{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RHV2BKAKJWN75WQMAE7DUKHNXK","short_pith_number":"pith:RHV2BKAK","canonical_record":{"source":{"id":"2302.08215","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-16T10:59:39Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e20b6545b565f5c75cb00bb19562ad5b5c5fcb81582d6eb4f58e62daa9787887","abstract_canon_sha256":"80ea778c6d2d33a444e4e985eea56dc4326ba682cba053baf8d482f4269feb44"},"schema_version":"1.0"},"canonical_sha256":"89eba0a80a4d9bfeda0c013e3a28edba80f37ef9a6db430aacaee0059f33d637","source":{"kind":"arxiv","id":"2302.08215","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08215","created_at":"2026-07-05T06:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08215v2","created_at":"2026-07-05T06:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08215","created_at":"2026-07-05T06:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"RHV2BKAKJWN7","created_at":"2026-07-05T06:17:46Z"},{"alias_kind":"pith_short_16","alias_value":"RHV2BKAKJWN75WQM","created_at":"2026-07-05T06:17:46Z"},{"alias_kind":"pith_short_8","alias_value":"RHV2BKAK","created_at":"2026-07-05T06:17:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RHV2BKAKJWN75WQMAE7DUKHNXK","target":"record","payload":{"canonical_record":{"source":{"id":"2302.08215","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-16T10:59:39Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e20b6545b565f5c75cb00bb19562ad5b5c5fcb81582d6eb4f58e62daa9787887","abstract_canon_sha256":"80ea778c6d2d33a444e4e985eea56dc4326ba682cba053baf8d482f4269feb44"},"schema_version":"1.0"},"canonical_sha256":"89eba0a80a4d9bfeda0c013e3a28edba80f37ef9a6db430aacaee0059f33d637","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:46.424919Z","signature_b64":"varCiR6tTtnzSrebG9JRSacVZcqkfF5hbalZblLSP2TSyoghfCfmcLt+x6OYvwpJJfMPhD628Frhwp0m16UEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89eba0a80a4d9bfeda0c013e3a28edba80f37ef9a6db430aacaee0059f33d637","last_reissued_at":"2026-07-05T06:17:46.424473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:46.424473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.08215","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":"2026-07-05T06:17:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XQrxwZJ+la+CyvQOkoe7p+vxGNJhyffFzw9EIDGxtd0jsQUc4EE1Z70NqCHORDmMIOUZIz7s+rGG75rL/NplCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:27:20.654419Z"},"content_sha256":"f52ebd9a6365bed24064e0dd1c3fd0d54c743c76779826374a7d66963cee6282","schema_version":"1.0","event_id":"sha256:f52ebd9a6365bed24064e0dd1c3fd0d54c743c76779826374a7d66963cee6282"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RHV2BKAKJWN75WQMAE7DUKHNXK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Language Models with Preferences through f-divergence Minimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Dongyoung Go, Germ\\'an Kruszewski, Jos Rozen, Marc Dymetman, Nahyeon Ryu, Tomasz Korbak","submitted_at":"2023-02-16T10:59:39Z","abstract_excerpt":"Aligning language models with preferences can be posed as approximating a target distribution representing some desired behavior. Existing approaches differ both in the functional form of the target distribution and the algorithm used to approximate it. For instance, Reinforcement Learning from Human Feedback (RLHF) corresponds to minimizing a reverse KL from an implicit target distribution arising from a KL penalty in the objective. On the other hand, Generative Distributional Control (GDC) has an explicit target distribution and minimizes a forward KL from it using the Distributional Policy "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08215","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/2302.08215/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":"2026-07-05T06:17:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x4FqYvvttzM5+tF9CEsEtwCgH/8ZSkaNBB0HNcOpeLvwTH0Ncm5E9hcnr+atqfYdpl5TdduLXJ2/45LfcdWNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:27:20.655355Z"},"content_sha256":"197b477cf231c4187b6cb5361154c692e468db0a9a88f7b0fa34eebec6e81c25","schema_version":"1.0","event_id":"sha256:197b477cf231c4187b6cb5361154c692e468db0a9a88f7b0fa34eebec6e81c25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHV2BKAKJWN75WQMAE7DUKHNXK/bundle.json","state_url":"https://pith.science/pith/RHV2BKAKJWN75WQMAE7DUKHNXK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHV2BKAKJWN75WQMAE7DUKHNXK/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":"2026-08-05T17:27:20Z","links":{"resolver":"https://pith.science/pith/RHV2BKAKJWN75WQMAE7DUKHNXK","bundle":"https://pith.science/pith/RHV2BKAKJWN75WQMAE7DUKHNXK/bundle.json","state":"https://pith.science/pith/RHV2BKAKJWN75WQMAE7DUKHNXK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHV2BKAKJWN75WQMAE7DUKHNXK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RHV2BKAKJWN75WQMAE7DUKHNXK","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":"80ea778c6d2d33a444e4e985eea56dc4326ba682cba053baf8d482f4269feb44","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-16T10:59:39Z","title_canon_sha256":"e20b6545b565f5c75cb00bb19562ad5b5c5fcb81582d6eb4f58e62daa9787887"},"schema_version":"1.0","source":{"id":"2302.08215","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08215","created_at":"2026-07-05T06:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08215v2","created_at":"2026-07-05T06:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08215","created_at":"2026-07-05T06:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"RHV2BKAKJWN7","created_at":"2026-07-05T06:17:46Z"},{"alias_kind":"pith_short_16","alias_value":"RHV2BKAKJWN75WQM","created_at":"2026-07-05T06:17:46Z"},{"alias_kind":"pith_short_8","alias_value":"RHV2BKAK","created_at":"2026-07-05T06:17:46Z"}],"graph_snapshots":[{"event_id":"sha256:197b477cf231c4187b6cb5361154c692e468db0a9a88f7b0fa34eebec6e81c25","target":"graph","created_at":"2026-07-05T06:17:46Z","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/2302.08215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning language models with preferences can be posed as approximating a target distribution representing some desired behavior. Existing approaches differ both in the functional form of the target distribution and the algorithm used to approximate it. For instance, Reinforcement Learning from Human Feedback (RLHF) corresponds to minimizing a reverse KL from an implicit target distribution arising from a KL penalty in the objective. On the other hand, Generative Distributional Control (GDC) has an explicit target distribution and minimizes a forward KL from it using the Distributional Policy ","authors_text":"Dongyoung Go, Germ\\'an Kruszewski, Jos Rozen, Marc Dymetman, Nahyeon Ryu, Tomasz Korbak","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-16T10:59:39Z","title":"Aligning Language Models with Preferences through f-divergence Minimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08215","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:f52ebd9a6365bed24064e0dd1c3fd0d54c743c76779826374a7d66963cee6282","target":"record","created_at":"2026-07-05T06:17:46Z","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":"80ea778c6d2d33a444e4e985eea56dc4326ba682cba053baf8d482f4269feb44","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-16T10:59:39Z","title_canon_sha256":"e20b6545b565f5c75cb00bb19562ad5b5c5fcb81582d6eb4f58e62daa9787887"},"schema_version":"1.0","source":{"id":"2302.08215","kind":"arxiv","version":2}},"canonical_sha256":"89eba0a80a4d9bfeda0c013e3a28edba80f37ef9a6db430aacaee0059f33d637","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89eba0a80a4d9bfeda0c013e3a28edba80f37ef9a6db430aacaee0059f33d637","first_computed_at":"2026-07-05T06:17:46.424473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:46.424473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"varCiR6tTtnzSrebG9JRSacVZcqkfF5hbalZblLSP2TSyoghfCfmcLt+x6OYvwpJJfMPhD628Frhwp0m16UEAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:46.424919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.08215","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f52ebd9a6365bed24064e0dd1c3fd0d54c743c76779826374a7d66963cee6282","sha256:197b477cf231c4187b6cb5361154c692e468db0a9a88f7b0fa34eebec6e81c25"],"state_sha256":"c84ec8c852b914f4e05421e461103faf0a3485952d6b4b240458e01a7c750de6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GJ8GV0L86dTL0oOcw9w+moUsrBHNlJJerxC7rB/3MmcHa8HnwlFeOwtzYx9FLqfCM7TUSW0Q0db+jS3YSjaDDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:27:20.664018Z","bundle_sha256":"7b526f62c73d9bfc3e2a969788cb8a16968386e3fb7fc0ee6d8bfeb1cbc83208"}}