{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CDPGG2YKZZRS3R3TUHZNO2APGI","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":"a599df410a26e8fa1e619b3857819cf708dc164940b4f6e1cb9eb9aed7826b1d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T12:44:15Z","title_canon_sha256":"8b249f938a1e66af756844ae70ad029a687cbacf5eff4b4482a7d6fbc0b2073c"},"schema_version":"1.0","source":{"id":"2506.00027","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00027","created_at":"2026-07-05T11:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00027v1","created_at":"2026-07-05T11:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00027","created_at":"2026-07-05T11:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"CDPGG2YKZZRS","created_at":"2026-07-05T11:12:58Z"},{"alias_kind":"pith_short_16","alias_value":"CDPGG2YKZZRS3R3T","created_at":"2026-07-05T11:12:58Z"},{"alias_kind":"pith_short_8","alias_value":"CDPGG2YK","created_at":"2026-07-05T11:12:58Z"}],"graph_snapshots":[{"event_id":"sha256:80d9b986c208f0473d0923c3891630ffd671fa115e852d90ccf89986e7ff94c0","target":"graph","created_at":"2026-07-05T11:12:58Z","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/2506.00027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in improving the reasoning capabilities of Large Language Models have underscored the efficacy of Process Reward Models (PRMs) in addressing intermediate errors through structured feedback mechanisms. This study analyzes PRMs from multiple perspectives, including training methodologies, scalability, and generalization capabilities. We investigate the interplay between pre-training and reward model training FLOPs to assess their influence on PRM efficiency and accuracy in complex reasoning tasks. Our analysis reveals a pattern of diminishing returns in performance with incre","authors_text":"Jingang Wang, Ruochen Zhou, Teng Xiao, Wei Wang, Xuesheng Yang, Yudong Wang, Zhengyu Chen, Zhifang Sui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T12:44:15Z","title":"From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00027","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":"sha256:62e7d03cafa945fc536dcf1d80f6cc41bb010172b4111ab078f0306714714d18","target":"record","created_at":"2026-07-05T11:12:58Z","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":"a599df410a26e8fa1e619b3857819cf708dc164940b4f6e1cb9eb9aed7826b1d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T12:44:15Z","title_canon_sha256":"8b249f938a1e66af756844ae70ad029a687cbacf5eff4b4482a7d6fbc0b2073c"},"schema_version":"1.0","source":{"id":"2506.00027","kind":"arxiv","version":1}},"canonical_sha256":"10de636b0ace632dc773a1f2d7680f321aa024de01026f5fa032915018bb29a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10de636b0ace632dc773a1f2d7680f321aa024de01026f5fa032915018bb29a8","first_computed_at":"2026-07-05T11:12:58.904301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:58.904301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GtcqowCLu1uvoEBohcyDEIJrnelJoV2I3TWXiHvjNy/ZueB53g1egytsFfpRmnaFKFAqPUuD33UiKPDEPIQGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:58.904813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00027","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62e7d03cafa945fc536dcf1d80f6cc41bb010172b4111ab078f0306714714d18","sha256:80d9b986c208f0473d0923c3891630ffd671fa115e852d90ccf89986e7ff94c0"],"state_sha256":"fc738e7672fe6a9b28233b4e4a3e35b7e1b8e30d3ad40cf0ed23c9a62fe9e5c0"}