{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RMBKLCLBP3KOI7HAPHJSAZ2XPT","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":"4ddd3cfb4e9c1f335f4ece327a2dda01b3dca1b8547f189c9ed83ea4a7afe3cc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-06T18:36:22Z","title_canon_sha256":"b5d37663db8810356d7e7f3633d2aeb90ed6008ea9d886cfe27ce1bac5f230c4"},"schema_version":"1.0","source":{"id":"2411.04109","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04109","created_at":"2026-07-05T11:32:20Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04109v3","created_at":"2026-07-05T11:32:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04109","created_at":"2026-07-05T11:32:20Z"},{"alias_kind":"pith_short_12","alias_value":"RMBKLCLBP3KO","created_at":"2026-07-05T11:32:20Z"},{"alias_kind":"pith_short_16","alias_value":"RMBKLCLBP3KOI7HA","created_at":"2026-07-05T11:32:20Z"},{"alias_kind":"pith_short_8","alias_value":"RMBKLCLB","created_at":"2026-07-05T11:32:20Z"}],"graph_snapshots":[{"event_id":"sha256:513c95ca21ca4204e27db9498a35683232afa05d80e61a19f8646c86f31c0fd6","target":"graph","created_at":"2026-07-05T11:32:20Z","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/2411.04109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex reasoning tasks due to the difficulty of assigning correct rewards. An orthogonal approach that is known to improve correctness is self-consistency, a method applied at inference time based on multiple sampling in order to find the most consistent answer. In this work, we extend the self-consistency concept to help train models. We thus introduce self-consistency preference optimization (ScPO), which iteratively trai","authors_text":"Archiki Prasad, Jane Yu, Jason Weston, Jing Xu, Maryam Fazel-Zarandi, Mohit Bansal, Richard Yuanzhe Pang, Sainbayar Sukhbaatar, Weizhe Yuan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-06T18:36:22Z","title":"Self-Consistency Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04109","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:acdefbab46e7a3c2d31ca7c046732bb32ad3ebf84954bda36c3732675039d5da","target":"record","created_at":"2026-07-05T11:32:20Z","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":"4ddd3cfb4e9c1f335f4ece327a2dda01b3dca1b8547f189c9ed83ea4a7afe3cc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-06T18:36:22Z","title_canon_sha256":"b5d37663db8810356d7e7f3633d2aeb90ed6008ea9d886cfe27ce1bac5f230c4"},"schema_version":"1.0","source":{"id":"2411.04109","kind":"arxiv","version":3}},"canonical_sha256":"8b02a589617ed4e47ce079d32067577ceb5dbe3fc8f6534762cda423d1b40817","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b02a589617ed4e47ce079d32067577ceb5dbe3fc8f6534762cda423d1b40817","first_computed_at":"2026-07-05T11:32:20.538710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:20.538710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i3WJ1l3CjmfuLsNld6WQHc7zpQag2VPohJy3RtAfaRk22vwrzLBvwqqOFfPGUNZU40FZZzKcr5Oqa7cmY5nRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:20.539293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04109","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acdefbab46e7a3c2d31ca7c046732bb32ad3ebf84954bda36c3732675039d5da","sha256:513c95ca21ca4204e27db9498a35683232afa05d80e61a19f8646c86f31c0fd6"],"state_sha256":"99a64213b9a2fda3c5adf2c333aac5ca1e4c39b841c64bd46e210d89da783769"}