{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MKKCRB52M5U6INECS7HAF3BYKM","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":"0135a3ace33b59539daed558ef0a6b6efe658d4a79bbef9b743c9005e1a0593d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T00:36:31Z","title_canon_sha256":"0fd0f55470d763f68a63c23f9afbe091b1394647c7fe27a264f9d8b6280f8896"},"schema_version":"1.0","source":{"id":"2503.01076","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01076","created_at":"2026-07-05T10:22:35Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01076v1","created_at":"2026-07-05T10:22:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01076","created_at":"2026-07-05T10:22:35Z"},{"alias_kind":"pith_short_12","alias_value":"MKKCRB52M5U6","created_at":"2026-07-05T10:22:35Z"},{"alias_kind":"pith_short_16","alias_value":"MKKCRB52M5U6INEC","created_at":"2026-07-05T10:22:35Z"},{"alias_kind":"pith_short_8","alias_value":"MKKCRB52","created_at":"2026-07-05T10:22:35Z"}],"graph_snapshots":[{"event_id":"sha256:0cd24bbc8d70c804abcc63046de242e88f182f6e04799b7583932198a9edba1a","target":"graph","created_at":"2026-07-05T10:22:35Z","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/2503.01076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the critical task of selecting the most informative feedback for training them is under-explored. We propose an active learning framework for DPO, which can be applied to collect human feedback online or to choose the most informative subset of already collected feedback offline. We propose efficient algorithms for both settings. The key idea is to linearize the DPO objective at the ","authors_text":"Branislav Kveton, Jingbo Shang, Julian McAuley, Junda Wu, Ryan Rossi, Tong Yu, Xintong Li","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T00:36:31Z","title":"Active Learning for Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01076","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:e481f92ce92c56a273bd4b2eeda48ce27125326f7429dc8be2cd3962480e40fc","target":"record","created_at":"2026-07-05T10:22:35Z","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":"0135a3ace33b59539daed558ef0a6b6efe658d4a79bbef9b743c9005e1a0593d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T00:36:31Z","title_canon_sha256":"0fd0f55470d763f68a63c23f9afbe091b1394647c7fe27a264f9d8b6280f8896"},"schema_version":"1.0","source":{"id":"2503.01076","kind":"arxiv","version":1}},"canonical_sha256":"62942887ba6769e4348297ce02ec38532dd93fdfdb569d929a1875d2b3821cb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62942887ba6769e4348297ce02ec38532dd93fdfdb569d929a1875d2b3821cb8","first_computed_at":"2026-07-05T10:22:35.496812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:35.496812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CXgqCTBNSuNiYlfcuQkyNPaRMtncMbuuYF6i8EUGv4iqig4k9ZMmzwvV9Z6QYHL0yo8IaGiQdCxWsvBQvFTyAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:35.497218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01076","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e481f92ce92c56a273bd4b2eeda48ce27125326f7429dc8be2cd3962480e40fc","sha256:0cd24bbc8d70c804abcc63046de242e88f182f6e04799b7583932198a9edba1a"],"state_sha256":"3a6f87f929584d9bf01271392959baa6ff2df3f3c6bcab65fd52270afc3226e9"}