{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M7JL5RCVY374DECJSAXCXOVQKN","short_pith_number":"pith:M7JL5RCV","canonical_record":{"source":{"id":"2411.16579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T17:11:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"10ce028b2398eb7b64e667a3aba712cf3d746e744dd6082af4c04f4c12380a50","abstract_canon_sha256":"1cf0eeb87895fd0f978763b636d9d45ac8eeeae7df5efe2ee0221a7c84c97401"},"schema_version":"1.0"},"canonical_sha256":"67d2bec455c6ffc19049902e2bbab0536491fac20e50481cfc1643df1b1bbdcf","source":{"kind":"arxiv","id":"2411.16579","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16579","created_at":"2026-07-05T09:40:11Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16579v1","created_at":"2026-07-05T09:40:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16579","created_at":"2026-07-05T09:40:11Z"},{"alias_kind":"pith_short_12","alias_value":"M7JL5RCVY374","created_at":"2026-07-05T09:40:11Z"},{"alias_kind":"pith_short_16","alias_value":"M7JL5RCVY374DECJ","created_at":"2026-07-05T09:40:11Z"},{"alias_kind":"pith_short_8","alias_value":"M7JL5RCV","created_at":"2026-07-05T09:40:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M7JL5RCVY374DECJSAXCXOVQKN","target":"record","payload":{"canonical_record":{"source":{"id":"2411.16579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T17:11:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"10ce028b2398eb7b64e667a3aba712cf3d746e744dd6082af4c04f4c12380a50","abstract_canon_sha256":"1cf0eeb87895fd0f978763b636d9d45ac8eeeae7df5efe2ee0221a7c84c97401"},"schema_version":"1.0"},"canonical_sha256":"67d2bec455c6ffc19049902e2bbab0536491fac20e50481cfc1643df1b1bbdcf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:11.504635Z","signature_b64":"l40IxX22jQqiSEGGrH2hOkbN2HHPe8X8kO35smevfDrYj1vAW1pxRYkEaa5FwHOJ+r2mS0VT5K+PvXsjL1opDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67d2bec455c6ffc19049902e2bbab0536491fac20e50481cfc1643df1b1bbdcf","last_reissued_at":"2026-07-05T09:40:11.504152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:11.504152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.16579","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:40:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5CqZXbF+G/ktX9KNGHw6HrrRM32Cxt/7pgX3kYiYgdqZlvGs5o2+MPRi8JmJ6Ta8tEcVe4ZfCF40lnsXg0gEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:50:22.696073Z"},"content_sha256":"abb62ef5f6367f9e46d855ffdfca8165c5e446ebf144e2875a07717ff8b8145d","schema_version":"1.0","event_id":"sha256:abb62ef5f6367f9e46d855ffdfca8165c5e446ebf144e2875a07717ff8b8145d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M7JL5RCVY374DECJSAXCXOVQKN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Boyang Hong, Dingwen Yang, Guanyu Li, Jiafu Tang, Jingang Wang, Jixuan Huang, Qi Zhang, Rongxiang Weng, Rui Zheng, Shihan Do, Tao Gui, Tao Ji, Wei He, Wenyu Zhan, Xiao Wang, Xiaowei Shi, Xipeng Qiu, Xuanjing Huang, Xunliang Cai, Yitao Zhai, Yiwen Ding, Yu-Gang Jiang, Zhiheng Xi, Zuxuan Wu","submitted_at":"2024-11-25T17:11:54Z","abstract_excerpt":"Training large language models (LLMs) to spend more time thinking and reflection before responding is crucial for effectively solving complex reasoning tasks in fields such as science, coding, and mathematics. However, the effectiveness of mechanisms like self-reflection and self-correction depends on the model's capacity to accurately assess its own performance, which can be limited by factors such as initial accuracy, question difficulty, and the lack of external feedback. In this paper, we delve into a two-player paradigm that separates the roles of reasoning and critique models, where the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16579","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/2411.16579/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":"2026-07-05T09:40:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jMFoPve37DKqkUIvPvk4vJ/vCKFEfyqCeVvg+mhgyFgJzipfJu3Qw5+PxLY+dpOdafrJV3ZQEajB2kmJDdEyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:50:22.696599Z"},"content_sha256":"b27cd5decd3a9916c1230a965b3e85203f04678e59bce99c34f34357298a8ccf","schema_version":"1.0","event_id":"sha256:b27cd5decd3a9916c1230a965b3e85203f04678e59bce99c34f34357298a8ccf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7JL5RCVY374DECJSAXCXOVQKN/bundle.json","state_url":"https://pith.science/pith/M7JL5RCVY374DECJSAXCXOVQKN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7JL5RCVY374DECJSAXCXOVQKN/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":"2026-08-05T19:50:22Z","links":{"resolver":"https://pith.science/pith/M7JL5RCVY374DECJSAXCXOVQKN","bundle":"https://pith.science/pith/M7JL5RCVY374DECJSAXCXOVQKN/bundle.json","state":"https://pith.science/pith/M7JL5RCVY374DECJSAXCXOVQKN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7JL5RCVY374DECJSAXCXOVQKN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M7JL5RCVY374DECJSAXCXOVQKN","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":"1cf0eeb87895fd0f978763b636d9d45ac8eeeae7df5efe2ee0221a7c84c97401","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T17:11:54Z","title_canon_sha256":"10ce028b2398eb7b64e667a3aba712cf3d746e744dd6082af4c04f4c12380a50"},"schema_version":"1.0","source":{"id":"2411.16579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16579","created_at":"2026-07-05T09:40:11Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16579v1","created_at":"2026-07-05T09:40:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16579","created_at":"2026-07-05T09:40:11Z"},{"alias_kind":"pith_short_12","alias_value":"M7JL5RCVY374","created_at":"2026-07-05T09:40:11Z"},{"alias_kind":"pith_short_16","alias_value":"M7JL5RCVY374DECJ","created_at":"2026-07-05T09:40:11Z"},{"alias_kind":"pith_short_8","alias_value":"M7JL5RCV","created_at":"2026-07-05T09:40:11Z"}],"graph_snapshots":[{"event_id":"sha256:b27cd5decd3a9916c1230a965b3e85203f04678e59bce99c34f34357298a8ccf","target":"graph","created_at":"2026-07-05T09:40:11Z","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/2411.16579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large language models (LLMs) to spend more time thinking and reflection before responding is crucial for effectively solving complex reasoning tasks in fields such as science, coding, and mathematics. However, the effectiveness of mechanisms like self-reflection and self-correction depends on the model's capacity to accurately assess its own performance, which can be limited by factors such as initial accuracy, question difficulty, and the lack of external feedback. In this paper, we delve into a two-player paradigm that separates the roles of reasoning and critique models, where the ","authors_text":"Boyang Hong, Dingwen Yang, Guanyu Li, Jiafu Tang, Jingang Wang, Jixuan Huang, Qi Zhang, Rongxiang Weng, Rui Zheng, Shihan Do, Tao Gui, Tao Ji, Wei He, Wenyu Zhan, Xiao Wang, Xiaowei Shi, Xipeng Qiu, Xuanjing Huang, Xunliang Cai, Yitao Zhai, Yiwen Ding, Yu-Gang Jiang, Zhiheng Xi, Zuxuan Wu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T17:11:54Z","title":"Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16579","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:abb62ef5f6367f9e46d855ffdfca8165c5e446ebf144e2875a07717ff8b8145d","target":"record","created_at":"2026-07-05T09:40:11Z","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":"1cf0eeb87895fd0f978763b636d9d45ac8eeeae7df5efe2ee0221a7c84c97401","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-25T17:11:54Z","title_canon_sha256":"10ce028b2398eb7b64e667a3aba712cf3d746e744dd6082af4c04f4c12380a50"},"schema_version":"1.0","source":{"id":"2411.16579","kind":"arxiv","version":1}},"canonical_sha256":"67d2bec455c6ffc19049902e2bbab0536491fac20e50481cfc1643df1b1bbdcf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67d2bec455c6ffc19049902e2bbab0536491fac20e50481cfc1643df1b1bbdcf","first_computed_at":"2026-07-05T09:40:11.504152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:11.504152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l40IxX22jQqiSEGGrH2hOkbN2HHPe8X8kO35smevfDrYj1vAW1pxRYkEaa5FwHOJ+r2mS0VT5K+PvXsjL1opDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:11.504635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abb62ef5f6367f9e46d855ffdfca8165c5e446ebf144e2875a07717ff8b8145d","sha256:b27cd5decd3a9916c1230a965b3e85203f04678e59bce99c34f34357298a8ccf"],"state_sha256":"d18f9b5c0c182e88a7872505a2d892bb02c499f1d64f50c51bba8a6691306948"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TxLQ1ZOu5Sglv5mtdEAC5PrYxTrJ9iakbNn4iG/AO+9QqvXywCfsZKozg88C2O4ZqlnTAtGeZZJG+sqDddrFAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T19:50:22.710982Z","bundle_sha256":"200e4f5c6fd1b4b93a005e4ad8e15a653b8e0ad6bcb4ea82168ad1e311ae8a3e"}}