{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FKUZSAERHR7F2S76XZQHE5I2Q6","short_pith_number":"pith:FKUZSAER","canonical_record":{"source":{"id":"2401.08967","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-17T04:43:21Z","cross_cats_sorted":[],"title_canon_sha256":"7079054bb8e87f6a13bea6b22945ce55be500dee155c5d42727f3279a6c43525","abstract_canon_sha256":"2c0607116b51589f14ca0982ff9803b6f56f3cdaeeebb0f9620371d82977bc82"},"schema_version":"1.0"},"canonical_sha256":"2aa99900913c7e5d4bfebe6072751a87af1648597b9f6eb02de785da1e6e52ca","source":{"kind":"arxiv","id":"2401.08967","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08967","created_at":"2026-07-05T09:48:30Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08967v3","created_at":"2026-07-05T09:48:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08967","created_at":"2026-07-05T09:48:30Z"},{"alias_kind":"pith_short_12","alias_value":"FKUZSAERHR7F","created_at":"2026-07-05T09:48:30Z"},{"alias_kind":"pith_short_16","alias_value":"FKUZSAERHR7F2S76","created_at":"2026-07-05T09:48:30Z"},{"alias_kind":"pith_short_8","alias_value":"FKUZSAER","created_at":"2026-07-05T09:48:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FKUZSAERHR7F2S76XZQHE5I2Q6","target":"record","payload":{"canonical_record":{"source":{"id":"2401.08967","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-17T04:43:21Z","cross_cats_sorted":[],"title_canon_sha256":"7079054bb8e87f6a13bea6b22945ce55be500dee155c5d42727f3279a6c43525","abstract_canon_sha256":"2c0607116b51589f14ca0982ff9803b6f56f3cdaeeebb0f9620371d82977bc82"},"schema_version":"1.0"},"canonical_sha256":"2aa99900913c7e5d4bfebe6072751a87af1648597b9f6eb02de785da1e6e52ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:30.904833Z","signature_b64":"NPbgBnb74JKpD+pkq9kk0G7u5qGEYJfsmXL8F/vQVNHUjnBucDx+IBtUZ/KDthYm6TNvN7yLvQXzO/oXGwNJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2aa99900913c7e5d4bfebe6072751a87af1648597b9f6eb02de785da1e6e52ca","last_reissued_at":"2026-07-05T09:48:30.904322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:30.904322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.08967","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:48:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/2oPWn7JmJaQ3PfksXG0a7f1rl3H8uKgjOUV9LA3pHwZybA2DMroYgNjBiHgNtyfcrJZRinKwQLoiRgTSKnWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:22:23.461700Z"},"content_sha256":"b84f4c8a19a5cfcfbd941c9895339a7cff6496649cf5efa95f07b4b0d5960216","schema_version":"1.0","event_id":"sha256:b84f4c8a19a5cfcfbd941c9895339a7cff6496649cf5efa95f07b4b0d5960216"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FKUZSAERHR7F2S76XZQHE5I2Q6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReFT: Reasoning with Reinforced Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Li, Peng Sun, Trung Quoc Luong, Xiaoran Jin, Xinbo Zhang, Zhanming Jie","submitted_at":"2024-01-17T04:43:21Z","abstract_excerpt":"One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This approach does not show sufficiently strong generalization ability, however, because the training only relies on the given CoT data. In math problem-solving, for example, there is usually only one annotated reasoning path for each question in the training data. Intuitively, it would be better for the algorithm to learn from multiple annotated reasoning paths given a question. To address this issue, we propose a simple yet effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08967","kind":"arxiv","version":3},"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/2401.08967/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":"2026-07-05T09:48:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hogpk2q61mfeAHJcofF0gA14Ud3Yp4R9h2T3WYpwrElW0bA0LiUosK9xWZKc3cvKflMq+UCi2oZRokWgMGJ6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:22:23.462220Z"},"content_sha256":"e9c0bf40de9838cfd0a833b89925e875e20b324d2794c2431138a43ba03a2021","schema_version":"1.0","event_id":"sha256:e9c0bf40de9838cfd0a833b89925e875e20b324d2794c2431138a43ba03a2021"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FKUZSAERHR7F2S76XZQHE5I2Q6/bundle.json","state_url":"https://pith.science/pith/FKUZSAERHR7F2S76XZQHE5I2Q6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FKUZSAERHR7F2S76XZQHE5I2Q6/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":"2026-08-06T14:22:23Z","links":{"resolver":"https://pith.science/pith/FKUZSAERHR7F2S76XZQHE5I2Q6","bundle":"https://pith.science/pith/FKUZSAERHR7F2S76XZQHE5I2Q6/bundle.json","state":"https://pith.science/pith/FKUZSAERHR7F2S76XZQHE5I2Q6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FKUZSAERHR7F2S76XZQHE5I2Q6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FKUZSAERHR7F2S76XZQHE5I2Q6","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":"2c0607116b51589f14ca0982ff9803b6f56f3cdaeeebb0f9620371d82977bc82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-17T04:43:21Z","title_canon_sha256":"7079054bb8e87f6a13bea6b22945ce55be500dee155c5d42727f3279a6c43525"},"schema_version":"1.0","source":{"id":"2401.08967","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08967","created_at":"2026-07-05T09:48:30Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08967v3","created_at":"2026-07-05T09:48:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08967","created_at":"2026-07-05T09:48:30Z"},{"alias_kind":"pith_short_12","alias_value":"FKUZSAERHR7F","created_at":"2026-07-05T09:48:30Z"},{"alias_kind":"pith_short_16","alias_value":"FKUZSAERHR7F2S76","created_at":"2026-07-05T09:48:30Z"},{"alias_kind":"pith_short_8","alias_value":"FKUZSAER","created_at":"2026-07-05T09:48:30Z"}],"graph_snapshots":[{"event_id":"sha256:e9c0bf40de9838cfd0a833b89925e875e20b324d2794c2431138a43ba03a2021","target":"graph","created_at":"2026-07-05T09:48:30Z","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/2401.08967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One way to enhance the reasoning capability of Large Language Models (LLMs) is to conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This approach does not show sufficiently strong generalization ability, however, because the training only relies on the given CoT data. In math problem-solving, for example, there is usually only one annotated reasoning path for each question in the training data. Intuitively, it would be better for the algorithm to learn from multiple annotated reasoning paths given a question. To address this issue, we propose a simple yet effective","authors_text":"Hang Li, Peng Sun, Trung Quoc Luong, Xiaoran Jin, Xinbo Zhang, Zhanming Jie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-17T04:43:21Z","title":"ReFT: Reasoning with Reinforced Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08967","kind":"arxiv","version":3},"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:b84f4c8a19a5cfcfbd941c9895339a7cff6496649cf5efa95f07b4b0d5960216","target":"record","created_at":"2026-07-05T09:48:30Z","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":"2c0607116b51589f14ca0982ff9803b6f56f3cdaeeebb0f9620371d82977bc82","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-17T04:43:21Z","title_canon_sha256":"7079054bb8e87f6a13bea6b22945ce55be500dee155c5d42727f3279a6c43525"},"schema_version":"1.0","source":{"id":"2401.08967","kind":"arxiv","version":3}},"canonical_sha256":"2aa99900913c7e5d4bfebe6072751a87af1648597b9f6eb02de785da1e6e52ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2aa99900913c7e5d4bfebe6072751a87af1648597b9f6eb02de785da1e6e52ca","first_computed_at":"2026-07-05T09:48:30.904322Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:30.904322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NPbgBnb74JKpD+pkq9kk0G7u5qGEYJfsmXL8F/vQVNHUjnBucDx+IBtUZ/KDthYm6TNvN7yLvQXzO/oXGwNJBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:30.904833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08967","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b84f4c8a19a5cfcfbd941c9895339a7cff6496649cf5efa95f07b4b0d5960216","sha256:e9c0bf40de9838cfd0a833b89925e875e20b324d2794c2431138a43ba03a2021"],"state_sha256":"2ac3adecdcd8d16307225bcdade7f56b42c67ace4278517a635ffc3649cf3051"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lkY8AhjD7Vhbb64rK5amNMnnYmhLDFvVzFU+DGju/63UELnpG3kGD3apeP2YsQpF7ssvImO2XLfVG1MSqkVaCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:22:23.469705Z","bundle_sha256":"dee8d542db26aa786dd47f78563fd0cf90f52d763ac85f0a1f4fc8a191c53184"}}