{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JXVYNV2NNPXWMHPLKZ2YQFWAUX","short_pith_number":"pith:JXVYNV2N","canonical_record":{"source":{"id":"2405.19332","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T17:59:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f723b524f9cb686809dcdecfce5c6b2634b217bbcbeae901f6810a8c6345fce","abstract_canon_sha256":"b39e3fb4575922279bd512f437e97f30741576820e746abcbdf596a424e5584f"},"schema_version":"1.0"},"canonical_sha256":"4deb86d74d6bef661deb56758816c0a5d2cbe0e24e29ca18f84a5c035f26388a","source":{"kind":"arxiv","id":"2405.19332","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19332","created_at":"2026-07-05T09:31:03Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19332v3","created_at":"2026-07-05T09:31:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19332","created_at":"2026-07-05T09:31:03Z"},{"alias_kind":"pith_short_12","alias_value":"JXVYNV2NNPXW","created_at":"2026-07-05T09:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"JXVYNV2NNPXWMHPL","created_at":"2026-07-05T09:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"JXVYNV2N","created_at":"2026-07-05T09:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JXVYNV2NNPXWMHPLKZ2YQFWAUX","target":"record","payload":{"canonical_record":{"source":{"id":"2405.19332","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T17:59:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f723b524f9cb686809dcdecfce5c6b2634b217bbcbeae901f6810a8c6345fce","abstract_canon_sha256":"b39e3fb4575922279bd512f437e97f30741576820e746abcbdf596a424e5584f"},"schema_version":"1.0"},"canonical_sha256":"4deb86d74d6bef661deb56758816c0a5d2cbe0e24e29ca18f84a5c035f26388a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:03.277699Z","signature_b64":"aEz8+YlxqazQE/hke0u7DZp7bvQCRHqgBYX1nFCFw4npZ5gYRqK2qJbeK8Hyy9lJw6L94oAojQlvxaEsKcnfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4deb86d74d6bef661deb56758816c0a5d2cbe0e24e29ca18f84a5c035f26388a","last_reissued_at":"2026-07-05T09:31:03.277151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:03.277151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.19332","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":"2026-07-05T09:31:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9VBTdMUYJnUp6nwJt4DsZUzy52VHFYRrDbZ5fX74Kth0QumelSVdjDNMenz+UCly8qV9J8+ZfFhkVbFtOLMrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:23:55.801911Z"},"content_sha256":"95f83884c9f960a9cc75c4275f4b5995ea03724d31b71433dfac705b46c1dc3c","schema_version":"1.0","event_id":"sha256:95f83884c9f960a9cc75c4275f4b5995ea03724d31b71433dfac705b46c1dc3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JXVYNV2NNPXWMHPLKZ2YQFWAUX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donghan Yu, Hany Hassan, Han Zhong, Hiteshi Sharma, Shenao Zhang, Shuohang Wang, Zhaoran Wang, Zhihan Liu, Ziyi Yang","submitted_at":"2024-05-29T17:59:07Z","abstract_excerpt":"Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed dataset, online feedback collection from humans or AI on model generations typically leads to more capable reward models and better-aligned LLMs through an iterative process. However, achieving a globally accurate reward model requires systematic exploration to generate diverse responses that span the vast space of natural language. Random sampling from stan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19332","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/2405.19332/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":"2026-07-05T09:31:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZCenNjdIjehvo0xqVMBDrgDvbzOixwjEFCvPVmXUTKPR7/5yqZ1VltzLdbjFXDKyS/dnscOKiZ2YRGb5B1j5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:23:55.802427Z"},"content_sha256":"6a07505a7146492dcbbc2300eea7e7a479a8d87774c571b78a7b7c3f2fa8acc3","schema_version":"1.0","event_id":"sha256:6a07505a7146492dcbbc2300eea7e7a479a8d87774c571b78a7b7c3f2fa8acc3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JXVYNV2NNPXWMHPLKZ2YQFWAUX/bundle.json","state_url":"https://pith.science/pith/JXVYNV2NNPXWMHPLKZ2YQFWAUX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JXVYNV2NNPXWMHPLKZ2YQFWAUX/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":"2026-08-06T13:23:55Z","links":{"resolver":"https://pith.science/pith/JXVYNV2NNPXWMHPLKZ2YQFWAUX","bundle":"https://pith.science/pith/JXVYNV2NNPXWMHPLKZ2YQFWAUX/bundle.json","state":"https://pith.science/pith/JXVYNV2NNPXWMHPLKZ2YQFWAUX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JXVYNV2NNPXWMHPLKZ2YQFWAUX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JXVYNV2NNPXWMHPLKZ2YQFWAUX","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":"b39e3fb4575922279bd512f437e97f30741576820e746abcbdf596a424e5584f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T17:59:07Z","title_canon_sha256":"8f723b524f9cb686809dcdecfce5c6b2634b217bbcbeae901f6810a8c6345fce"},"schema_version":"1.0","source":{"id":"2405.19332","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19332","created_at":"2026-07-05T09:31:03Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19332v3","created_at":"2026-07-05T09:31:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19332","created_at":"2026-07-05T09:31:03Z"},{"alias_kind":"pith_short_12","alias_value":"JXVYNV2NNPXW","created_at":"2026-07-05T09:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"JXVYNV2NNPXWMHPL","created_at":"2026-07-05T09:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"JXVYNV2N","created_at":"2026-07-05T09:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:6a07505a7146492dcbbc2300eea7e7a479a8d87774c571b78a7b7c3f2fa8acc3","target":"graph","created_at":"2026-07-05T09:31:03Z","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/2405.19332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed dataset, online feedback collection from humans or AI on model generations typically leads to more capable reward models and better-aligned LLMs through an iterative process. However, achieving a globally accurate reward model requires systematic exploration to generate diverse responses that span the vast space of natural language. Random sampling from stan","authors_text":"Donghan Yu, Hany Hassan, Han Zhong, Hiteshi Sharma, Shenao Zhang, Shuohang Wang, Zhaoran Wang, Zhihan Liu, Ziyi Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T17:59:07Z","title":"Self-Exploring Language Models: Active Preference Elicitation for Online Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19332","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":"sha256:95f83884c9f960a9cc75c4275f4b5995ea03724d31b71433dfac705b46c1dc3c","target":"record","created_at":"2026-07-05T09:31:03Z","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":"b39e3fb4575922279bd512f437e97f30741576820e746abcbdf596a424e5584f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T17:59:07Z","title_canon_sha256":"8f723b524f9cb686809dcdecfce5c6b2634b217bbcbeae901f6810a8c6345fce"},"schema_version":"1.0","source":{"id":"2405.19332","kind":"arxiv","version":3}},"canonical_sha256":"4deb86d74d6bef661deb56758816c0a5d2cbe0e24e29ca18f84a5c035f26388a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4deb86d74d6bef661deb56758816c0a5d2cbe0e24e29ca18f84a5c035f26388a","first_computed_at":"2026-07-05T09:31:03.277151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:03.277151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aEz8+YlxqazQE/hke0u7DZp7bvQCRHqgBYX1nFCFw4npZ5gYRqK2qJbeK8Hyy9lJw6L94oAojQlvxaEsKcnfAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:03.277699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19332","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95f83884c9f960a9cc75c4275f4b5995ea03724d31b71433dfac705b46c1dc3c","sha256:6a07505a7146492dcbbc2300eea7e7a479a8d87774c571b78a7b7c3f2fa8acc3"],"state_sha256":"e0bdc08869f6041f64e9f89145fe5e0b382af73df0019a8ae036b01017d50612"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GilflAj9PvnPx+DByxA1mQMWJ54CvO2qQomf1W+NqqUZC0kYLVg1brofV+m5bEcPOQMgdIoorXjd0su/a+GUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:23:55.806591Z","bundle_sha256":"2bc80b24460281c6a473a4ddcbcef662788fa3a65531fa31ee49d30b28732ab2"}}