{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FIHGPDF7BULGDLCFZZLFEGAHD2","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":"12a6687911ddf419c05e522e0096e57c78fd7b2b5b9c2d4888b4deac7af916ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-20T14:12:05Z","title_canon_sha256":"46ab7c6d2d0d1649b0d9d0d78a6abb708871ba118a8176bb1e4ca0dcffbff8fe"},"schema_version":"1.0","source":{"id":"2505.14391","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14391","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14391v1","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14391","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"FIHGPDF7BULG","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"FIHGPDF7BULGDLCF","created_at":"2026-07-05T11:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"FIHGPDF7","created_at":"2026-07-05T11:06:00Z"}],"graph_snapshots":[{"event_id":"sha256:f24790dd2e71101bd80e272c809793ed0406084e205e1e6dd908c9e8a44a3efa","target":"graph","created_at":"2026-07-05T11:06:00Z","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/2505.14391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many studies focus on data annotation techniques for training effective PRMs. However, current methods encounter a significant issue when applied to long CoT reasoning processes: they tend to focus solely on the first incorrect step and all preceding steps, assuming that all subsequent steps are incorrect. These methods overlook the unique self-correction and reflection mechanisms inherent in long CoT, where correct reasoning steps may still occur after initial reasoning mistakes. To address this issue, we propose a novel data annotation method for PRMs specifically designed to score the long ","authors_text":"Chenghua He, Daxin Jiang, Linjing Li, Qiyue Yin, Shihong Deng, Xiaowen Shi, Zhaohui Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-20T14:12:05Z","title":"Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14391","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:eb3b53148da3bad21ea88febbd0f28b65366eb6ac491a18f4a569b0625a8809e","target":"record","created_at":"2026-07-05T11:06:00Z","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":"12a6687911ddf419c05e522e0096e57c78fd7b2b5b9c2d4888b4deac7af916ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-20T14:12:05Z","title_canon_sha256":"46ab7c6d2d0d1649b0d9d0d78a6abb708871ba118a8176bb1e4ca0dcffbff8fe"},"schema_version":"1.0","source":{"id":"2505.14391","kind":"arxiv","version":1}},"canonical_sha256":"2a0e678cbf0d1661ac45ce565218071eb339ef8401719792762fe4592b42e4bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a0e678cbf0d1661ac45ce565218071eb339ef8401719792762fe4592b42e4bd","first_computed_at":"2026-07-05T11:06:00.769747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:00.769747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d6SeNAwwq7O8H6IBpoecCXmOL76VMA1PdhTD/Xrk+wXgPZV9ADWpW0Gwx9a0+DK3BjgW2v5JD4Y4ONnCRhTFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:00.770174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14391","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb3b53148da3bad21ea88febbd0f28b65366eb6ac491a18f4a569b0625a8809e","sha256:f24790dd2e71101bd80e272c809793ed0406084e205e1e6dd908c9e8a44a3efa"],"state_sha256":"524422b93a0dfb255ad3c3a3e8bd45b64e401513a655274820eb14a15125682f"}