{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BTKPMPNVZAWPSCEGT6BAKRWQYX","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":"52e0443a4047368f6518fdc92ac9248db4b88cdf5eb22a8cec0f26ba17c77d4b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T15:15:05Z","title_canon_sha256":"0c5d3308f50dceb3b31944292f426460dd9a88d88009128050cd6eeba62e63d9"},"schema_version":"1.0","source":{"id":"2310.05782","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05782","created_at":"2026-07-05T07:33:20Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05782v3","created_at":"2026-07-05T07:33:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05782","created_at":"2026-07-05T07:33:20Z"},{"alias_kind":"pith_short_12","alias_value":"BTKPMPNVZAWP","created_at":"2026-07-05T07:33:20Z"},{"alias_kind":"pith_short_16","alias_value":"BTKPMPNVZAWPSCEG","created_at":"2026-07-05T07:33:20Z"},{"alias_kind":"pith_short_8","alias_value":"BTKPMPNV","created_at":"2026-07-05T07:33:20Z"}],"graph_snapshots":[{"event_id":"sha256:708dbb4e58682528624e549d00ce3666eb805a004a68cb201edcbffac8cce31c","target":"graph","created_at":"2026-07-05T07:33:20Z","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/2310.05782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the quest to advance human-centric natural language generation (NLG) systems, ensuring alignment between NLG models and human preferences is crucial. For this alignment, current popular methods leverage a reinforcement learning (RL) approach with a reward model trained on feedback from humans. However, inherent disagreements due to the subjective nature of human preferences pose a significant challenge for training the reward model, resulting in a deterioration of the NLG performance. To tackle this issue, previous approaches typically rely on majority voting or averaging to consolidate mul","authors_text":"Haozhao Wang, Jiashuo Wang, Shichao Sun, Wenjie Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T15:15:05Z","title":"Aligning Language Models with Human Preferences via a Bayesian Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05782","kind":"arxiv","version":3},"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":"sha256:534704f2ac66a8c1a073ebb3b35d1a65aa0130d7d46f38d1f2afd3b2d56cfeb9","target":"record","created_at":"2026-07-05T07:33:20Z","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":"52e0443a4047368f6518fdc92ac9248db4b88cdf5eb22a8cec0f26ba17c77d4b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T15:15:05Z","title_canon_sha256":"0c5d3308f50dceb3b31944292f426460dd9a88d88009128050cd6eeba62e63d9"},"schema_version":"1.0","source":{"id":"2310.05782","kind":"arxiv","version":3}},"canonical_sha256":"0cd4f63db5c82cf908869f820546d0c5f7f938fbdbfaf1d6fdae4188857069df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cd4f63db5c82cf908869f820546d0c5f7f938fbdbfaf1d6fdae4188857069df","first_computed_at":"2026-07-05T07:33:20.579645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:20.579645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l2vTK2IdLVQ+BMSN0N8kdMa0xvCYTdS7ytfLPnuwLQfYHuD66rwrSoMRZD87SpOC3uhDUB4si7TUQc52IKYhBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:20.580003Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05782","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:534704f2ac66a8c1a073ebb3b35d1a65aa0130d7d46f38d1f2afd3b2d56cfeb9","sha256:708dbb4e58682528624e549d00ce3666eb805a004a68cb201edcbffac8cce31c"],"state_sha256":"81ee3e0236a7c5d725d30435d726ec30f79ec07f31d2206104b2e5021875d3e0"}