{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YTRGYHXXOKC4XOPSSGES2YYTL2","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":"162df9330a90a8e19ed25737cdb0d1529d5fb71ea39c36c932b2f17769ef15b9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T08:30:15Z","title_canon_sha256":"67aa8b396acbbec79a62aa6644ac6a204654448a5722bbd9f9a3e1d0afea44d1"},"schema_version":"1.0","source":{"id":"2404.00604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00604","created_at":"2026-07-05T08:02:54Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00604v1","created_at":"2026-07-05T08:02:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00604","created_at":"2026-07-05T08:02:54Z"},{"alias_kind":"pith_short_12","alias_value":"YTRGYHXXOKC4","created_at":"2026-07-05T08:02:54Z"},{"alias_kind":"pith_short_16","alias_value":"YTRGYHXXOKC4XOPS","created_at":"2026-07-05T08:02:54Z"},{"alias_kind":"pith_short_8","alias_value":"YTRGYHXX","created_at":"2026-07-05T08:02:54Z"}],"graph_snapshots":[{"event_id":"sha256:05b103715a42cc277c96cd90d1d7a3ac7e92e9b1035ed0626fbf4d10689e60fe","target":"graph","created_at":"2026-07-05T08:02:54Z","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/2404.00604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from human feedback (RLHF) has been a central technique for recent large language model (LLM) alignment. However, its heavy dependence on costly human or LLM-as-Judge preference feedback could stymie its wider applications. In this work, we introduce Self-Contrast, a feedback-free large language model alignment method via exploiting extensive self-generated negatives. With only supervised fine-tuning (SFT) targets, Self-Contrast leverages the LLM itself to generate massive diverse candidates, and harnesses a pre-trained embedding model to filter multiple negatives accord","authors_text":"Jie Tang, Xiao Liu, Xixuan Song, Yuxiao Dong","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T08:30:15Z","title":"Extensive Self-Contrast Enables Feedback-Free Language Model Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00604","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":"sha256:8cc020571445417144230d00214a0c2df015249b11308c34fe72a5fef91912d7","target":"record","created_at":"2026-07-05T08:02:54Z","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":"162df9330a90a8e19ed25737cdb0d1529d5fb71ea39c36c932b2f17769ef15b9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T08:30:15Z","title_canon_sha256":"67aa8b396acbbec79a62aa6644ac6a204654448a5722bbd9f9a3e1d0afea44d1"},"schema_version":"1.0","source":{"id":"2404.00604","kind":"arxiv","version":1}},"canonical_sha256":"c4e26c1ef77285cbb9f291892d63135e98825751a46f0e1ec73c2dd471396fc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4e26c1ef77285cbb9f291892d63135e98825751a46f0e1ec73c2dd471396fc2","first_computed_at":"2026-07-05T08:02:54.311734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:54.311734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zkfKOtR47HO9rPYZKn3p1BaK0jpPDrvGBKPyYOPMWKXe1d8TcbONQNFOt/XriQjk0DZRpXD7xqzS4AVCzfwtBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:54.312286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cc020571445417144230d00214a0c2df015249b11308c34fe72a5fef91912d7","sha256:05b103715a42cc277c96cd90d1d7a3ac7e92e9b1035ed0626fbf4d10689e60fe"],"state_sha256":"df04cb0947efd40d2cf42caa2fa153adc05ad019ddbb570fade28fd168571f57"}