{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BNDGZ3FZMNENXFJLKN3OWE5AMQ","short_pith_number":"pith:BNDGZ3FZ","canonical_record":{"source":{"id":"2412.01981","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T21:20:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"918e238225c16ae03b223a38ae4846370cba4ec8e73b17ae2d9dbc3c75d7a19a","abstract_canon_sha256":"380c643f8f08279065583c85910f6c37009177b63b2a3243b046865661cff6a2"},"schema_version":"1.0"},"canonical_sha256":"0b466cecb96348db952b5376eb13a0640cb4db09621647c2d46b2049d9f82686","source":{"kind":"arxiv","id":"2412.01981","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01981","created_at":"2026-07-05T09:43:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01981v1","created_at":"2026-07-05T09:43:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01981","created_at":"2026-07-05T09:43:41Z"},{"alias_kind":"pith_short_12","alias_value":"BNDGZ3FZMNEN","created_at":"2026-07-05T09:43:41Z"},{"alias_kind":"pith_short_16","alias_value":"BNDGZ3FZMNENXFJL","created_at":"2026-07-05T09:43:41Z"},{"alias_kind":"pith_short_8","alias_value":"BNDGZ3FZ","created_at":"2026-07-05T09:43:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BNDGZ3FZMNENXFJLKN3OWE5AMQ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01981","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T21:20:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"918e238225c16ae03b223a38ae4846370cba4ec8e73b17ae2d9dbc3c75d7a19a","abstract_canon_sha256":"380c643f8f08279065583c85910f6c37009177b63b2a3243b046865661cff6a2"},"schema_version":"1.0"},"canonical_sha256":"0b466cecb96348db952b5376eb13a0640cb4db09621647c2d46b2049d9f82686","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:41.877468Z","signature_b64":"Ms4xXctxzYpxXhsIWAOLHEeKDOtMOmdGPcocsNJ9R47iJdWIGYCV3vbD9r16bRmTQIIPrgTDcKssQsd3+GQ4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b466cecb96348db952b5376eb13a0640cb4db09621647c2d46b2049d9f82686","last_reissued_at":"2026-07-05T09:43:41.877063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:41.877063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01981","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:43:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9nGViV1aEburbtrFtFa0rMWrEdTehgZGQ0UoWKwMBwwEUHs2CZ1wLNDDwRRGucA09bl0v0e8rcK0iToH0nXZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:33:16.212686Z"},"content_sha256":"9b2fbbab04f091dc086c931145a8c6cf91f0e2ebd6eb653d28a266fc26650002","schema_version":"1.0","event_id":"sha256:9b2fbbab04f091dc086c931145a8c6cf91f0e2ebd6eb653d28a266fc26650002"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BNDGZ3FZMNENXFJLKN3OWE5AMQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Free Process Rewards without Process Labels","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bowen Zhou, Ganqu Cui, Hao Peng, Huayu Chen, Kaiyan Zhang, Lifan Yuan, Ning Ding, Wendi Li, Zhiyuan Liu","submitted_at":"2024-12-02T21:20:02Z","abstract_excerpt":"Different from its counterpart outcome reward models (ORMs), which evaluate the entire responses, a process reward model (PRM) scores a reasoning trajectory step by step, providing denser and more fine grained rewards. However, training a PRM requires labels annotated at every intermediate step, presenting significant challenges for both manual and automatic data collection. This paper aims to address this challenge. Both theoretically and empirically, we show that an \\textit{implicit PRM} can be obtained at no additional cost, by simply training an ORM on the cheaper response-level labels. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01981","kind":"arxiv","version":1},"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/2412.01981/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":"2026-07-05T09:43:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MYYvNQFBBJ/K3JyTBNafCliSFpQ5EUaeYuNuOY/YHzbHZOA6wB+v814qHh59B1w+X+oI/3pZKSXwV71n67dqAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:33:16.213119Z"},"content_sha256":"7549eb880adcff80718d23062b03f3421aabb892aa88e80e54dbaa2ac063362b","schema_version":"1.0","event_id":"sha256:7549eb880adcff80718d23062b03f3421aabb892aa88e80e54dbaa2ac063362b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BNDGZ3FZMNENXFJLKN3OWE5AMQ/bundle.json","state_url":"https://pith.science/pith/BNDGZ3FZMNENXFJLKN3OWE5AMQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BNDGZ3FZMNENXFJLKN3OWE5AMQ/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":"2026-08-03T22:33:16Z","links":{"resolver":"https://pith.science/pith/BNDGZ3FZMNENXFJLKN3OWE5AMQ","bundle":"https://pith.science/pith/BNDGZ3FZMNENXFJLKN3OWE5AMQ/bundle.json","state":"https://pith.science/pith/BNDGZ3FZMNENXFJLKN3OWE5AMQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BNDGZ3FZMNENXFJLKN3OWE5AMQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BNDGZ3FZMNENXFJLKN3OWE5AMQ","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":"380c643f8f08279065583c85910f6c37009177b63b2a3243b046865661cff6a2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T21:20:02Z","title_canon_sha256":"918e238225c16ae03b223a38ae4846370cba4ec8e73b17ae2d9dbc3c75d7a19a"},"schema_version":"1.0","source":{"id":"2412.01981","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01981","created_at":"2026-07-05T09:43:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01981v1","created_at":"2026-07-05T09:43:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01981","created_at":"2026-07-05T09:43:41Z"},{"alias_kind":"pith_short_12","alias_value":"BNDGZ3FZMNEN","created_at":"2026-07-05T09:43:41Z"},{"alias_kind":"pith_short_16","alias_value":"BNDGZ3FZMNENXFJL","created_at":"2026-07-05T09:43:41Z"},{"alias_kind":"pith_short_8","alias_value":"BNDGZ3FZ","created_at":"2026-07-05T09:43:41Z"}],"graph_snapshots":[{"event_id":"sha256:7549eb880adcff80718d23062b03f3421aabb892aa88e80e54dbaa2ac063362b","target":"graph","created_at":"2026-07-05T09:43:41Z","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/2412.01981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Different from its counterpart outcome reward models (ORMs), which evaluate the entire responses, a process reward model (PRM) scores a reasoning trajectory step by step, providing denser and more fine grained rewards. However, training a PRM requires labels annotated at every intermediate step, presenting significant challenges for both manual and automatic data collection. This paper aims to address this challenge. Both theoretically and empirically, we show that an \\textit{implicit PRM} can be obtained at no additional cost, by simply training an ORM on the cheaper response-level labels. Th","authors_text":"Bowen Zhou, Ganqu Cui, Hao Peng, Huayu Chen, Kaiyan Zhang, Lifan Yuan, Ning Ding, Wendi Li, Zhiyuan Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T21:20:02Z","title":"Free Process Rewards without Process Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01981","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":"sha256:9b2fbbab04f091dc086c931145a8c6cf91f0e2ebd6eb653d28a266fc26650002","target":"record","created_at":"2026-07-05T09:43:41Z","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":"380c643f8f08279065583c85910f6c37009177b63b2a3243b046865661cff6a2","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-02T21:20:02Z","title_canon_sha256":"918e238225c16ae03b223a38ae4846370cba4ec8e73b17ae2d9dbc3c75d7a19a"},"schema_version":"1.0","source":{"id":"2412.01981","kind":"arxiv","version":1}},"canonical_sha256":"0b466cecb96348db952b5376eb13a0640cb4db09621647c2d46b2049d9f82686","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b466cecb96348db952b5376eb13a0640cb4db09621647c2d46b2049d9f82686","first_computed_at":"2026-07-05T09:43:41.877063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:41.877063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ms4xXctxzYpxXhsIWAOLHEeKDOtMOmdGPcocsNJ9R47iJdWIGYCV3vbD9r16bRmTQIIPrgTDcKssQsd3+GQ4Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:41.877468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01981","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b2fbbab04f091dc086c931145a8c6cf91f0e2ebd6eb653d28a266fc26650002","sha256:7549eb880adcff80718d23062b03f3421aabb892aa88e80e54dbaa2ac063362b"],"state_sha256":"c48755a291a14bfe1ef64c042ddf41e6d52e3b28e831c2b9085fb2d8dfa10f20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FK5geRXtBqr/sdBZE5dhDk7PEfJdeNbDjG7eTuy1x3JhdDmSAgd+5YEaWxcc/aQSZt6ls9ySyT2w868QgEonCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:33:16.215575Z","bundle_sha256":"72a5176707e231e2ded9d630358515774337614e6e103da2f00fef4a9a6b8706"}}