{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZJHCQDSOBF5QEURQHTBDGSY6KF","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":"755015d3d252a8f12a23b8b806c7b35b59e902083fd5c1ad9f243002016b868d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-08T05:25:54Z","title_canon_sha256":"fa6f87a41baac22fd1ccd147bc813243e405a3b8a2a3cc99d3cfd49d142aba18"},"schema_version":"1.0","source":{"id":"2508.06026","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06026","created_at":"2026-07-05T11:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06026v1","created_at":"2026-07-05T11:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06026","created_at":"2026-07-05T11:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZJHCQDSOBF5Q","created_at":"2026-07-05T11:50:47Z"},{"alias_kind":"pith_short_16","alias_value":"ZJHCQDSOBF5QEURQ","created_at":"2026-07-05T11:50:47Z"},{"alias_kind":"pith_short_8","alias_value":"ZJHCQDSO","created_at":"2026-07-05T11:50:47Z"}],"graph_snapshots":[{"event_id":"sha256:d155885c7f5c0685b6f58827e81263c3e9eb63c04b70a4b742ccbc5ef6ea1fbf","target":"graph","created_at":"2026-07-05T11:50:47Z","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/2508.06026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting, dynamically improving its generative capabilities through iterative Direct Preference Optimization (DPO). However, our analysis reveals a critical limitation in existing Self-Rewarding paradigms: the synchronized improvement of chosen and rejected responses progressively narrows the representational difference between contrasting samples, undermining effective preference learning. We propose \\textbf{Temporal Self-Re","authors_text":"Cunxiang Wang, Jianing Chu, Junfeng Fang, Libo Qin, Qiufeng Wang, Shikun Zhang, Shuxun Yang, Wei Ye, Xin Wang, Xuran Meng, Yidong Wang, Yue Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-08T05:25:54Z","title":"Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06026","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":"sha256:22ae3d884ed0cd3e1566dc24b20c0ef8fe89caccd296d8d02f66b3719d8e68d5","target":"record","created_at":"2026-07-05T11:50:47Z","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":"755015d3d252a8f12a23b8b806c7b35b59e902083fd5c1ad9f243002016b868d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-08T05:25:54Z","title_canon_sha256":"fa6f87a41baac22fd1ccd147bc813243e405a3b8a2a3cc99d3cfd49d142aba18"},"schema_version":"1.0","source":{"id":"2508.06026","kind":"arxiv","version":1}},"canonical_sha256":"ca4e280e4e097b0252303cc2334b1e516497168ae8c8042e966cf8703c831691","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca4e280e4e097b0252303cc2334b1e516497168ae8c8042e966cf8703c831691","first_computed_at":"2026-07-05T11:50:47.834369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:47.834369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DO1djsK71Y6UpKppm6KqUi22+OrBLmEABFjNplA1khRTJAXs2ah2GU8jAk+3fciZ0JO7v622EHqmJSjWToInCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:47.834874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.06026","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22ae3d884ed0cd3e1566dc24b20c0ef8fe89caccd296d8d02f66b3719d8e68d5","sha256:d155885c7f5c0685b6f58827e81263c3e9eb63c04b70a4b742ccbc5ef6ea1fbf"],"state_sha256":"7a23939d01264da9a1032a98384a1aa26e5fa6e4d4117c91147a876faae1bbb3"}