{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZGXPLEYEGD7RFJFDZ2UFCCRAMV","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":"68c37ebb1dd5735f5986d4b1842284fbc0acad002fe35675d5554a07c154a2a9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-06T16:31:45Z","title_canon_sha256":"f9d73ad938a531752f3dba936d52f90121e4e948b7d3c9469711c2c13c68ee29"},"schema_version":"1.0","source":{"id":"2501.03124","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03124","created_at":"2026-07-05T11:28:33Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03124v5","created_at":"2026-07-05T11:28:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03124","created_at":"2026-07-05T11:28:33Z"},{"alias_kind":"pith_short_12","alias_value":"ZGXPLEYEGD7R","created_at":"2026-07-05T11:28:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZGXPLEYEGD7RFJFD","created_at":"2026-07-05T11:28:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZGXPLEYE","created_at":"2026-07-05T11:28:33Z"}],"graph_snapshots":[{"event_id":"sha256:8716c3aa15c6b39e195d284ff135abe276e3ab173fa4a6456e404ba191b5a8bc","target":"graph","created_at":"2026-07-05T11:28:33Z","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/2501.03124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Process-level Reward Models (PRMs) are crucial for complex reasoning and decision-making tasks, where each intermediate step plays an important role in the reasoning process. Since language models are prone to various types of errors during the reasoning process, PRMs are required to possess nuanced capabilities for detecting various implicit error types in real-world scenarios. However, current benchmarks primarily focus on step correctness, failing to evaluate PRMs' performance systematically. To address this gap, we introduce PRMBench, a process-level benchmark specifically designed to asse","authors_text":"Jiawei Zhou, Mingyang Song, Xiaoye Qu, Yu Cheng, Zhaochen Su","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-06T16:31:45Z","title":"PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03124","kind":"arxiv","version":5},"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":"sha256:03b4a32071e3fa4000e28a2df59c9e4bf8a0a4869115902961971c218d8e9986","target":"record","created_at":"2026-07-05T11:28:33Z","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":"68c37ebb1dd5735f5986d4b1842284fbc0acad002fe35675d5554a07c154a2a9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-06T16:31:45Z","title_canon_sha256":"f9d73ad938a531752f3dba936d52f90121e4e948b7d3c9469711c2c13c68ee29"},"schema_version":"1.0","source":{"id":"2501.03124","kind":"arxiv","version":5}},"canonical_sha256":"c9aef5930430ff12a4a3cea8510a20656b8712636b9d73137463cfb487f2d069","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9aef5930430ff12a4a3cea8510a20656b8712636b9d73137463cfb487f2d069","first_computed_at":"2026-07-05T11:28:33.281468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:33.281468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gpa79jHaQsPrDZ5taboEHl1LJU3PfL3lzcifncUc/ahwn+E8/lykhAz3t8NVw7oZUXU7A4RzdmPMOymOWbyGDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:33.281986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03124","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03b4a32071e3fa4000e28a2df59c9e4bf8a0a4869115902961971c218d8e9986","sha256:8716c3aa15c6b39e195d284ff135abe276e3ab173fa4a6456e404ba191b5a8bc"],"state_sha256":"18d17ae1958d5a49818a638fdc78852ec39999c4d421e337242766f7cf8bef97"}