{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H2Q4RL7CGGLWSYRDDEPGFA45DB","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":"a83905eafabde9356dfcdcef2e98940ce998b9886d01ea7ff98a13192af04855","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T10:05:14Z","title_canon_sha256":"d910e7451f7a0ad662613f6561b706b8e0670e14b886a6a6ac1d493b0afd8f66"},"schema_version":"1.0","source":{"id":"2507.01551","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01551","created_at":"2026-07-05T11:31:29Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01551v2","created_at":"2026-07-05T11:31:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01551","created_at":"2026-07-05T11:31:29Z"},{"alias_kind":"pith_short_12","alias_value":"H2Q4RL7CGGLW","created_at":"2026-07-05T11:31:29Z"},{"alias_kind":"pith_short_16","alias_value":"H2Q4RL7CGGLWSYRD","created_at":"2026-07-05T11:31:29Z"},{"alias_kind":"pith_short_8","alias_value":"H2Q4RL7C","created_at":"2026-07-05T11:31:29Z"}],"graph_snapshots":[{"event_id":"sha256:e9e795e1d45a2bd0eca20517e7d31bb62fd4db9e45cbb7692e25b89ec45a2889","target":"graph","created_at":"2026-07-05T11:31:29Z","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/2507.01551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~(LLMs). However, introducing additional process reward models incurs substantial computational overhead, and there is no unified theoretical framework for process-level advantage estimation. To bridge this gap, we propose \\textbf{S}elf-Guided \\textbf{P}rocess \\textbf{R}eward \\textbf{O}ptimization~(\\textbf{SPRO}), a novel framework that enables process-aware RL through two key innovations: (1) we first theoretically demonstrate that process rewards can be","authors_text":"Hao Kong, Jing Tang, Lei Chen, Shuxian Liang, Wu Fei, Xiansheng Hua, Yang Lin, Yibo Yang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T10:05:14Z","title":"Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01551","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:e0c7702b5f82c778047b22c054965a5f5f30dfbd60706c072ee7227ef145d8c4","target":"record","created_at":"2026-07-05T11:31:29Z","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":"a83905eafabde9356dfcdcef2e98940ce998b9886d01ea7ff98a13192af04855","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-02T10:05:14Z","title_canon_sha256":"d910e7451f7a0ad662613f6561b706b8e0670e14b886a6a6ac1d493b0afd8f66"},"schema_version":"1.0","source":{"id":"2507.01551","kind":"arxiv","version":2}},"canonical_sha256":"3ea1c8afe23197696223191e62839d185f4f1f7e491307129d6ca1e533159f44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ea1c8afe23197696223191e62839d185f4f1f7e491307129d6ca1e533159f44","first_computed_at":"2026-07-05T11:31:29.376690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:29.376690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m0s+43e8v6ViDeRa2szaVH83eW5C0qG8PZS6++Ahn7kZUIngl4+0j4cbYD/A64o/tQdmKel0pRfDJecUNrSEDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:29.377154Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01551","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0c7702b5f82c778047b22c054965a5f5f30dfbd60706c072ee7227ef145d8c4","sha256:e9e795e1d45a2bd0eca20517e7d31bb62fd4db9e45cbb7692e25b89ec45a2889"],"state_sha256":"55e046e359f9975bbcef2364acfc15d3127dd9caf7c85db563ced0226db0598e"}