{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:X662LZJJMJRRO64MS6ZUH5N7DJ","short_pith_number":"pith:X662LZJJ","canonical_record":{"source":{"id":"2312.08358","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T18:51:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bb9ac2a0754658d3cb15384c0e6126ccf0bd3007448cdf9d2067c9933985f412","abstract_canon_sha256":"7296a150875687fc2d60c97bfa66a0b7389c37a60fef877a216198942b3c54bf"},"schema_version":"1.0"},"canonical_sha256":"bfbda5e5296263177b8c97b343f5bf1a72fe0380194698b01a234049fac1ee85","source":{"kind":"arxiv","id":"2312.08358","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08358","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08358v2","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08358","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_12","alias_value":"X662LZJJMJRR","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_16","alias_value":"X662LZJJMJRRO64M","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_8","alias_value":"X662LZJJ","created_at":"2026-07-05T08:08:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:X662LZJJMJRRO64MS6ZUH5N7DJ","target":"record","payload":{"canonical_record":{"source":{"id":"2312.08358","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T18:51:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bb9ac2a0754658d3cb15384c0e6126ccf0bd3007448cdf9d2067c9933985f412","abstract_canon_sha256":"7296a150875687fc2d60c97bfa66a0b7389c37a60fef877a216198942b3c54bf"},"schema_version":"1.0"},"canonical_sha256":"bfbda5e5296263177b8c97b343f5bf1a72fe0380194698b01a234049fac1ee85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:53.476691Z","signature_b64":"TAjj1xvl6fRj2sKFMO+j2O9EweCyxKM+v4Fb8daTK8PuQiasyrEzfHcpfLvA4RuAq1djMx1v0XES1ypGD+tODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfbda5e5296263177b8c97b343f5bf1a72fe0380194698b01a234049fac1ee85","last_reissued_at":"2026-07-05T08:08:53.476266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:53.476266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.08358","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":"2026-07-05T08:08:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vuswRIdgU0hVwhLYGIicRTg2S/C32MUrcw9E/4sauGEvAw0+jAXzF7wZgRl3ml1H4gCbUOZnDqWEMTWdWbPnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:57:51.663932Z"},"content_sha256":"87eb0f3c26a78d97d93062a65fcfa93fd69dac3607d07533f4eaf0ca5276b9ca","schema_version":"1.0","event_id":"sha256:87eb0f3c26a78d97d93062a65fcfa93fd69dac3607d07533f4eaf0ca5276b9ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:X662LZJJMJRRO64MS6ZUH5N7DJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anand Siththaranjan, Cassidy Laidlaw, Dylan Hadfield-Menell","submitted_at":"2023-12-13T18:51:34Z","abstract_excerpt":"In practice, preference learning from human feedback depends on incomplete data with hidden context. Hidden context refers to data that affects the feedback received, but which is not represented in the data used to train a preference model. This captures common issues of data collection, such as having human annotators with varied preferences, cognitive processes that result in seemingly irrational behavior, and combining data labeled according to different criteria. We prove that standard applications of preference learning, including reinforcement learning from human feedback (RLHF), implic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08358","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/2312.08358/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":"2026-07-05T08:08:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nDKSfJQvTDtQzv+wTGysmIdDjVISxUQAEALsPrrrq6nGCiC+160X4y7kt89pWNWuEE4PwCPOczXH9+96RfNbBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:57:51.664589Z"},"content_sha256":"4d2708bc537ee8a6ba933fe67ead22dccc64170eb1fdd5aa78777eb35470afe5","schema_version":"1.0","event_id":"sha256:4d2708bc537ee8a6ba933fe67ead22dccc64170eb1fdd5aa78777eb35470afe5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X662LZJJMJRRO64MS6ZUH5N7DJ/bundle.json","state_url":"https://pith.science/pith/X662LZJJMJRRO64MS6ZUH5N7DJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X662LZJJMJRRO64MS6ZUH5N7DJ/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":"2026-08-08T22:57:51Z","links":{"resolver":"https://pith.science/pith/X662LZJJMJRRO64MS6ZUH5N7DJ","bundle":"https://pith.science/pith/X662LZJJMJRRO64MS6ZUH5N7DJ/bundle.json","state":"https://pith.science/pith/X662LZJJMJRRO64MS6ZUH5N7DJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X662LZJJMJRRO64MS6ZUH5N7DJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:X662LZJJMJRRO64MS6ZUH5N7DJ","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":"7296a150875687fc2d60c97bfa66a0b7389c37a60fef877a216198942b3c54bf","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T18:51:34Z","title_canon_sha256":"bb9ac2a0754658d3cb15384c0e6126ccf0bd3007448cdf9d2067c9933985f412"},"schema_version":"1.0","source":{"id":"2312.08358","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08358","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08358v2","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08358","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_12","alias_value":"X662LZJJMJRR","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_16","alias_value":"X662LZJJMJRRO64M","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_8","alias_value":"X662LZJJ","created_at":"2026-07-05T08:08:53Z"}],"graph_snapshots":[{"event_id":"sha256:4d2708bc537ee8a6ba933fe67ead22dccc64170eb1fdd5aa78777eb35470afe5","target":"graph","created_at":"2026-07-05T08:08:53Z","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/2312.08358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In practice, preference learning from human feedback depends on incomplete data with hidden context. Hidden context refers to data that affects the feedback received, but which is not represented in the data used to train a preference model. This captures common issues of data collection, such as having human annotators with varied preferences, cognitive processes that result in seemingly irrational behavior, and combining data labeled according to different criteria. We prove that standard applications of preference learning, including reinforcement learning from human feedback (RLHF), implic","authors_text":"Anand Siththaranjan, Cassidy Laidlaw, Dylan Hadfield-Menell","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T18:51:34Z","title":"Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08358","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":"sha256:87eb0f3c26a78d97d93062a65fcfa93fd69dac3607d07533f4eaf0ca5276b9ca","target":"record","created_at":"2026-07-05T08:08:53Z","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":"7296a150875687fc2d60c97bfa66a0b7389c37a60fef877a216198942b3c54bf","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T18:51:34Z","title_canon_sha256":"bb9ac2a0754658d3cb15384c0e6126ccf0bd3007448cdf9d2067c9933985f412"},"schema_version":"1.0","source":{"id":"2312.08358","kind":"arxiv","version":2}},"canonical_sha256":"bfbda5e5296263177b8c97b343f5bf1a72fe0380194698b01a234049fac1ee85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfbda5e5296263177b8c97b343f5bf1a72fe0380194698b01a234049fac1ee85","first_computed_at":"2026-07-05T08:08:53.476266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:53.476266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TAjj1xvl6fRj2sKFMO+j2O9EweCyxKM+v4Fb8daTK8PuQiasyrEzfHcpfLvA4RuAq1djMx1v0XES1ypGD+tODg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:53.476691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08358","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87eb0f3c26a78d97d93062a65fcfa93fd69dac3607d07533f4eaf0ca5276b9ca","sha256:4d2708bc537ee8a6ba933fe67ead22dccc64170eb1fdd5aa78777eb35470afe5"],"state_sha256":"0f336ce0479e9e851cd7d1f3d54b0b6ee4d41e4b55ec20428a5e4fcbb55d0408"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JFqA73zqssHTXrEMFYEhOjGFqYO1hs6G38VikY7cxm4clnD2q/fOakXQ6IS6Wg3/ZFacIPILF35LPp3zc0B9Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:57:51.673263Z","bundle_sha256":"abc852f8bcfd02f525036c4ab343d79829dcf28782c0d782824ff9a85c9b91e3"}}