{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QY62SQFFBLDCWIJW2RZPHNDE45","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":"a6e41caa876349f178ebd7d4e335f82524ac0a27c421d13fd5a25416ff1ea850","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T18:58:44Z","title_canon_sha256":"b0e504c5c4a523dcf8552f47ac02522f17d0839f0378db98a83de1f8f3e53333"},"schema_version":"1.0","source":{"id":"2503.03746","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03746","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03746v1","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03746","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_12","alias_value":"QY62SQFFBLDC","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_16","alias_value":"QY62SQFFBLDCWIJW","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_8","alias_value":"QY62SQFF","created_at":"2026-07-05T10:24:59Z"}],"graph_snapshots":[{"event_id":"sha256:78da99ba104464a67985fbc654de06e4ea16bfd8cb53665038192b5e73c5abc6","target":"graph","created_at":"2026-07-05T10:24:59Z","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/2503.03746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models have demonstrated outstanding performance across various downstream tasks and have been widely applied in multiple scenarios. Human-annotated preference data is used for training to further improve LLMs' performance, which is constrained by the upper limit of human performance. Therefore, Self-Rewarding method has been proposed, where LLMs generate training data by rewarding their own outputs. However, the existing self-rewarding paradigm is not effective in mathematical reasoning scenarios and may even lead to a decline in performance. In this work, we propose the Proces","authors_text":"Junxiao Liu, Shimao Zhang, Shujian Huang, Xiao Liu, Xin Zhang, Yeyun Gong, Zheheng Luo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T18:58:44Z","title":"Process-based Self-Rewarding Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03746","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":"sha256:5cad8666bd049d30b491b2fbb622b4de95a917bba0486a66bd36994d0e802943","target":"record","created_at":"2026-07-05T10:24:59Z","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":"a6e41caa876349f178ebd7d4e335f82524ac0a27c421d13fd5a25416ff1ea850","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T18:58:44Z","title_canon_sha256":"b0e504c5c4a523dcf8552f47ac02522f17d0839f0378db98a83de1f8f3e53333"},"schema_version":"1.0","source":{"id":"2503.03746","kind":"arxiv","version":1}},"canonical_sha256":"863da940a50ac62b2136d472f3b464e756741769f0350ea2b3df058909fb9866","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"863da940a50ac62b2136d472f3b464e756741769f0350ea2b3df058909fb9866","first_computed_at":"2026-07-05T10:24:59.925945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:59.925945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/4W1C5pq0jfmi4Py42eKbQS+D6PXaNetj95ik4FBXZKYxAgvAATV1eqFJNQW7MPicCiLjUmwnd43+AOavn6PBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:59.926557Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.03746","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cad8666bd049d30b491b2fbb622b4de95a917bba0486a66bd36994d0e802943","sha256:78da99ba104464a67985fbc654de06e4ea16bfd8cb53665038192b5e73c5abc6"],"state_sha256":"0cf69745bd07fbfdfb003e6142e80f08f2b9110005de4ab611afaab9b140dea4"}