{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GKT5YPL2AYQCYSHWC3UM7C6SM4","short_pith_number":"pith:GKT5YPL2","schema_version":"1.0","canonical_sha256":"32a7dc3d7a06202c48f616e8cf8bd2672f649aaeb29609b0c039d0060edde591","source":{"kind":"arxiv","id":"2411.11681","version":3},"attestation_state":"computed","paper":{"title":"PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chong Feng, Jiawei Li, Junlong Zhang, Xinyue Liang, Yang Gao, Yizhe Yang","submitted_at":"2024-11-18T16:03:51Z","abstract_excerpt":"Process supervision enhances the performance of large language models in reasoning tasks by providing feedback at each step of chain-of-thought reasoning. However, due to the lack of effective process supervision methods, even advanced large language models are prone to logical errors and redundant reasoning. We claim that the effectiveness of process supervision significantly depends on both the accuracy and the length of reasoning chains. Moreover, we identify that these factors exhibit a nonlinear relationship with the overall reward score of the reasoning process. Inspired by these insight"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.11681","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-18T16:03:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6131e137d034eafb5f64c88198c9df6f8c463502ae1d51f50e07f2309e0d9ab5","abstract_canon_sha256":"91df77a8a5841775a8f8465e99831ca9b677f43c48f12e5e289597c7726dbc2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:02.231919Z","signature_b64":"I76XsX3CclSwXio40TJ0DYoaX3bMbRpMATsPWuTl27xzSjibj+yvQvog3Gg9IWLf/+uYEmRV4SaJBu/pi6CSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32a7dc3d7a06202c48f616e8cf8bd2672f649aaeb29609b0c039d0060edde591","last_reissued_at":"2026-07-05T11:03:02.231352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:02.231352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chong Feng, Jiawei Li, Junlong Zhang, Xinyue Liang, Yang Gao, Yizhe Yang","submitted_at":"2024-11-18T16:03:51Z","abstract_excerpt":"Process supervision enhances the performance of large language models in reasoning tasks by providing feedback at each step of chain-of-thought reasoning. However, due to the lack of effective process supervision methods, even advanced large language models are prone to logical errors and redundant reasoning. We claim that the effectiveness of process supervision significantly depends on both the accuracy and the length of reasoning chains. Moreover, we identify that these factors exhibit a nonlinear relationship with the overall reward score of the reasoning process. Inspired by these insight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11681","kind":"arxiv","version":3},"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/2411.11681/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.11681","created_at":"2026-07-05T11:03:02.231429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11681v3","created_at":"2026-07-05T11:03:02.231429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11681","created_at":"2026-07-05T11:03:02.231429+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKT5YPL2AYQC","created_at":"2026-07-05T11:03:02.231429+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKT5YPL2AYQCYSHW","created_at":"2026-07-05T11:03:02.231429+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKT5YPL2","created_at":"2026-07-05T11:03:02.231429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GKT5YPL2AYQCYSHWC3UM7C6SM4","json":"https://pith.science/pith/GKT5YPL2AYQCYSHWC3UM7C6SM4.json","graph_json":"https://pith.science/api/pith-number/GKT5YPL2AYQCYSHWC3UM7C6SM4/graph.json","events_json":"https://pith.science/api/pith-number/GKT5YPL2AYQCYSHWC3UM7C6SM4/events.json","paper":"https://pith.science/paper/GKT5YPL2"},"agent_actions":{"view_html":"https://pith.science/pith/GKT5YPL2AYQCYSHWC3UM7C6SM4","download_json":"https://pith.science/pith/GKT5YPL2AYQCYSHWC3UM7C6SM4.json","view_paper":"https://pith.science/paper/GKT5YPL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11681&json=true","fetch_graph":"https://pith.science/api/pith-number/GKT5YPL2AYQCYSHWC3UM7C6SM4/graph.json","fetch_events":"https://pith.science/api/pith-number/GKT5YPL2AYQCYSHWC3UM7C6SM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKT5YPL2AYQCYSHWC3UM7C6SM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKT5YPL2AYQCYSHWC3UM7C6SM4/action/storage_attestation","attest_author":"https://pith.science/pith/GKT5YPL2AYQCYSHWC3UM7C6SM4/action/author_attestation","sign_citation":"https://pith.science/pith/GKT5YPL2AYQCYSHWC3UM7C6SM4/action/citation_signature","submit_replication":"https://pith.science/pith/GKT5YPL2AYQCYSHWC3UM7C6SM4/action/replication_record"}},"created_at":"2026-07-05T11:03:02.231429+00:00","updated_at":"2026-07-05T11:03:02.231429+00:00"}