{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:56XO2Z3UQEGIFW5LYOWWIJCMFV","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":"39dfefcdee3f8261382665173630ab2421a89a088f550841ab9234eb61eb09b9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T15:29:51Z","title_canon_sha256":"dc1b7353417f5e322961fceff82254c8a785a43d6490d82f5081b8af95ce9fb7"},"schema_version":"1.0","source":{"id":"2502.18293","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18293","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18293v2","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18293","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"pith_short_12","alias_value":"56XO2Z3UQEGI","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"pith_short_16","alias_value":"56XO2Z3UQEGIFW5L","created_at":"2026-07-05T11:17:41Z"},{"alias_kind":"pith_short_8","alias_value":"56XO2Z3U","created_at":"2026-07-05T11:17:41Z"}],"graph_snapshots":[{"event_id":"sha256:9eecb132ea7e44e9ee98c9e8a21cd84453e47de8858ff4dfe71441132caf6db9","target":"graph","created_at":"2026-07-05T11:17:41Z","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/2502.18293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer training signals for large language models. During self-play alignment, these models often produce numerous candidate answers per query, rendering it computationally infeasible to include all responses in the training objective. In this work, we propose $\\textit{Active Multi-Preference Optimization}$ (AMPO), a novel approach that combines on-policy generation, a multi-preference group-contrastive loss, and active subs","authors_text":"Chetan Bansal, Rahul Madhavan, Saravan Rajmohan, Taneesh Gupta, Xuchao Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T15:29:51Z","title":"AMPO: Active Multi-Preference Optimization for Self-play Preference Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18293","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:f0fb4d8dcd72ec209d168fb8ee8d4672627ebb0a5860e2f122df5c0b9029daa6","target":"record","created_at":"2026-07-05T11:17:41Z","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":"39dfefcdee3f8261382665173630ab2421a89a088f550841ab9234eb61eb09b9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T15:29:51Z","title_canon_sha256":"dc1b7353417f5e322961fceff82254c8a785a43d6490d82f5081b8af95ce9fb7"},"schema_version":"1.0","source":{"id":"2502.18293","kind":"arxiv","version":2}},"canonical_sha256":"efaeed6774810c82dbabc3ad64244c2d5fffaf3d42178ac7192ba047d1b684d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efaeed6774810c82dbabc3ad64244c2d5fffaf3d42178ac7192ba047d1b684d0","first_computed_at":"2026-07-05T11:17:41.972638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:41.972638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dBXAvXZwBsy6v9lIbufuw9nl9IW6qhKaubg2gMWoeFb09w8FEpipi8jqUCGWGLR59iL9a6cX7cv0H6cmB9T+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:41.973138Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18293","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0fb4d8dcd72ec209d168fb8ee8d4672627ebb0a5860e2f122df5c0b9029daa6","sha256:9eecb132ea7e44e9ee98c9e8a21cd84453e47de8858ff4dfe71441132caf6db9"],"state_sha256":"abf11333e9e352d70f0c3aebe83898801f33d4673f47267192e86282ba11cc1b"}