{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZS2WXIWNRD2AJONDZQP6SQX5L2","short_pith_number":"pith:ZS2WXIWN","canonical_record":{"source":{"id":"2407.13399","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-18T11:08:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b68e00937b888249c3e44bc73e138190384bae96fa2fb2416a3b532bbf111ca8","abstract_canon_sha256":"b73f74b81558abf3584ecaa403996a6bd99fb5970dab209d11cfe58b616e1fff"},"schema_version":"1.0"},"canonical_sha256":"ccb56ba2cd88f404b9a3cc1fe942fd5ebbd98e597ae6dd8d4409bf32e8b681fa","source":{"kind":"arxiv","id":"2407.13399","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13399","created_at":"2026-07-05T10:16:11Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13399v3","created_at":"2026-07-05T10:16:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13399","created_at":"2026-07-05T10:16:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZS2WXIWNRD2A","created_at":"2026-07-05T10:16:11Z"},{"alias_kind":"pith_short_16","alias_value":"ZS2WXIWNRD2AJOND","created_at":"2026-07-05T10:16:11Z"},{"alias_kind":"pith_short_8","alias_value":"ZS2WXIWN","created_at":"2026-07-05T10:16:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZS2WXIWNRD2AJONDZQP6SQX5L2","target":"record","payload":{"canonical_record":{"source":{"id":"2407.13399","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-18T11:08:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b68e00937b888249c3e44bc73e138190384bae96fa2fb2416a3b532bbf111ca8","abstract_canon_sha256":"b73f74b81558abf3584ecaa403996a6bd99fb5970dab209d11cfe58b616e1fff"},"schema_version":"1.0"},"canonical_sha256":"ccb56ba2cd88f404b9a3cc1fe942fd5ebbd98e597ae6dd8d4409bf32e8b681fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:11.691659Z","signature_b64":"eYffCKLQW0th9fJj+0fwn8whie1gbRJRHn4/F04etXxUPrDe0g58BQkfxXgRWFOve0TmVi9829fzlqZja8NpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccb56ba2cd88f404b9a3cc1fe942fd5ebbd98e597ae6dd8d4409bf32e8b681fa","last_reissued_at":"2026-07-05T10:16:11.691134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:11.691134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.13399","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":"2026-07-05T10:16:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bDPyy7uEehrNpg+0hCgQqs5lgSVArWbYUJ49uyCs+MdCERG9kL+C1J9D984mhhmqBEom0aEPIbCJ36+B9uQzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:02:56.566053Z"},"content_sha256":"8b0371cab203b84ebe87693c31b58cf7a70fde0bb4e7c893cfa3e6e8712207e5","schema_version":"1.0","event_id":"sha256:8b0371cab203b84ebe87693c31b58cf7a70fde0bb4e7c893cfa3e6e8712207e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZS2WXIWNRD2AJONDZQP6SQX5L2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Akshay Krishnamurthy, Audrey Huang, Dylan J. Foster, Jason D. Lee, Tengyang Xie, Wenhao Zhan, Wen Sun","submitted_at":"2024-07-18T11:08:40Z","abstract_excerpt":"Language model alignment methods such as reinforcement learning from human feedback (RLHF) have led to impressive advances in language model capabilities, but are limited by a widely observed phenomenon known as overoptimization, where the quality of the language model degrades over the course of the alignment process. As the model optimizes performance with respect to an offline reward model, it overfits to inaccuracies and drifts away from preferred responses covered by the data. To discourage such distribution shift, KL-regularization is widely employed in existing offline alignment methods"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13399","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/2407.13399/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":"2026-07-05T10:16:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SAbbd3/J1FEU0EnyWxYJcvaoU6kFwaGQV467ROjGYpiJCn+ALRSgxDbVkpYyIPzw+leYoFW/jOq5tI4S+QvUAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:02:56.567041Z"},"content_sha256":"6ae2581a8b4a5e899b05bb9b47fc6c74eeaab752f341ea9aec95bd7eddd307c5","schema_version":"1.0","event_id":"sha256:6ae2581a8b4a5e899b05bb9b47fc6c74eeaab752f341ea9aec95bd7eddd307c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZS2WXIWNRD2AJONDZQP6SQX5L2/bundle.json","state_url":"https://pith.science/pith/ZS2WXIWNRD2AJONDZQP6SQX5L2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZS2WXIWNRD2AJONDZQP6SQX5L2/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":"2026-08-06T19:02:56Z","links":{"resolver":"https://pith.science/pith/ZS2WXIWNRD2AJONDZQP6SQX5L2","bundle":"https://pith.science/pith/ZS2WXIWNRD2AJONDZQP6SQX5L2/bundle.json","state":"https://pith.science/pith/ZS2WXIWNRD2AJONDZQP6SQX5L2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZS2WXIWNRD2AJONDZQP6SQX5L2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZS2WXIWNRD2AJONDZQP6SQX5L2","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":"b73f74b81558abf3584ecaa403996a6bd99fb5970dab209d11cfe58b616e1fff","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-18T11:08:40Z","title_canon_sha256":"b68e00937b888249c3e44bc73e138190384bae96fa2fb2416a3b532bbf111ca8"},"schema_version":"1.0","source":{"id":"2407.13399","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13399","created_at":"2026-07-05T10:16:11Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13399v3","created_at":"2026-07-05T10:16:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13399","created_at":"2026-07-05T10:16:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZS2WXIWNRD2A","created_at":"2026-07-05T10:16:11Z"},{"alias_kind":"pith_short_16","alias_value":"ZS2WXIWNRD2AJOND","created_at":"2026-07-05T10:16:11Z"},{"alias_kind":"pith_short_8","alias_value":"ZS2WXIWN","created_at":"2026-07-05T10:16:11Z"}],"graph_snapshots":[{"event_id":"sha256:6ae2581a8b4a5e899b05bb9b47fc6c74eeaab752f341ea9aec95bd7eddd307c5","target":"graph","created_at":"2026-07-05T10:16:11Z","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/2407.13399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model alignment methods such as reinforcement learning from human feedback (RLHF) have led to impressive advances in language model capabilities, but are limited by a widely observed phenomenon known as overoptimization, where the quality of the language model degrades over the course of the alignment process. As the model optimizes performance with respect to an offline reward model, it overfits to inaccuracies and drifts away from preferred responses covered by the data. To discourage such distribution shift, KL-regularization is widely employed in existing offline alignment methods","authors_text":"Akshay Krishnamurthy, Audrey Huang, Dylan J. Foster, Jason D. Lee, Tengyang Xie, Wenhao Zhan, Wen Sun","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-18T11:08:40Z","title":"Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13399","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":"sha256:8b0371cab203b84ebe87693c31b58cf7a70fde0bb4e7c893cfa3e6e8712207e5","target":"record","created_at":"2026-07-05T10:16:11Z","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":"b73f74b81558abf3584ecaa403996a6bd99fb5970dab209d11cfe58b616e1fff","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-18T11:08:40Z","title_canon_sha256":"b68e00937b888249c3e44bc73e138190384bae96fa2fb2416a3b532bbf111ca8"},"schema_version":"1.0","source":{"id":"2407.13399","kind":"arxiv","version":3}},"canonical_sha256":"ccb56ba2cd88f404b9a3cc1fe942fd5ebbd98e597ae6dd8d4409bf32e8b681fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccb56ba2cd88f404b9a3cc1fe942fd5ebbd98e597ae6dd8d4409bf32e8b681fa","first_computed_at":"2026-07-05T10:16:11.691134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:11.691134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eYffCKLQW0th9fJj+0fwn8whie1gbRJRHn4/F04etXxUPrDe0g58BQkfxXgRWFOve0TmVi9829fzlqZja8NpCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:11.691659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13399","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b0371cab203b84ebe87693c31b58cf7a70fde0bb4e7c893cfa3e6e8712207e5","sha256:6ae2581a8b4a5e899b05bb9b47fc6c74eeaab752f341ea9aec95bd7eddd307c5"],"state_sha256":"3bcd4ec5ed504ba214ed1735b74147fe4d21113f8093a34443830b2082c358b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AHCG8v8dMJ3QuOyIrQcIdqgH/hVpnQc+3XhdQTplKtMw6mX7SXah7AC4YyBf8kyRlVYquJQTf6STDBwtRmEvDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:02:56.575471Z","bundle_sha256":"3b65d0882771276f3b70e2d70d553c7af229c37355be548faa1b13d82bbfbf7f"}}