{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:W6UHQ6VVNDCZPFOSU4WMVIZCFZ","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":"f8209cabd163b30c059f55a96401c95459ad103653fa5f2f246c44976b3ba4de","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T10:05:32Z","title_canon_sha256":"1621fad34099b3ff6152acb1d28d43264b245014040912791b829f342b7f868b"},"schema_version":"1.0","source":{"id":"2310.15694","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15694","created_at":"2026-07-05T08:00:37Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15694v5","created_at":"2026-07-05T08:00:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15694","created_at":"2026-07-05T08:00:37Z"},{"alias_kind":"pith_short_12","alias_value":"W6UHQ6VVNDCZ","created_at":"2026-07-05T08:00:37Z"},{"alias_kind":"pith_short_16","alias_value":"W6UHQ6VVNDCZPFOS","created_at":"2026-07-05T08:00:37Z"},{"alias_kind":"pith_short_8","alias_value":"W6UHQ6VV","created_at":"2026-07-05T08:00:37Z"}],"graph_snapshots":[{"event_id":"sha256:a7d3125f9a53b82aab78abb773f79cbc5a1404862d3f03220f9c695a0d4084d5","target":"graph","created_at":"2026-07-05T08:00:37Z","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/2310.15694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The technique of Reinforcement Learning from Human Feedback (RLHF) is a commonly employed method to improve pre-trained Language Models (LM), enhancing their ability to conform to human preferences. Nevertheless, the current RLHF-based LMs necessitate full retraining each time novel queries or feedback are introduced, which becomes a challenging task because human preferences can vary between different domains or tasks. Retraining LMs poses practical difficulties in many real-world situations due to the significant time and computational resources required, along with concerns related to data ","authors_text":"Han Zhang, Hui Wang, Lin Gui, Ruifeng Xu, Yuanzhao Zhai, Yu Lei","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T10:05:32Z","title":"COPR: Continual Learning Human Preference through Optimal Policy Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15694","kind":"arxiv","version":5},"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:a5ad99620e46077374072d58a84e449c079461b85da6114a998b375b5cfa2cbd","target":"record","created_at":"2026-07-05T08:00:37Z","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":"f8209cabd163b30c059f55a96401c95459ad103653fa5f2f246c44976b3ba4de","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T10:05:32Z","title_canon_sha256":"1621fad34099b3ff6152acb1d28d43264b245014040912791b829f342b7f868b"},"schema_version":"1.0","source":{"id":"2310.15694","kind":"arxiv","version":5}},"canonical_sha256":"b7a8787ab568c59795d2a72ccaa3222e75ed189c7d828b101d5bff1f5dab425e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7a8787ab568c59795d2a72ccaa3222e75ed189c7d828b101d5bff1f5dab425e","first_computed_at":"2026-07-05T08:00:37.173267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:37.173267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HjQB+NJCF7ghGL07OfwZp+w9CcdMhAf0UJiRXh2KgWBRZul/2uDP1SWr4RGPykeMi1V5v2pbfGYNHCBc2j7qCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:37.173744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15694","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5ad99620e46077374072d58a84e449c079461b85da6114a998b375b5cfa2cbd","sha256:a7d3125f9a53b82aab78abb773f79cbc5a1404862d3f03220f9c695a0d4084d5"],"state_sha256":"e4b3fdd69e135fbd5f341e3bf0e8ea62ee33f4887f4e45d08e5cce60b974c3a5"}