{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VZRTYQTDZHRZF5CU3L32HQZAJ6","short_pith_number":"pith:VZRTYQTD","canonical_record":{"source":{"id":"2506.07492","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T07:11:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5a72417bb53f493d0885d62426fe162ca5c6f9cfdaa266e55f3984fab8e2dfc1","abstract_canon_sha256":"d5abe577aaca56031e76b3ce6822a9402ffb2cb54d324c09ca11df3c24512a46"},"schema_version":"1.0"},"canonical_sha256":"ae633c4263c9e392f454daf7a3c3204f9dfb53f354b621fb00e9ef12eb1d5142","source":{"kind":"arxiv","id":"2506.07492","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07492","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07492v1","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07492","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"VZRTYQTDZHRZ","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"VZRTYQTDZHRZF5CU","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"VZRTYQTD","created_at":"2026-07-05T11:18:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VZRTYQTDZHRZF5CU3L32HQZAJ6","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07492","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T07:11:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5a72417bb53f493d0885d62426fe162ca5c6f9cfdaa266e55f3984fab8e2dfc1","abstract_canon_sha256":"d5abe577aaca56031e76b3ce6822a9402ffb2cb54d324c09ca11df3c24512a46"},"schema_version":"1.0"},"canonical_sha256":"ae633c4263c9e392f454daf7a3c3204f9dfb53f354b621fb00e9ef12eb1d5142","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:28.239806Z","signature_b64":"+KPlJ5QzOgwhrmJpmAWKX/mGlz8P9rU1D9EnNamu16xRmqjpnPzoknTF5BaN0AV4Y0BAFqdhON/hHNnDdvjYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae633c4263c9e392f454daf7a3c3204f9dfb53f354b621fb00e9ef12eb1d5142","last_reissued_at":"2026-07-05T11:18:28.239296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:28.239296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07492","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":"2026-07-05T11:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MI7zQyQySaGQB5PGvIvoBmT051BgCdfL4zMtRqQPctzghaY8m+H6ME9lUOQUOYM7sGHCgLXVyGg7L9i2NONSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:28:24.670735Z"},"content_sha256":"c93c6beeed9d445a2f6eddb9d989f91f04cac53f057a59102f932b5a1793533d","schema_version":"1.0","event_id":"sha256:c93c6beeed9d445a2f6eddb9d989f91f04cac53f057a59102f932b5a1793533d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VZRTYQTDZHRZF5CU3L32HQZAJ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explicit Preference Optimization: No Need for an Implicit Reward Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Wipf, Lemin Kong, Tong He, Xiangkun Hu","submitted_at":"2025-06-09T07:11:01Z","abstract_excerpt":"The generated responses of large language models (LLMs) are often fine-tuned to human preferences through a process called reinforcement learning from human feedback (RLHF). As RLHF relies on a challenging training sequence, whereby a separate reward model is independently learned and then later applied to LLM policy updates, ongoing research effort has targeted more straightforward alternatives. In this regard, direct preference optimization (DPO) and its many offshoots circumvent the need for a separate reward training step. Instead, through the judicious use of a reparameterization trick th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07492","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/2506.07492/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":"2026-07-05T11:18:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QyzgRPGVDKafMHoiGut628HQ26Un70DOOYOg1Uxo4IifX52tnLUtsWtm7kT6ZqS/UpvB2+RHfXive0ZUS2OCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:28:24.671607Z"},"content_sha256":"13c4aa21c770b3a842ca384b510cb9a159a7333a9c4b8bd97246130446b3f8de","schema_version":"1.0","event_id":"sha256:13c4aa21c770b3a842ca384b510cb9a159a7333a9c4b8bd97246130446b3f8de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VZRTYQTDZHRZF5CU3L32HQZAJ6/bundle.json","state_url":"https://pith.science/pith/VZRTYQTDZHRZF5CU3L32HQZAJ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VZRTYQTDZHRZF5CU3L32HQZAJ6/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":"2026-08-10T00:28:24Z","links":{"resolver":"https://pith.science/pith/VZRTYQTDZHRZF5CU3L32HQZAJ6","bundle":"https://pith.science/pith/VZRTYQTDZHRZF5CU3L32HQZAJ6/bundle.json","state":"https://pith.science/pith/VZRTYQTDZHRZF5CU3L32HQZAJ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VZRTYQTDZHRZF5CU3L32HQZAJ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VZRTYQTDZHRZF5CU3L32HQZAJ6","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":"d5abe577aaca56031e76b3ce6822a9402ffb2cb54d324c09ca11df3c24512a46","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T07:11:01Z","title_canon_sha256":"5a72417bb53f493d0885d62426fe162ca5c6f9cfdaa266e55f3984fab8e2dfc1"},"schema_version":"1.0","source":{"id":"2506.07492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07492","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07492v1","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07492","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"VZRTYQTDZHRZ","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"VZRTYQTDZHRZF5CU","created_at":"2026-07-05T11:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"VZRTYQTD","created_at":"2026-07-05T11:18:28Z"}],"graph_snapshots":[{"event_id":"sha256:13c4aa21c770b3a842ca384b510cb9a159a7333a9c4b8bd97246130446b3f8de","target":"graph","created_at":"2026-07-05T11:18:28Z","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/2506.07492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The generated responses of large language models (LLMs) are often fine-tuned to human preferences through a process called reinforcement learning from human feedback (RLHF). As RLHF relies on a challenging training sequence, whereby a separate reward model is independently learned and then later applied to LLM policy updates, ongoing research effort has targeted more straightforward alternatives. In this regard, direct preference optimization (DPO) and its many offshoots circumvent the need for a separate reward training step. Instead, through the judicious use of a reparameterization trick th","authors_text":"David Wipf, Lemin Kong, Tong He, Xiangkun Hu","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T07:11:01Z","title":"Explicit Preference Optimization: No Need for an Implicit Reward Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07492","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:c93c6beeed9d445a2f6eddb9d989f91f04cac53f057a59102f932b5a1793533d","target":"record","created_at":"2026-07-05T11:18:28Z","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":"d5abe577aaca56031e76b3ce6822a9402ffb2cb54d324c09ca11df3c24512a46","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T07:11:01Z","title_canon_sha256":"5a72417bb53f493d0885d62426fe162ca5c6f9cfdaa266e55f3984fab8e2dfc1"},"schema_version":"1.0","source":{"id":"2506.07492","kind":"arxiv","version":1}},"canonical_sha256":"ae633c4263c9e392f454daf7a3c3204f9dfb53f354b621fb00e9ef12eb1d5142","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae633c4263c9e392f454daf7a3c3204f9dfb53f354b621fb00e9ef12eb1d5142","first_computed_at":"2026-07-05T11:18:28.239296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:28.239296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+KPlJ5QzOgwhrmJpmAWKX/mGlz8P9rU1D9EnNamu16xRmqjpnPzoknTF5BaN0AV4Y0BAFqdhON/hHNnDdvjYDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:28.239806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c93c6beeed9d445a2f6eddb9d989f91f04cac53f057a59102f932b5a1793533d","sha256:13c4aa21c770b3a842ca384b510cb9a159a7333a9c4b8bd97246130446b3f8de"],"state_sha256":"5fe897db0a9af3d1aa0f59e5898202437a95fdfd4a435b0ee9a6d42d25d232a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PSSCVKM0lZqUVvpSokL0DGjREJ//iY6tRNhc6+Xq/EDutmMeUPq6CqNlHBpDfbWLGy5v9RKUPRcubkVjHD7kDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:28:24.686862Z","bundle_sha256":"cab7707acfea7b634a7ee6b69e5dc57716f7216d8362dddbfc816f2de6cb7538"}}