{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T3CPF6FMDSCLLXOAY3EJM76TLK","short_pith_number":"pith:T3CPF6FM","canonical_record":{"source":{"id":"2402.07314","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T21:44:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6bc8a4e8b396505d047129dc2602cc5f31387418a2e15d2cf7ed85386fbd48e7","abstract_canon_sha256":"a0cf55c17006fac0f8939ca45261d7d5014dcccee3acd1f11273dfe336b6d5ff"},"schema_version":"1.0"},"canonical_sha256":"9ec4f2f8ac1c84b5ddc0c6c8967fd35ab83ba8042c2c814224a228acb1b01862","source":{"kind":"arxiv","id":"2402.07314","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07314","created_at":"2026-07-05T09:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07314v3","created_at":"2026-07-05T09:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07314","created_at":"2026-07-05T09:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"T3CPF6FMDSCL","created_at":"2026-07-05T09:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"T3CPF6FMDSCLLXOA","created_at":"2026-07-05T09:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"T3CPF6FM","created_at":"2026-07-05T09:34:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T3CPF6FMDSCLLXOAY3EJM76TLK","target":"record","payload":{"canonical_record":{"source":{"id":"2402.07314","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T21:44:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6bc8a4e8b396505d047129dc2602cc5f31387418a2e15d2cf7ed85386fbd48e7","abstract_canon_sha256":"a0cf55c17006fac0f8939ca45261d7d5014dcccee3acd1f11273dfe336b6d5ff"},"schema_version":"1.0"},"canonical_sha256":"9ec4f2f8ac1c84b5ddc0c6c8967fd35ab83ba8042c2c814224a228acb1b01862","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:11.423468Z","signature_b64":"cdWFKyGBgR5/ot7IqWRaG3bIdhuvga/sZYS/wr9SlOaipLd6Qu3SJlhMQd/mnabbkSd1PmJ6pivd+aXXD4YqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ec4f2f8ac1c84b5ddc0c6c8967fd35ab83ba8042c2c814224a228acb1b01862","last_reissued_at":"2026-07-05T09:34:11.422939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:11.422939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.07314","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:34:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"shlaO7liEAq8qOovuBLC/qviJ7QnVxMQRTiu9tHsNeVZ0Jp/fdBavmt/U7LY1xSCEF+mvT5AVZPQmI8Z+oyHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:52:45.567002Z"},"content_sha256":"913a5e3721d79f0f23b20dfa6251c05c3ceaf62541a734c7469aed89bfa0ddd1","schema_version":"1.0","event_id":"sha256:913a5e3721d79f0f23b20dfa6251c05c3ceaf62541a734c7469aed89bfa0ddd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T3CPF6FMDSCLLXOAY3EJM76TLK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chenlu Ye, HanZe Dong, Nan Jiang, Tong Zhang, Wei Xiong, Yuheng Zhang","submitted_at":"2024-02-11T21:44:21Z","abstract_excerpt":"We investigate Reinforcement Learning from Human Feedback (RLHF) in the context of a general preference oracle. In particular, we do not assume the existence of a reward function and an oracle preference signal drawn from the Bradley-Terry model as most of the prior works do. We consider a standard mathematical formulation, the reverse-KL regularized minimax game between two LLMs for RLHF under general preference oracle. The learning objective of this formulation is to find a policy so that it is consistently preferred by the KL-regularized preference oracle over any competing LLMs. We show th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07314","kind":"arxiv","version":3},"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/2402.07314/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":"2026-07-05T09:34:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nrRCF7hYecvNIyjvo1IvjNwqaYvzkxUKBhh489OtzhYI7sBGga1Jo3ZYDaSyyrxNuv+LtNZJ5M3ZKuhoR5OTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:52:45.567541Z"},"content_sha256":"0c4562fb425f7786bfee5ecbd757683876bdda85286e396892f8a591b3174650","schema_version":"1.0","event_id":"sha256:0c4562fb425f7786bfee5ecbd757683876bdda85286e396892f8a591b3174650"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T3CPF6FMDSCLLXOAY3EJM76TLK/bundle.json","state_url":"https://pith.science/pith/T3CPF6FMDSCLLXOAY3EJM76TLK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T3CPF6FMDSCLLXOAY3EJM76TLK/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":"2026-08-08T15:52:45Z","links":{"resolver":"https://pith.science/pith/T3CPF6FMDSCLLXOAY3EJM76TLK","bundle":"https://pith.science/pith/T3CPF6FMDSCLLXOAY3EJM76TLK/bundle.json","state":"https://pith.science/pith/T3CPF6FMDSCLLXOAY3EJM76TLK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T3CPF6FMDSCLLXOAY3EJM76TLK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T3CPF6FMDSCLLXOAY3EJM76TLK","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":"a0cf55c17006fac0f8939ca45261d7d5014dcccee3acd1f11273dfe336b6d5ff","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T21:44:21Z","title_canon_sha256":"6bc8a4e8b396505d047129dc2602cc5f31387418a2e15d2cf7ed85386fbd48e7"},"schema_version":"1.0","source":{"id":"2402.07314","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07314","created_at":"2026-07-05T09:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07314v3","created_at":"2026-07-05T09:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07314","created_at":"2026-07-05T09:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"T3CPF6FMDSCL","created_at":"2026-07-05T09:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"T3CPF6FMDSCLLXOA","created_at":"2026-07-05T09:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"T3CPF6FM","created_at":"2026-07-05T09:34:11Z"}],"graph_snapshots":[{"event_id":"sha256:0c4562fb425f7786bfee5ecbd757683876bdda85286e396892f8a591b3174650","target":"graph","created_at":"2026-07-05T09:34:11Z","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/2402.07314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate Reinforcement Learning from Human Feedback (RLHF) in the context of a general preference oracle. In particular, we do not assume the existence of a reward function and an oracle preference signal drawn from the Bradley-Terry model as most of the prior works do. We consider a standard mathematical formulation, the reverse-KL regularized minimax game between two LLMs for RLHF under general preference oracle. The learning objective of this formulation is to find a policy so that it is consistently preferred by the KL-regularized preference oracle over any competing LLMs. We show th","authors_text":"Chenlu Ye, HanZe Dong, Nan Jiang, Tong Zhang, Wei Xiong, Yuheng Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T21:44:21Z","title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07314","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":"sha256:913a5e3721d79f0f23b20dfa6251c05c3ceaf62541a734c7469aed89bfa0ddd1","target":"record","created_at":"2026-07-05T09:34:11Z","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":"a0cf55c17006fac0f8939ca45261d7d5014dcccee3acd1f11273dfe336b6d5ff","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T21:44:21Z","title_canon_sha256":"6bc8a4e8b396505d047129dc2602cc5f31387418a2e15d2cf7ed85386fbd48e7"},"schema_version":"1.0","source":{"id":"2402.07314","kind":"arxiv","version":3}},"canonical_sha256":"9ec4f2f8ac1c84b5ddc0c6c8967fd35ab83ba8042c2c814224a228acb1b01862","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ec4f2f8ac1c84b5ddc0c6c8967fd35ab83ba8042c2c814224a228acb1b01862","first_computed_at":"2026-07-05T09:34:11.422939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:11.422939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cdWFKyGBgR5/ot7IqWRaG3bIdhuvga/sZYS/wr9SlOaipLd6Qu3SJlhMQd/mnabbkSd1PmJ6pivd+aXXD4YqAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:11.423468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07314","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:913a5e3721d79f0f23b20dfa6251c05c3ceaf62541a734c7469aed89bfa0ddd1","sha256:0c4562fb425f7786bfee5ecbd757683876bdda85286e396892f8a591b3174650"],"state_sha256":"9b3006480d12e9ffbac142d3dfb5a9bcf76859cba22d0d3864859e31bcc5b5eb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lu1xVsUBQB2a7UTprzrRuLnWzfwbc2kl4oihxzh6HBTQwV+NZz7SGGmokPmIR6fcDcXrg/mP6zhXnY0OQCtMAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:52:45.571009Z","bundle_sha256":"d638621be51b4e0b6a23b1cfec9b163c7e937cf488b739b1cdeb0c1272d0d20b"}}