{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BIT5NWROT7FPQFCJVBFCPPTEXN","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":"1496746744ed260aa72cada00113fcb5e2c1d95ebd0b156c1e1f4fb32483195d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-04T08:18:46Z","title_canon_sha256":"9dc1d201bb667db8acfc6a25783fd8b6e422447460282cf2db9f1b9018467198"},"schema_version":"1.0","source":{"id":"2503.02382","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02382","created_at":"2026-07-05T11:41:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02382v2","created_at":"2026-07-05T11:41:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02382","created_at":"2026-07-05T11:41:39Z"},{"alias_kind":"pith_short_12","alias_value":"BIT5NWROT7FP","created_at":"2026-07-05T11:41:39Z"},{"alias_kind":"pith_short_16","alias_value":"BIT5NWROT7FPQFCJ","created_at":"2026-07-05T11:41:39Z"},{"alias_kind":"pith_short_8","alias_value":"BIT5NWRO","created_at":"2026-07-05T11:41:39Z"}],"graph_snapshots":[{"event_id":"sha256:7cbf0984603f62e0435baa7d7557a699ad3ef49c67b9f2868def8776123d8202","target":"graph","created_at":"2026-07-05T11:41:39Z","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/2503.02382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enhancing the mathematical reasoning capabilities of Large Language Models (LLMs) is of great scientific and practical significance. Researchers typically employ process-supervised reward models (PRMs) to guide the reasoning process, effectively improving the models' reasoning abilities. However, existing methods for constructing process supervision training data, such as manual annotation and per-step Monte Carlo estimation, are often costly or suffer from poor quality. To address these challenges, this paper introduces a framework called EpicPRM, which annotates each intermediate reasoning s","authors_text":"Fuwei Cui, Jiajun Zhang, Qianlong Du, Wei Sun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-04T08:18:46Z","title":"An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02382","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":"sha256:0fe55b1d628d403f8a49dc8b5c26402b5fb13a49b3e24d725a251e582527e295","target":"record","created_at":"2026-07-05T11:41:39Z","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":"1496746744ed260aa72cada00113fcb5e2c1d95ebd0b156c1e1f4fb32483195d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-04T08:18:46Z","title_canon_sha256":"9dc1d201bb667db8acfc6a25783fd8b6e422447460282cf2db9f1b9018467198"},"schema_version":"1.0","source":{"id":"2503.02382","kind":"arxiv","version":2}},"canonical_sha256":"0a27d6da2e9fcaf81449a84a27be64bb6e3e8541881900b0a23c77c455abf1b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a27d6da2e9fcaf81449a84a27be64bb6e3e8541881900b0a23c77c455abf1b7","first_computed_at":"2026-07-05T11:41:39.790869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:39.790869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I2h8RS9WPjtCsTkUU5h9KOWeiHZGasihs/e2wr8lRcW8/3o0TnspBKgsqL9WnLe7KThMhHnha6erx5/Y1QYFAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:39.791373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.02382","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fe55b1d628d403f8a49dc8b5c26402b5fb13a49b3e24d725a251e582527e295","sha256:7cbf0984603f62e0435baa7d7557a699ad3ef49c67b9f2868def8776123d8202"],"state_sha256":"a3a5b9701071b69578c35bb466dfda58504a8a6c09ba157398b9db029d470187"}