{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OV4WD5Q72WNXXCVHTFRR7NKULB","short_pith_number":"pith:OV4WD5Q7","canonical_record":{"source":{"id":"2502.05773","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-09T04:31:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4fbbd67d4d986f23e9754a65ee272d3386fe81fb8236817a71c9280279a03d2c","abstract_canon_sha256":"c556da69761e63272aa39761412ede9507e8cb2130f87c55f90325d93fc1bd16"},"schema_version":"1.0"},"canonical_sha256":"757961f61fd59b7b8aa799631fb55458598121ea4917e3679131b5a901cabccb","source":{"kind":"arxiv","id":"2502.05773","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05773","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05773v2","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05773","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"OV4WD5Q72WNX","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"OV4WD5Q72WNXXCVH","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"OV4WD5Q7","created_at":"2026-07-05T11:42:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OV4WD5Q72WNXXCVHTFRR7NKULB","target":"record","payload":{"canonical_record":{"source":{"id":"2502.05773","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-09T04:31:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4fbbd67d4d986f23e9754a65ee272d3386fe81fb8236817a71c9280279a03d2c","abstract_canon_sha256":"c556da69761e63272aa39761412ede9507e8cb2130f87c55f90325d93fc1bd16"},"schema_version":"1.0"},"canonical_sha256":"757961f61fd59b7b8aa799631fb55458598121ea4917e3679131b5a901cabccb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:53.395267Z","signature_b64":"eA/IfjKEpdzWrHkJECIodXxlk9xBGX1AyzdL+ighw2I2oginHEo8XEnDiMvSdlwSNLJb2shcGVvO158Ui7GDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"757961f61fd59b7b8aa799631fb55458598121ea4917e3679131b5a901cabccb","last_reissued_at":"2026-07-05T11:42:53.394774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:53.394774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.05773","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SLCIf/ZD7UNbUEoIejdd5rEbUPJOSxFgrN7tlMb6khGuL+CBVLL6lCTggN3IiZsVXmOZVQ/zE5Kgn3yvALmCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:33:44.068578Z"},"content_sha256":"e4ac5d5d296cbf5f48374e6ddb4591ceb01ad8f306875c6c0cea9e455dcbb12a","schema_version":"1.0","event_id":"sha256:e4ac5d5d296cbf5f48374e6ddb4591ceb01ad8f306875c6c0cea9e455dcbb12a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OV4WD5Q72WNXXCVHTFRR7NKULB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PIPA: Preference Alignment as Prior-Informed Statistical Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junbo Li, Qiang Liu, Zhangyang Wang","submitted_at":"2025-02-09T04:31:30Z","abstract_excerpt":"Offline preference alignment for language models such as Direct Preference Optimization (DPO) is favored for its effectiveness and simplicity, eliminating the need for costly reinforcement learning. Various offline algorithms have been developed for different data settings, yet they lack a unified understanding.\n  In this study, we introduce Pior-Informed Preference Alignment (PIPA), a unified, RL-free probabilistic framework that formulates language model preference alignment as a Maximum Likelihood Estimation (MLE) problem with prior constraints. This method effectively accommodates both pai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05773","kind":"arxiv","version":2},"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/2502.05773/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":"2026-07-05T11:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+VYQ7CmeutU/ds4HCHNs4+La96CE/5a1rn7iGAfSVVYefO1YhDAtIutodMA8JYKFzjeZUmIKjlbGZhdzmoFcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:33:44.069112Z"},"content_sha256":"d47b32a3a885aa659e48da4a45c86d282aeda2be58370870214e96535b51ca3e","schema_version":"1.0","event_id":"sha256:d47b32a3a885aa659e48da4a45c86d282aeda2be58370870214e96535b51ca3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OV4WD5Q72WNXXCVHTFRR7NKULB/bundle.json","state_url":"https://pith.science/pith/OV4WD5Q72WNXXCVHTFRR7NKULB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OV4WD5Q72WNXXCVHTFRR7NKULB/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":"2026-08-09T17:33:44Z","links":{"resolver":"https://pith.science/pith/OV4WD5Q72WNXXCVHTFRR7NKULB","bundle":"https://pith.science/pith/OV4WD5Q72WNXXCVHTFRR7NKULB/bundle.json","state":"https://pith.science/pith/OV4WD5Q72WNXXCVHTFRR7NKULB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OV4WD5Q72WNXXCVHTFRR7NKULB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OV4WD5Q72WNXXCVHTFRR7NKULB","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":"c556da69761e63272aa39761412ede9507e8cb2130f87c55f90325d93fc1bd16","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-09T04:31:30Z","title_canon_sha256":"4fbbd67d4d986f23e9754a65ee272d3386fe81fb8236817a71c9280279a03d2c"},"schema_version":"1.0","source":{"id":"2502.05773","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05773","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05773v2","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05773","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"OV4WD5Q72WNX","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"OV4WD5Q72WNXXCVH","created_at":"2026-07-05T11:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"OV4WD5Q7","created_at":"2026-07-05T11:42:53Z"}],"graph_snapshots":[{"event_id":"sha256:d47b32a3a885aa659e48da4a45c86d282aeda2be58370870214e96535b51ca3e","target":"graph","created_at":"2026-07-05T11:42:53Z","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/2502.05773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline preference alignment for language models such as Direct Preference Optimization (DPO) is favored for its effectiveness and simplicity, eliminating the need for costly reinforcement learning. Various offline algorithms have been developed for different data settings, yet they lack a unified understanding.\n  In this study, we introduce Pior-Informed Preference Alignment (PIPA), a unified, RL-free probabilistic framework that formulates language model preference alignment as a Maximum Likelihood Estimation (MLE) problem with prior constraints. This method effectively accommodates both pai","authors_text":"Junbo Li, Qiang Liu, Zhangyang Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-09T04:31:30Z","title":"PIPA: Preference Alignment as Prior-Informed Statistical Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05773","kind":"arxiv","version":2},"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:e4ac5d5d296cbf5f48374e6ddb4591ceb01ad8f306875c6c0cea9e455dcbb12a","target":"record","created_at":"2026-07-05T11:42:53Z","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":"c556da69761e63272aa39761412ede9507e8cb2130f87c55f90325d93fc1bd16","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-09T04:31:30Z","title_canon_sha256":"4fbbd67d4d986f23e9754a65ee272d3386fe81fb8236817a71c9280279a03d2c"},"schema_version":"1.0","source":{"id":"2502.05773","kind":"arxiv","version":2}},"canonical_sha256":"757961f61fd59b7b8aa799631fb55458598121ea4917e3679131b5a901cabccb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"757961f61fd59b7b8aa799631fb55458598121ea4917e3679131b5a901cabccb","first_computed_at":"2026-07-05T11:42:53.394774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:53.394774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eA/IfjKEpdzWrHkJECIodXxlk9xBGX1AyzdL+ighw2I2oginHEo8XEnDiMvSdlwSNLJb2shcGVvO158Ui7GDDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:53.395267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05773","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4ac5d5d296cbf5f48374e6ddb4591ceb01ad8f306875c6c0cea9e455dcbb12a","sha256:d47b32a3a885aa659e48da4a45c86d282aeda2be58370870214e96535b51ca3e"],"state_sha256":"006dc85190aa8bc811cba2563969fd304a94de60c92759a7de3d99977feb96e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O0gcWIFW9USRIr92KvToNRWFzeTFwIXCbNo3X8a5hNqkzeWngpzo+IxnlDe4DKOc0NcKNYPdEMk0QcUJn7kQAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:33:44.074417Z","bundle_sha256":"b4ffea7cc63a2909855ef7d898c7983cff8edac91636ca155b4996cdc6390665"}}