{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QXDH4M6WEUAHZBAZDMGUETQIRW","short_pith_number":"pith:QXDH4M6W","canonical_record":{"source":{"id":"2404.05692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T17:18:04Z","cross_cats_sorted":[],"title_canon_sha256":"555267f58550ff6d46dbfc68b3dc01ac3bf714c53e41b8f7e354b389f13908f5","abstract_canon_sha256":"d8e6b3ada393c45cc796a74c4a2cde6b3f3a8b9bb2c050bf7c2a7c297c6d11fc"},"schema_version":"1.0"},"canonical_sha256":"85c67e33d625007c84191b0d424e088da9ca8b7749aae9159f23aaf124f22252","source":{"kind":"arxiv","id":"2404.05692","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05692","created_at":"2026-07-05T10:00:35Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05692v2","created_at":"2026-07-05T10:00:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05692","created_at":"2026-07-05T10:00:35Z"},{"alias_kind":"pith_short_12","alias_value":"QXDH4M6WEUAH","created_at":"2026-07-05T10:00:35Z"},{"alias_kind":"pith_short_16","alias_value":"QXDH4M6WEUAHZBAZ","created_at":"2026-07-05T10:00:35Z"},{"alias_kind":"pith_short_8","alias_value":"QXDH4M6W","created_at":"2026-07-05T10:00:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QXDH4M6WEUAHZBAZDMGUETQIRW","target":"record","payload":{"canonical_record":{"source":{"id":"2404.05692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T17:18:04Z","cross_cats_sorted":[],"title_canon_sha256":"555267f58550ff6d46dbfc68b3dc01ac3bf714c53e41b8f7e354b389f13908f5","abstract_canon_sha256":"d8e6b3ada393c45cc796a74c4a2cde6b3f3a8b9bb2c050bf7c2a7c297c6d11fc"},"schema_version":"1.0"},"canonical_sha256":"85c67e33d625007c84191b0d424e088da9ca8b7749aae9159f23aaf124f22252","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:35.857176Z","signature_b64":"NF0YBB1Ci8ocA4//gMop+J7+slIp6kRww1/5+/NaWxllRs1a3OpDj7zPQfYRhEJGs6Ngmml99HnQGcntZ+SKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85c67e33d625007c84191b0d424e088da9ca8b7749aae9159f23aaf124f22252","last_reissued_at":"2026-07-05T10:00:35.856703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:35.856703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.05692","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:00:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tqgFp89wsi7FKSWitMfdAMtx+pt03RJ0q47u7aVEVvF822OCjV7UKa5SWUvszj3SIKpv353ihTwVIicRsvT7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:35:21.718628Z"},"content_sha256":"e2c5a2da8c368c6d84ce04438943efd6902f9c6313ac88c504bc210c7bc574c9","schema_version":"1.0","event_id":"sha256:e2c5a2da8c368c6d84ce04438943efd6902f9c6313ac88c504bc210c7bc574c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QXDH4M6WEUAHZBAZDMGUETQIRW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Mathematical Reasoning Beyond Accuracy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pengfei Liu, Shijie Xia, Tongshuang Wu, Xuefeng Li, Yixin Liu","submitted_at":"2024-04-08T17:18:04Z","abstract_excerpt":"The leaderboard of Large Language Models (LLMs) in mathematical tasks has been continuously updated. However, the majority of evaluations focus solely on the final results, neglecting the quality of the intermediate steps. This oversight can mask underlying problems, such as logical errors or unnecessary steps in the reasoning process. To measure reasoning beyond final-answer accuracy, we introduce ReasonEval, a new methodology for evaluating the quality of reasoning steps. ReasonEval employs validity and redundancy to characterize the reasoning quality, as well as accompanying LLMs to assess "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05692","kind":"arxiv","version":2},"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/2404.05692/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":"2026-07-05T10:00:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/V5JhlvNpI6TVpYyCuu9k+RqCVOw9vmcrbhk6gJg0luin4tYRLwNRTWlk59kDD/W+lh3aR8DqDUKiXcgxFxECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:35:21.719511Z"},"content_sha256":"f1324f8dea58c7a13c0919a251b750482697fc4d78daff0328ba318973539504","schema_version":"1.0","event_id":"sha256:f1324f8dea58c7a13c0919a251b750482697fc4d78daff0328ba318973539504"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXDH4M6WEUAHZBAZDMGUETQIRW/bundle.json","state_url":"https://pith.science/pith/QXDH4M6WEUAHZBAZDMGUETQIRW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXDH4M6WEUAHZBAZDMGUETQIRW/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":"2026-08-10T07:35:21Z","links":{"resolver":"https://pith.science/pith/QXDH4M6WEUAHZBAZDMGUETQIRW","bundle":"https://pith.science/pith/QXDH4M6WEUAHZBAZDMGUETQIRW/bundle.json","state":"https://pith.science/pith/QXDH4M6WEUAHZBAZDMGUETQIRW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXDH4M6WEUAHZBAZDMGUETQIRW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QXDH4M6WEUAHZBAZDMGUETQIRW","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":"d8e6b3ada393c45cc796a74c4a2cde6b3f3a8b9bb2c050bf7c2a7c297c6d11fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T17:18:04Z","title_canon_sha256":"555267f58550ff6d46dbfc68b3dc01ac3bf714c53e41b8f7e354b389f13908f5"},"schema_version":"1.0","source":{"id":"2404.05692","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05692","created_at":"2026-07-05T10:00:35Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05692v2","created_at":"2026-07-05T10:00:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05692","created_at":"2026-07-05T10:00:35Z"},{"alias_kind":"pith_short_12","alias_value":"QXDH4M6WEUAH","created_at":"2026-07-05T10:00:35Z"},{"alias_kind":"pith_short_16","alias_value":"QXDH4M6WEUAHZBAZ","created_at":"2026-07-05T10:00:35Z"},{"alias_kind":"pith_short_8","alias_value":"QXDH4M6W","created_at":"2026-07-05T10:00:35Z"}],"graph_snapshots":[{"event_id":"sha256:f1324f8dea58c7a13c0919a251b750482697fc4d78daff0328ba318973539504","target":"graph","created_at":"2026-07-05T10:00:35Z","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/2404.05692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The leaderboard of Large Language Models (LLMs) in mathematical tasks has been continuously updated. However, the majority of evaluations focus solely on the final results, neglecting the quality of the intermediate steps. This oversight can mask underlying problems, such as logical errors or unnecessary steps in the reasoning process. To measure reasoning beyond final-answer accuracy, we introduce ReasonEval, a new methodology for evaluating the quality of reasoning steps. ReasonEval employs validity and redundancy to characterize the reasoning quality, as well as accompanying LLMs to assess ","authors_text":"Pengfei Liu, Shijie Xia, Tongshuang Wu, Xuefeng Li, Yixin Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T17:18:04Z","title":"Evaluating Mathematical Reasoning Beyond Accuracy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05692","kind":"arxiv","version":2},"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:e2c5a2da8c368c6d84ce04438943efd6902f9c6313ac88c504bc210c7bc574c9","target":"record","created_at":"2026-07-05T10:00:35Z","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":"d8e6b3ada393c45cc796a74c4a2cde6b3f3a8b9bb2c050bf7c2a7c297c6d11fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T17:18:04Z","title_canon_sha256":"555267f58550ff6d46dbfc68b3dc01ac3bf714c53e41b8f7e354b389f13908f5"},"schema_version":"1.0","source":{"id":"2404.05692","kind":"arxiv","version":2}},"canonical_sha256":"85c67e33d625007c84191b0d424e088da9ca8b7749aae9159f23aaf124f22252","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85c67e33d625007c84191b0d424e088da9ca8b7749aae9159f23aaf124f22252","first_computed_at":"2026-07-05T10:00:35.856703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:35.856703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NF0YBB1Ci8ocA4//gMop+J7+slIp6kRww1/5+/NaWxllRs1a3OpDj7zPQfYRhEJGs6Ngmml99HnQGcntZ+SKCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:35.857176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05692","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2c5a2da8c368c6d84ce04438943efd6902f9c6313ac88c504bc210c7bc574c9","sha256:f1324f8dea58c7a13c0919a251b750482697fc4d78daff0328ba318973539504"],"state_sha256":"117316c75eb5859e0bc1fe3a1f50fe536578408dd70aa06eb1fb8ca45e371a0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R1v9OGVx9eLCq/pE3ImPhEj3R8pKNwv7k6rrrsiVvr3VeUQc7PWw0ugevKg2dOakfWgSi/3Iwp3/E9OhM0wIAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:35:21.727357Z","bundle_sha256":"6112d3fc4ab4f03cf9ec7b8be25e3d3a40831ee995d207af51c742b232f43a4e"}}