{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QBDVZZST4VIMEVNXS6TNAXKW4Q","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":"ec2150190016c79cc0d5e8160bd54d3e8ec7cf6d3384d1431c6acfa21d91a9ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T06:22:33Z","title_canon_sha256":"dfb1ee41ca32c7226c64adff44bd4bb34732d367a7d95f3b5e6d0d3dac4c1709"},"schema_version":"1.0","source":{"id":"2606.09078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09078","created_at":"2026-06-09T02:07:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09078v1","created_at":"2026-06-09T02:07:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09078","created_at":"2026-06-09T02:07:57Z"},{"alias_kind":"pith_short_12","alias_value":"QBDVZZST4VIM","created_at":"2026-06-09T02:07:57Z"},{"alias_kind":"pith_short_16","alias_value":"QBDVZZST4VIMEVNX","created_at":"2026-06-09T02:07:57Z"},{"alias_kind":"pith_short_8","alias_value":"QBDVZZST","created_at":"2026-06-09T02:07:57Z"}],"graph_snapshots":[{"event_id":"sha256:d7eccb3fefe22cf019fce205c0d8d4782b70a6f1787f371f9b082eab2cee259c","target":"graph","created_at":"2026-06-09T02:07:57Z","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/2606.09078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Process Reward Models (PRMs) improve credit assignment for reasoning by providing step-level feedback. However, we identify a hidden bias in PRMs caused by severe imbalance in step-level training data. Standard cross-entropy training amplifies this bias, causing PRMs to overcredit plausible but incorrect steps and produce high false-positive rates. We show that these false positives have an asymmetric downstream effect: false negatives mainly slow exploration, whereas false positives actively steer Best-of-N selection, guided decoding, and policy optimization toward flawed reasoning. This sugg","authors_text":"Aakriti Agrawal, Amrit Singh Bedi, Armin Saghafian, C. Bayan Bruss, Furong Huang, Nam H Nguyen, Nihal Sharma, Rizal Fathony, Souradip Chakraborty","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T06:22:33Z","title":"The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09078","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:d02fdb68bb7f755819f95b9142aff21128cfca81d7b384ae1346503dd65f381a","target":"record","created_at":"2026-06-09T02:07:57Z","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":"ec2150190016c79cc0d5e8160bd54d3e8ec7cf6d3384d1431c6acfa21d91a9ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T06:22:33Z","title_canon_sha256":"dfb1ee41ca32c7226c64adff44bd4bb34732d367a7d95f3b5e6d0d3dac4c1709"},"schema_version":"1.0","source":{"id":"2606.09078","kind":"arxiv","version":1}},"canonical_sha256":"80475ce653e550c255b797a6d05d56e41137c2df7eec2b288548601d735e656f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80475ce653e550c255b797a6d05d56e41137c2df7eec2b288548601d735e656f","first_computed_at":"2026-06-09T02:07:57.595074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:57.595074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lBHZ8v3GUU2+sebObNrcE3qcZQsEK6u+ahqmR2wU7/b6L7dweWYRDnNmxNMj9OTmMBsT0XlJGN/gFdrHE5dWBw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:57.596067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d02fdb68bb7f755819f95b9142aff21128cfca81d7b384ae1346503dd65f381a","sha256:d7eccb3fefe22cf019fce205c0d8d4782b70a6f1787f371f9b082eab2cee259c"],"state_sha256":"e364f9780b2e06dc2fa8745c35fcd5e97e9b8797e8d000fbc73127b5a7721e6f"}