{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FJKUVUJZD3QZL6MJXZOW4XCO4B","short_pith_number":"pith:FJKUVUJZ","canonical_record":{"source":{"id":"2406.14024","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T06:42:27Z","cross_cats_sorted":[],"title_canon_sha256":"f5426c0de810f750740625924d08e03f70619f796dfdc0715022a06cd8f6b886","abstract_canon_sha256":"2ebf186f5ec3221c3197ee932ca9ec9eca2371997187e17bf53ec34c652c9012"},"schema_version":"1.0"},"canonical_sha256":"2a554ad1391ee195f989be5d6e5c4ee058d137c49a9a9779677065ddf7182ec4","source":{"kind":"arxiv","id":"2406.14024","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14024","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14024v4","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14024","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"pith_short_12","alias_value":"FJKUVUJZD3QZ","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"pith_short_16","alias_value":"FJKUVUJZD3QZL6MJ","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"pith_short_8","alias_value":"FJKUVUJZ","created_at":"2026-07-05T09:22:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FJKUVUJZD3QZL6MJXZOW4XCO4B","target":"record","payload":{"canonical_record":{"source":{"id":"2406.14024","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T06:42:27Z","cross_cats_sorted":[],"title_canon_sha256":"f5426c0de810f750740625924d08e03f70619f796dfdc0715022a06cd8f6b886","abstract_canon_sha256":"2ebf186f5ec3221c3197ee932ca9ec9eca2371997187e17bf53ec34c652c9012"},"schema_version":"1.0"},"canonical_sha256":"2a554ad1391ee195f989be5d6e5c4ee058d137c49a9a9779677065ddf7182ec4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:19.839780Z","signature_b64":"yztuMv0uj+I0c1ZLCInEV4iKYJcLaAC5ZBIgkFdXQj1wG9m9MBAQPIJr7llsOx5S7pI5aKqs2N4CyCaWd+3dBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a554ad1391ee195f989be5d6e5c4ee058d137c49a9a9779677065ddf7182ec4","last_reissued_at":"2026-07-05T09:22:19.839275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:19.839275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.14024","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":"2026-07-05T09:22:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hKgR0WviDYJ1sgPTZTmireYT97uVvVeaMa4yWMFVg0T6azrjfv4xnju6JIYnisbroHLjat41YHIGWXuZdZ9zAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:45:49.345624Z"},"content_sha256":"0097cfc90a05223cd1a16221c5f0d1b13f22bd79b51879ce7de95982f9706f95","schema_version":"1.0","event_id":"sha256:0097cfc90a05223cd1a16221c5f0d1b13f22bd79b51879ce7de95982f9706f95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FJKUVUJZD3QZL6MJXZOW4XCO4B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baobao Chang, Bofei Gao, Ce Zheng, Chang Zhou, Dayiheng Liu, Junjie Hu, Keming Lu, Peiyi Wang, Runji Lin, Runxin Xu, Tianyu Liu, Wen Xiao, Zefan Cai","submitted_at":"2024-06-20T06:42:27Z","abstract_excerpt":"In recent progress, mathematical verifiers have achieved success in mathematical reasoning tasks by validating the correctness of solutions generated by policy models. However, existing verifiers are trained with binary classification labels, which are not informative enough for the model to accurately assess the solutions. To mitigate the aforementioned insufficiency of binary labels, we introduce step-wise natural language feedback as rationale labels, that is, the correctness of each step and the detailed explanations. In this paper, we propose Math-Minos, a natural language feedback-enhanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14024","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/2406.14024/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":"2026-07-05T09:22:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BYgNV21AzUADYaoCccKlX6lP/mQAbMpd4qhp6Mbj5v7TqfN9qPsxuWutoi0daf8EAjk1TT5hTu9kzkH/9IyZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:45:49.346563Z"},"content_sha256":"659d1989e161ee4874f3eb9ca6f104e2c0ad6bd8469c2d3cc202b9acf389cea7","schema_version":"1.0","event_id":"sha256:659d1989e161ee4874f3eb9ca6f104e2c0ad6bd8469c2d3cc202b9acf389cea7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FJKUVUJZD3QZL6MJXZOW4XCO4B/bundle.json","state_url":"https://pith.science/pith/FJKUVUJZD3QZL6MJXZOW4XCO4B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FJKUVUJZD3QZL6MJXZOW4XCO4B/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":"2026-08-15T19:45:49Z","links":{"resolver":"https://pith.science/pith/FJKUVUJZD3QZL6MJXZOW4XCO4B","bundle":"https://pith.science/pith/FJKUVUJZD3QZL6MJXZOW4XCO4B/bundle.json","state":"https://pith.science/pith/FJKUVUJZD3QZL6MJXZOW4XCO4B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FJKUVUJZD3QZL6MJXZOW4XCO4B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FJKUVUJZD3QZL6MJXZOW4XCO4B","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":"2ebf186f5ec3221c3197ee932ca9ec9eca2371997187e17bf53ec34c652c9012","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T06:42:27Z","title_canon_sha256":"f5426c0de810f750740625924d08e03f70619f796dfdc0715022a06cd8f6b886"},"schema_version":"1.0","source":{"id":"2406.14024","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14024","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14024v4","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14024","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"pith_short_12","alias_value":"FJKUVUJZD3QZ","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"pith_short_16","alias_value":"FJKUVUJZD3QZL6MJ","created_at":"2026-07-05T09:22:19Z"},{"alias_kind":"pith_short_8","alias_value":"FJKUVUJZ","created_at":"2026-07-05T09:22:19Z"}],"graph_snapshots":[{"event_id":"sha256:659d1989e161ee4874f3eb9ca6f104e2c0ad6bd8469c2d3cc202b9acf389cea7","target":"graph","created_at":"2026-07-05T09:22:19Z","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/2406.14024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent progress, mathematical verifiers have achieved success in mathematical reasoning tasks by validating the correctness of solutions generated by policy models. However, existing verifiers are trained with binary classification labels, which are not informative enough for the model to accurately assess the solutions. To mitigate the aforementioned insufficiency of binary labels, we introduce step-wise natural language feedback as rationale labels, that is, the correctness of each step and the detailed explanations. In this paper, we propose Math-Minos, a natural language feedback-enhanc","authors_text":"Baobao Chang, Bofei Gao, Ce Zheng, Chang Zhou, Dayiheng Liu, Junjie Hu, Keming Lu, Peiyi Wang, Runji Lin, Runxin Xu, Tianyu Liu, Wen Xiao, Zefan Cai","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T06:42:27Z","title":"LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14024","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":"sha256:0097cfc90a05223cd1a16221c5f0d1b13f22bd79b51879ce7de95982f9706f95","target":"record","created_at":"2026-07-05T09:22:19Z","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":"2ebf186f5ec3221c3197ee932ca9ec9eca2371997187e17bf53ec34c652c9012","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-20T06:42:27Z","title_canon_sha256":"f5426c0de810f750740625924d08e03f70619f796dfdc0715022a06cd8f6b886"},"schema_version":"1.0","source":{"id":"2406.14024","kind":"arxiv","version":4}},"canonical_sha256":"2a554ad1391ee195f989be5d6e5c4ee058d137c49a9a9779677065ddf7182ec4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a554ad1391ee195f989be5d6e5c4ee058d137c49a9a9779677065ddf7182ec4","first_computed_at":"2026-07-05T09:22:19.839275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:19.839275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yztuMv0uj+I0c1ZLCInEV4iKYJcLaAC5ZBIgkFdXQj1wG9m9MBAQPIJr7llsOx5S7pI5aKqs2N4CyCaWd+3dBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:19.839780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14024","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0097cfc90a05223cd1a16221c5f0d1b13f22bd79b51879ce7de95982f9706f95","sha256:659d1989e161ee4874f3eb9ca6f104e2c0ad6bd8469c2d3cc202b9acf389cea7"],"state_sha256":"7e5e8384e2197658d7ba01b39ef4eceadbc5671e4616df574a347cfaf2de5013"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TXe3D3HuEXrxRD9XQur/LeyY1ABtQbZiYoa2nLb68ksk1+85U+3oln/pXsHlWPNIkHVR6LpZdjU1vXBo/wv4Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:45:49.351104Z","bundle_sha256":"ca83ff61ab2ba4dd783cdf60c71cb63d19786edf090610ef5422487f9eb51c0c"}}