{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7GCUYPFKLCERXBHR5DBTBXG7TE","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":"07abe512ab954e119fa41090757c92249bc8de47b3edaa916061ae895030b8ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:05:58Z","title_canon_sha256":"29facd608b0c8a453eeb6bd239f490b015061b48d342fb666db19b0b53f17f45"},"schema_version":"1.0","source":{"id":"2409.11212","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11212","created_at":"2026-07-05T09:08:03Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11212v1","created_at":"2026-07-05T09:08:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11212","created_at":"2026-07-05T09:08:03Z"},{"alias_kind":"pith_short_12","alias_value":"7GCUYPFKLCER","created_at":"2026-07-05T09:08:03Z"},{"alias_kind":"pith_short_16","alias_value":"7GCUYPFKLCERXBHR","created_at":"2026-07-05T09:08:03Z"},{"alias_kind":"pith_short_8","alias_value":"7GCUYPFK","created_at":"2026-07-05T09:08:03Z"}],"graph_snapshots":[{"event_id":"sha256:4642dd517be052d15f8b3b22595257d8e6fdfb06c95766a74566210cc2e1bc90","target":"graph","created_at":"2026-07-05T09:08:03Z","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/2409.11212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs), but the performance is still underwhelming due to too much noisy preference data yielded in the loop. To combat this issue, we present an \\textbf{U}ncertainty-enhanced \\textbf{P}reference \\textbf{O}ptimization (UPO) framework to make the LLM self-evolve with reliable feedback. The key idea is mitigating the noisy preference data derived from the current policy and reward models by performing pair-wise uncertainty estimation and judiciously reliable feedback sampling. T","authors_text":"Jianing Wang, Mengjiao Bao, Peng Yan, Xiaocheng Zhang, Yang Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:05:58Z","title":"Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11212","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":"sha256:45a6ee7c71cf989d56d823dff44d1ae919715d3b7d92a9bc1a58fed3a68ed4e0","target":"record","created_at":"2026-07-05T09:08:03Z","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":"07abe512ab954e119fa41090757c92249bc8de47b3edaa916061ae895030b8ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:05:58Z","title_canon_sha256":"29facd608b0c8a453eeb6bd239f490b015061b48d342fb666db19b0b53f17f45"},"schema_version":"1.0","source":{"id":"2409.11212","kind":"arxiv","version":1}},"canonical_sha256":"f9854c3caa58891b84f1e8c330dcdf993a39efb7de71898fa3dae3e8c94152d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9854c3caa58891b84f1e8c330dcdf993a39efb7de71898fa3dae3e8c94152d7","first_computed_at":"2026-07-05T09:08:03.338651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:03.338651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1avv5b/1Brh7+s8emkZDTj7o2WXDVscRQCblp0JKnviUGc5kRCzF21YfnJvNuu+eJmJyBdq9lKs4hVfispp/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:03.339031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11212","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45a6ee7c71cf989d56d823dff44d1ae919715d3b7d92a9bc1a58fed3a68ed4e0","sha256:4642dd517be052d15f8b3b22595257d8e6fdfb06c95766a74566210cc2e1bc90"],"state_sha256":"378df6ee4e7e8fcc8325657577de87639cfb6e2344c7c4ef7f28725c8aa0d777"}