z"},{"alias_kind":"pith_short_16","alias_value":"WTGFSDP2TC7HF3ES","created_at":"2026-07-05T10:41:20Z"},{"alias_kind":"pith_short_8","alias_value":"WTGFSDP2","created_at":"2026-07-05T10:41:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WTGFSDP2TC7HF3ESY7CSGJREF3","target":"record","payload":{"canonical_record":{"source":{"id":"2501.17703","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T15:20:30Z","cross_cats_sorted":[],"title_canon_sha256":"dad1a929e5c0182287d20e595e17062b2f802a52cc6ecc77c530b9df508f1b9c","abstract_canon_sha256":"e6f8a81cd7ea9d444b7509293b530c0687151bf1a66b02e450b96f26bbdaa706"},"schema_version":"1.0"},"canonical_sha256":"b4cc590dfa98be72ec92c7c52326242ec69008d000cf27f5c8a86464c5a6e486","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:20.097655Z","signature_b64":"qf2OFsu9yRlDZ6Ma2ayhbZr0IsphsIF+DNjX5hMlf69bFWUOLR25S60BfNMe/0AfCdT+N2+dPKdLHjgnnJfKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4cc590dfa98be72ec92c7c52326242ec69008d000cf27f5c8a86464c5a6e486","last_reissued_at":"2026-07-05T10:41:20.097062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:20.097062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.17703","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cq53FjmEqu5AQ+MQLsQqJf9sksH5say7PyOvxp3kBT+khatEsTrIfK4STpuEMTwvxGt40mAfme38suroC5QDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T20:27:57.483081Z"},"content_sha256":"e67350af7c9805bac633f9e4486b4375df0eecefd6716ccff71242148831a797","schema_version":"1.0","event_id":"sha256:e67350af7c9805bac633f9e4486b4375df0eecefd6716ccff71242148831a797"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WTGFSDP2TC7HF3ESY7CSGJREF3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Wenhu Chen, Xiang Yue, Yubo Wang","submitted_at":"2025-01-29T15:20:30Z","abstract_excerpt":"Supervised Fine-Tuning (SFT) is commonly used to train language models to imitate annotated responses for given instructions. In this paper, we propose Critique Fine-Tuning (CFT), a method more effective than SFT for reasoning tasks. Instead of simply imitating correct responses, CFT trains models to critique noisy responses, inspired by human learning processes that emphasize critical thinking, deeper analysis, and nuanced understanding - traits often overlooked by standard SFT. To validate the effectiveness of CFT, we construct multiple critique datasets (e.g., WebInstruct, MetaMath, NuminaM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17703","kind":"arxiv","version":4},"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/2501.17703/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z9larG2qvFNKKdejA3Tw4JvL38KvQ4IDk22GUWWricBLUMIZ7VMctZzxGopI7rGf7vVhBncDS5+kZagtM5VlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T20:27:57.483464Z"},"content_sha256":"76d8b29f5496fc6047fcb3058e5a1dfd5c5c8658a99860fddabd76bc77d66ef9","schema_version":"1.0","event_id":"sha256:76d8b29f5496fc6047fcb3058e5a1dfd5c5c8658a99860fddabd76bc77d66ef9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTGFSDP2TC7HF3ESY7CSGJREF3/bundle.json","state_url":"https://pith.science/pith/WTGFSDP2TC7HF3ESY7CSGJREF3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTGFSDP2TC7HF3ESY7CSGJREF3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-10T20:27:57Z","links":{"resolver":"https://pith.science/pith/WTGFSDP2TC7HF3ESY7CSGJREF3","bundle":"https://pith.science/pith/WTGFSDP2TC7HF3ESY7CSGJREF3/bundle.json","state":"https://pith.science/pith/WTGFSDP2TC7HF3ESY7CSGJREF3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTGFSDP2TC7HF3ESY7CSGJREF3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WTGFSDP2TC7HF3ESY7CSGJREF3","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":"e6f8a81cd7ea9d444b7509293b530c0687151bf1a66b02e450b96f26bbdaa706","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T15:20:30Z","title_canon_sha256":"dad1a929e5c0182287d20e595e17062b2f802a52cc6ecc77c530b9df508f1b9c"},"schema_version":"1.0","source":{"id":"2501.17703","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17703","created_at":"2026-07-05T10:41:20Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17703v4","created_at":"2026-07-05T10:41:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17703","created_at":"2026-07-05T10:41:20Z"},{"alias_kind":"pith_short_12","alias_value":"WTGFSDP2TC7H","created_at":"2026-07-05T10:41:20Z"},{"alias_kind":"pith_short_16","alias_value":"WTGFSDP2TC7HF3ES","created_at":"2026-07-05T10:41:20Z"},{"alias_kind":"pith_short_8","alias_value":"WTGFSDP2","created_at":"2026-07-05T10:41:20Z"}],"graph_snapshots":[{"event_id":"sha256:76d8b29f5496fc6047fcb3058e5a1dfd5c5c8658a99860fddabd76bc77d66ef9","target":"graph","created_at":"2026-07-05T10:41:20Z","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/2501.17703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised Fine-Tuning (SFT) is commonly used to train language models to imitate annotated responses for given instructions. In this paper, we propose Critique Fine-Tuning (CFT), a method more effective than SFT for reasoning tasks. Instead of simply imitating correct responses, CFT trains models to critique noisy responses, inspired by human learning processes that emphasize critical thinking, deeper analysis, and nuanced understanding - traits often overlooked by standard SFT. To validate the effectiveness of CFT, we construct multiple critique datasets (e.g., WebInstruct, MetaMath, NuminaM","authors_text":"Wenhu Chen, Xiang Yue, Yubo Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T15:20:30Z","title":"Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17703","kind":"arxiv","version":4},"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:e67350af7c9805bac633f9e4486b4375df0eecefd6716ccff71242148831a797","target":"record","created_at":"2026-07-05T10:41:20Z","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":"e6f8a81cd7ea9d444b7509293b530c0687151bf1a66b02e450b96f26bbdaa706","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-29T15:20:30Z","title_canon_sha256":"dad1a929e5c0182287d20e595e17062b2f802a52cc6ecc77c530b9df508f1b9c"},"schema_version":"1.0","source":{"id":"2501.17703","kind":"arxiv","version":4}},"canonical_sha256":"b4cc590dfa98be72ec92c7c52326242ec69008d000cf27f5c8a86464c5a6e486","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4cc590dfa98be72ec92c7c52326242ec69008d000cf27f5c8a86464c5a6e486","first_computed_at":"2026-07-05T10:41:20.097062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:20.097062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qf2OFsu9yRlDZ6Ma2ayhbZr0IsphsIF+DNjX5hMlf69bFWUOLR25S60BfNMe/0AfCdT+N2+dPKdLHjgnnJfKCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:20.097655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17703","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e67350af7c9805bac633f9e4486b4375df0eecefd6716ccff71242148831a797","sha256:76d8b29f5496fc6047fcb3058e5a1dfd5c5c8658a99860fddabd76bc77d66ef9"],"state_sha256":"5de5ec2176fb33462f2f0ebb30b60642e71977c1e8d1e335fd7f9d9cc19ef38e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VVoV0CFJGNhcObsBaSMV8bNqIGV0MYHZiHdKbb/I5TjlZuqaqTKaR9J8O7h46Uu42Ai5k5la5VgunZfI0N58Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T20:27:57.485979Z","bundle_sha256":"75990719e9b5ccb29e0e913991f9337381add776a25dda65cfc62540747894f7"}}