{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EWU7G3DXDD4NVOGTIEEZJUERTK","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":"c9e9386f9dec4f30d204c77ef55bd2065b8e6142e5864cd72a70abae377bbdbe","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T17:31:23Z","title_canon_sha256":"902fdefaf98de11fae6312d25228e4eff2eb2f3e5dcf0c49070aba16f779dc5e"},"schema_version":"1.0","source":{"id":"2410.08146","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08146","created_at":"2026-05-21T01:36:42Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08146v1","created_at":"2026-05-21T01:36:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08146","created_at":"2026-05-21T01:36:42Z"},{"alias_kind":"pith_short_12","alias_value":"EWU7G3DXDD4N","created_at":"2026-05-21T01:36:42Z"},{"alias_kind":"pith_short_16","alias_value":"EWU7G3DXDD4NVOGT","created_at":"2026-05-21T01:36:42Z"},{"alias_kind":"pith_short_8","alias_value":"EWU7G3DX","created_at":"2026-05-21T01:36:42Z"}],"graph_snapshots":[{"event_id":"sha256:71acae3c7982e28bb7fb3ab810f8034f9727f76b8108e1948cf083a9f60ea8e2","target":"graph","created_at":"2026-05-21T01:36:42Z","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/2410.08146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward models (ORMs) that only provide feedback at the final step. However, collecting dense, per-step human labels is not scalable, and training PRMs from automatically-labeled data has thus far led to limited gains. To improve a base policy by running search against a PRM or using it as dense rewards for reinforcement learning (RL), we ask: \"How should we design pr","authors_text":"Adam Fisch, Alekh Agarwal, Amrith Setlur, Aviral Kumar, Chirag Nagpal, Jacob Eisenstein, Jonathan Berant, Rishabh Agarwal, Xinyang Geng","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T17:31:23Z","title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08146","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:de1108f7f836d70f9e68409180defa55c0e029ffc4ee9b0e222497dc597165dc","target":"record","created_at":"2026-05-21T01:36:42Z","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":"c9e9386f9dec4f30d204c77ef55bd2065b8e6142e5864cd72a70abae377bbdbe","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T17:31:23Z","title_canon_sha256":"902fdefaf98de11fae6312d25228e4eff2eb2f3e5dcf0c49070aba16f779dc5e"},"schema_version":"1.0","source":{"id":"2410.08146","kind":"arxiv","version":1}},"canonical_sha256":"25a9f36c7718f8dab8d3410994d0919aacd8c3783656df69625f2b6347379c55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25a9f36c7718f8dab8d3410994d0919aacd8c3783656df69625f2b6347379c55","first_computed_at":"2026-05-21T01:36:42.127656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:36:42.127656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"488XLloOuui9IPExjD+RzFg9YoVSsPjBI676G+vfx6Bnw/UMcqHoTNragN/BcSpvvyL0fnR4DBvFcILtaE/dDw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:36:42.130275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08146","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de1108f7f836d70f9e68409180defa55c0e029ffc4ee9b0e222497dc597165dc","sha256:71acae3c7982e28bb7fb3ab810f8034f9727f76b8108e1948cf083a9f60ea8e2"],"state_sha256":"135eb65e298be21cda52cfa104cbf71a3a493aaeb779a57dd73fa3e5a0ae9378"}