{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YSCV53R7HVGDYHOYRO2GLDSSID","short_pith_number":"pith:YSCV53R7","canonical_record":{"source":{"id":"2406.07657","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-11T18:55:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"322b61790ac764dfc89021f41574c79dc0c5c95c95997d1430ad1843baf14bd2","abstract_canon_sha256":"2ed909b90d0f6a08f7489c2956ab059ba100e6b803cc67d65ce6645b7528ed13"},"schema_version":"1.0"},"canonical_sha256":"c4855eee3f3d4c3c1dd88bb4658e5240c8d9bb820685f3597fa4a970e0163aa3","source":{"kind":"arxiv","id":"2406.07657","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07657","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07657v1","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07657","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_12","alias_value":"YSCV53R7HVGD","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"YSCV53R7HVGDYHOY","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"YSCV53R7","created_at":"2026-07-05T08:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YSCV53R7HVGDYHOYRO2GLDSSID","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07657","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-11T18:55:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"322b61790ac764dfc89021f41574c79dc0c5c95c95997d1430ad1843baf14bd2","abstract_canon_sha256":"2ed909b90d0f6a08f7489c2956ab059ba100e6b803cc67d65ce6645b7528ed13"},"schema_version":"1.0"},"canonical_sha256":"c4855eee3f3d4c3c1dd88bb4658e5240c8d9bb820685f3597fa4a970e0163aa3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:36.357756Z","signature_b64":"fQ7Yb8kKxGwDUfljUl3tfZO3i1GuV4dA1ARU4JzvOFsIJDe54VsYkzEpeYxicKnvvTcMuRV2J2HxYd3FItQ2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4855eee3f3d4c3c1dd88bb4658e5240c8d9bb820685f3597fa4a970e0163aa3","last_reissued_at":"2026-07-05T08:30:36.357240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:36.357240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07657","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:30:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EeI2bw1AU7SMo91oqCEuKVdkvKfeK2/+8fRvQySA80BlICglN4/ID9PoIDGzEhcPM5AlMx893FAobo89oK7KCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:39:55.271505Z"},"content_sha256":"26e4e947682ff17e056198084e2c92d8c2e893597ab6e64dbe543bd66f8532e5","schema_version":"1.0","event_id":"sha256:26e4e947682ff17e056198084e2c92d8c2e893597ab6e64dbe543bd66f8532e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YSCV53R7HVGDYHOYRO2GLDSSID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OPTune: Efficient Online Preference Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Chenxi Liu, Chen Zhu, Davit Soselia, Heng Huang, Jiuhai Chen, John Kirchenbauer, Lichang Chen, Tianyi Zhou, Tom Goldstein","submitted_at":"2024-06-11T18:55:04Z","abstract_excerpt":"Reinforcement learning with human feedback~(RLHF) is critical for aligning Large Language Models (LLMs) with human preference. Compared to the widely studied offline version of RLHF, \\emph{e.g.} direct preference optimization (DPO), recent works have shown that the online variants achieve even better alignment. However, online alignment requires on-the-fly generation of new training data, which is costly, hard to parallelize, and suffers from varying quality and utility. In this paper, we propose a more efficient data exploration strategy for online preference tuning (OPTune), which does not r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07657","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.07657/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:30:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OdkiAHfxeggjcbYaxf5Rgst/KPNok3mxG2J5+kZ8p1HPt78BliNcRrIPXHP2sfGe70YTLjUxYH2pzPc7F1N5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:39:55.271998Z"},"content_sha256":"e5c4beb1e25a02bbb7c0d2d11530998e19aa5e86bdcd7291f09183156d902d53","schema_version":"1.0","event_id":"sha256:e5c4beb1e25a02bbb7c0d2d11530998e19aa5e86bdcd7291f09183156d902d53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YSCV53R7HVGDYHOYRO2GLDSSID/bundle.json","state_url":"https://pith.science/pith/YSCV53R7HVGDYHOYRO2GLDSSID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YSCV53R7HVGDYHOYRO2GLDSSID/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T17:39:55Z","links":{"resolver":"https://pith.science/pith/YSCV53R7HVGDYHOYRO2GLDSSID","bundle":"https://pith.science/pith/YSCV53R7HVGDYHOYRO2GLDSSID/bundle.json","state":"https://pith.science/pith/YSCV53R7HVGDYHOYRO2GLDSSID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YSCV53R7HVGDYHOYRO2GLDSSID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YSCV53R7HVGDYHOYRO2GLDSSID","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":"2ed909b90d0f6a08f7489c2956ab059ba100e6b803cc67d65ce6645b7528ed13","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-11T18:55:04Z","title_canon_sha256":"322b61790ac764dfc89021f41574c79dc0c5c95c95997d1430ad1843baf14bd2"},"schema_version":"1.0","source":{"id":"2406.07657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07657","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07657v1","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07657","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_12","alias_value":"YSCV53R7HVGD","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"YSCV53R7HVGDYHOY","created_at":"2026-07-05T08:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"YSCV53R7","created_at":"2026-07-05T08:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:e5c4beb1e25a02bbb7c0d2d11530998e19aa5e86bdcd7291f09183156d902d53","target":"graph","created_at":"2026-07-05T08:30:36Z","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/2406.07657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with human feedback~(RLHF) is critical for aligning Large Language Models (LLMs) with human preference. Compared to the widely studied offline version of RLHF, \\emph{e.g.} direct preference optimization (DPO), recent works have shown that the online variants achieve even better alignment. However, online alignment requires on-the-fly generation of new training data, which is costly, hard to parallelize, and suffers from varying quality and utility. In this paper, we propose a more efficient data exploration strategy for online preference tuning (OPTune), which does not r","authors_text":"Chenxi Liu, Chen Zhu, Davit Soselia, Heng Huang, Jiuhai Chen, John Kirchenbauer, Lichang Chen, Tianyi Zhou, Tom Goldstein","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-11T18:55:04Z","title":"OPTune: Efficient Online Preference Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07657","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":"sha256:26e4e947682ff17e056198084e2c92d8c2e893597ab6e64dbe543bd66f8532e5","target":"record","created_at":"2026-07-05T08:30:36Z","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":"2ed909b90d0f6a08f7489c2956ab059ba100e6b803cc67d65ce6645b7528ed13","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-11T18:55:04Z","title_canon_sha256":"322b61790ac764dfc89021f41574c79dc0c5c95c95997d1430ad1843baf14bd2"},"schema_version":"1.0","source":{"id":"2406.07657","kind":"arxiv","version":1}},"canonical_sha256":"c4855eee3f3d4c3c1dd88bb4658e5240c8d9bb820685f3597fa4a970e0163aa3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4855eee3f3d4c3c1dd88bb4658e5240c8d9bb820685f3597fa4a970e0163aa3","first_computed_at":"2026-07-05T08:30:36.357240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:36.357240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fQ7Yb8kKxGwDUfljUl3tfZO3i1GuV4dA1ARU4JzvOFsIJDe54VsYkzEpeYxicKnvvTcMuRV2J2HxYd3FItQ2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:36.357756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26e4e947682ff17e056198084e2c92d8c2e893597ab6e64dbe543bd66f8532e5","sha256:e5c4beb1e25a02bbb7c0d2d11530998e19aa5e86bdcd7291f09183156d902d53"],"state_sha256":"6849bafb290c3e3a6d45bc3d628a188e9dc4c9649f62a2098997bccabdcb57b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ASx+UbMx0gvf6d0YxNjePhF0pOSjBUeNWsQ0OIA3ngyV6Bi6FkkvW6CIfF4YMjRG8oVUDgCnoDoWu5vpyM1CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:39:55.275634Z","bundle_sha256":"3b7b17259bf49d3a2d93d3b6ba91198a163eeaae221c7f9315efe8e9ae301195"}}