{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OPCVJNQ3JDPIMOQMAGZBTFYCZX","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":"d037f95ad8c4991a1b7d0af6299da3467b4273e1c182a524b1ac013ac98e8463","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-25T11:37:15Z","title_canon_sha256":"6441c32c1f832d3008c2061b391039d7e5c96e30666c29e507aa64d7f94a689a"},"schema_version":"1.0","source":{"id":"2403.16649","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16649","created_at":"2026-07-05T08:00:43Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16649v2","created_at":"2026-07-05T08:00:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16649","created_at":"2026-07-05T08:00:43Z"},{"alias_kind":"pith_short_12","alias_value":"OPCVJNQ3JDPI","created_at":"2026-07-05T08:00:43Z"},{"alias_kind":"pith_short_16","alias_value":"OPCVJNQ3JDPIMOQM","created_at":"2026-07-05T08:00:43Z"},{"alias_kind":"pith_short_8","alias_value":"OPCVJNQ3","created_at":"2026-07-05T08:00:43Z"}],"graph_snapshots":[{"event_id":"sha256:4f5e08b51ee8ad6549d29c167fe9cabfa4c6a273faf57bf14084f68ad28695a0","target":"graph","created_at":"2026-07-05T08:00:43Z","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/2403.16649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from human feedback (RLHF) is a crucial technique in aligning large language models (LLMs) with human preferences, ensuring these LLMs behave in beneficial and comprehensible ways to users. However, a longstanding challenge in human alignment techniques based on reinforcement learning lies in their inherent complexity and difficulty in training. To address this challenge, we present a simple yet effective Contrastive Learning Framework for Human Alignment (CLHA) to align LLMs with human preferences directly. CLHA employs a novel rescoring strategy to evaluate the noise w","authors_text":"Chengming Li, Feiteng Fang, Jinchang Hou, Liang Zhu, Min Yang, Qixuan Zhao, Ruifeng Xu, Xi Feng, Xiping Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-25T11:37:15Z","title":"CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16649","kind":"arxiv","version":2},"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":"sha256:4f22d15ed5709392c2212480401c7b3a2522f3f0b487d7621bf70680959858c5","target":"record","created_at":"2026-07-05T08:00:43Z","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":"d037f95ad8c4991a1b7d0af6299da3467b4273e1c182a524b1ac013ac98e8463","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-25T11:37:15Z","title_canon_sha256":"6441c32c1f832d3008c2061b391039d7e5c96e30666c29e507aa64d7f94a689a"},"schema_version":"1.0","source":{"id":"2403.16649","kind":"arxiv","version":2}},"canonical_sha256":"73c554b61b48de863a0c01b2199702cdd72a8b18875c7f47a42bcf67281bf720","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73c554b61b48de863a0c01b2199702cdd72a8b18875c7f47a42bcf67281bf720","first_computed_at":"2026-07-05T08:00:43.671418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:43.671418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GrHZjHiqR9t80JYM5JJ16LEJyqQpUzV3Elya1FdbXsu0ImSvILYWhWtkaPO14KltRQW3mYx4WqtjbY5UdD4WDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:43.671891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16649","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f22d15ed5709392c2212480401c7b3a2522f3f0b487d7621bf70680959858c5","sha256:4f5e08b51ee8ad6549d29c167fe9cabfa4c6a273faf57bf14084f68ad28695a0"],"state_sha256":"24378f38d9cd1522bfdb59e34e875a9531fde9ba02ba0a2ce5f8c94ff10ea717"}