{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V3Q3XLNRFYKFJOWY6IZQT77ZQI","short_pith_number":"pith:V3Q3XLNR","canonical_record":{"source":{"id":"2504.00891","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T15:21:05Z","cross_cats_sorted":[],"title_canon_sha256":"bcbc2a5427cad23b4cec57930f6bbd411cb13ad72da6eebc05c129544d7e6385","abstract_canon_sha256":"51532361c7ef11937e0e2c1b06125c7490e05dd3f7a29f4a85448ab2846959d5"},"schema_version":"1.0"},"canonical_sha256":"aee1bbadb12e1454bad8f23309fff98232143c53bae5321965485ec07ff25e94","source":{"kind":"arxiv","id":"2504.00891","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00891","created_at":"2026-07-05T10:44:44Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00891v2","created_at":"2026-07-05T10:44:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00891","created_at":"2026-07-05T10:44:44Z"},{"alias_kind":"pith_short_12","alias_value":"V3Q3XLNRFYKF","created_at":"2026-07-05T10:44:44Z"},{"alias_kind":"pith_short_16","alias_value":"V3Q3XLNRFYKFJOWY","created_at":"2026-07-05T10:44:44Z"},{"alias_kind":"pith_short_8","alias_value":"V3Q3XLNR","created_at":"2026-07-05T10:44:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V3Q3XLNRFYKFJOWY6IZQT77ZQI","target":"record","payload":{"canonical_record":{"source":{"id":"2504.00891","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T15:21:05Z","cross_cats_sorted":[],"title_canon_sha256":"bcbc2a5427cad23b4cec57930f6bbd411cb13ad72da6eebc05c129544d7e6385","abstract_canon_sha256":"51532361c7ef11937e0e2c1b06125c7490e05dd3f7a29f4a85448ab2846959d5"},"schema_version":"1.0"},"canonical_sha256":"aee1bbadb12e1454bad8f23309fff98232143c53bae5321965485ec07ff25e94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:44.985405Z","signature_b64":"sDCDJinGKgoBkw6s/X/5WHHtoLYmDbnzUyuIDQxWIgYuA5MGCkOq7Ttd6H6raTrizuEYQ4zc4ZrI79+gQDnECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aee1bbadb12e1454bad8f23309fff98232143c53bae5321965485ec07ff25e94","last_reissued_at":"2026-07-05T10:44:44.984890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:44.984890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.00891","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":"2026-07-05T10:44:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bFFbpRpOy2GzSocTIjBxqGf4/5Tuwqu5YH4VVe2sRrHpqtUKJ1OiG+n+AQ1EKJ5tPl7Vvt200jLQJtCfldeCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:10:24.062384Z"},"content_sha256":"b058a65085ae810b1c46749f0c15f27590b1411a7aaf40fd418bdcbcde64b331","schema_version":"1.0","event_id":"sha256:b058a65085ae810b1c46749f0c15f27590b1411a7aaf40fd418bdcbcde64b331"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V3Q3XLNRFYKFJOWY6IZQT77ZQI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Biqing Qi, Bowen Zhou, Dong Li, Jiafei Lyu, Jian Zhao, Junqi Gao, Kaiyan Zhang, Runze Liu, Xiu Li, Zhimu Zhou, Zhouyi Qian","submitted_at":"2025-04-01T15:21:05Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have shown that it is promising to utilize Process Reward Models (PRMs) as verifiers to enhance the performance of LLMs. However, current PRMs face three key challenges: (1) limited process supervision and generalization capabilities, (2) dependence on scalar value prediction without leveraging the generative abilities of LLMs, and (3) inability to scale the test-time compute of PRMs. In this work, we introduce GenPRM, a generative process reward model that performs explicit Chain-of-Thought (CoT) reasoning with code verification before provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00891","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/2504.00891/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":"2026-07-05T10:44:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zxFprOoc49yTnCHihkQ8DXNBKl56AaoLY2hVYS8FsTxHXztaLWXa5utQo6j4kl/3cdg6fDXt5+UBbvRKZBkBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:10:24.062905Z"},"content_sha256":"1a3629666764c7a9a6cb6a547ac6d123a60ac3a2d51e782406f2eee0e40bb525","schema_version":"1.0","event_id":"sha256:1a3629666764c7a9a6cb6a547ac6d123a60ac3a2d51e782406f2eee0e40bb525"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V3Q3XLNRFYKFJOWY6IZQT77ZQI/bundle.json","state_url":"https://pith.science/pith/V3Q3XLNRFYKFJOWY6IZQT77ZQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V3Q3XLNRFYKFJOWY6IZQT77ZQI/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":"2026-08-22T00:10:24Z","links":{"resolver":"https://pith.science/pith/V3Q3XLNRFYKFJOWY6IZQT77ZQI","bundle":"https://pith.science/pith/V3Q3XLNRFYKFJOWY6IZQT77ZQI/bundle.json","state":"https://pith.science/pith/V3Q3XLNRFYKFJOWY6IZQT77ZQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V3Q3XLNRFYKFJOWY6IZQT77ZQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V3Q3XLNRFYKFJOWY6IZQT77ZQI","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":"51532361c7ef11937e0e2c1b06125c7490e05dd3f7a29f4a85448ab2846959d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T15:21:05Z","title_canon_sha256":"bcbc2a5427cad23b4cec57930f6bbd411cb13ad72da6eebc05c129544d7e6385"},"schema_version":"1.0","source":{"id":"2504.00891","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.00891","created_at":"2026-07-05T10:44:44Z"},{"alias_kind":"arxiv_version","alias_value":"2504.00891v2","created_at":"2026-07-05T10:44:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00891","created_at":"2026-07-05T10:44:44Z"},{"alias_kind":"pith_short_12","alias_value":"V3Q3XLNRFYKF","created_at":"2026-07-05T10:44:44Z"},{"alias_kind":"pith_short_16","alias_value":"V3Q3XLNRFYKFJOWY","created_at":"2026-07-05T10:44:44Z"},{"alias_kind":"pith_short_8","alias_value":"V3Q3XLNR","created_at":"2026-07-05T10:44:44Z"}],"graph_snapshots":[{"event_id":"sha256:1a3629666764c7a9a6cb6a547ac6d123a60ac3a2d51e782406f2eee0e40bb525","target":"graph","created_at":"2026-07-05T10:44:44Z","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/2504.00891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have shown that it is promising to utilize Process Reward Models (PRMs) as verifiers to enhance the performance of LLMs. However, current PRMs face three key challenges: (1) limited process supervision and generalization capabilities, (2) dependence on scalar value prediction without leveraging the generative abilities of LLMs, and (3) inability to scale the test-time compute of PRMs. In this work, we introduce GenPRM, a generative process reward model that performs explicit Chain-of-Thought (CoT) reasoning with code verification before provi","authors_text":"Biqing Qi, Bowen Zhou, Dong Li, Jiafei Lyu, Jian Zhao, Junqi Gao, Kaiyan Zhang, Runze Liu, Xiu Li, Zhimu Zhou, Zhouyi Qian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T15:21:05Z","title":"GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00891","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:b058a65085ae810b1c46749f0c15f27590b1411a7aaf40fd418bdcbcde64b331","target":"record","created_at":"2026-07-05T10:44:44Z","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":"51532361c7ef11937e0e2c1b06125c7490e05dd3f7a29f4a85448ab2846959d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T15:21:05Z","title_canon_sha256":"bcbc2a5427cad23b4cec57930f6bbd411cb13ad72da6eebc05c129544d7e6385"},"schema_version":"1.0","source":{"id":"2504.00891","kind":"arxiv","version":2}},"canonical_sha256":"aee1bbadb12e1454bad8f23309fff98232143c53bae5321965485ec07ff25e94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aee1bbadb12e1454bad8f23309fff98232143c53bae5321965485ec07ff25e94","first_computed_at":"2026-07-05T10:44:44.984890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:44.984890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sDCDJinGKgoBkw6s/X/5WHHtoLYmDbnzUyuIDQxWIgYuA5MGCkOq7Ttd6H6raTrizuEYQ4zc4ZrI79+gQDnECw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:44.985405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.00891","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b058a65085ae810b1c46749f0c15f27590b1411a7aaf40fd418bdcbcde64b331","sha256:1a3629666764c7a9a6cb6a547ac6d123a60ac3a2d51e782406f2eee0e40bb525"],"state_sha256":"78db82c88e4504e34c69948e023a343d40ef25056317434d369576dea7e3d216"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ub+kMHzb1JwtF3jg0TlK3zZ/+CliRet2dlpM2mSudNd9zV8ut8vOGygVPiGN0csJYMEOY6vUUbVyYT0Tl5EMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:10:24.068269Z","bundle_sha256":"88a6c7f848ea5fd62d378f5276c4a57383e23a9303fe3b657ef7cfbd26cd884e"}}