{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SC5JP674CIUXVPVGXGW24XMH6L","short_pith_number":"pith:SC5JP674","canonical_record":{"source":{"id":"2406.15599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T18:57:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48d1a26caf8152e778f210930d216ea8a54f801b5b83d28c05ab4303d4f95d5c","abstract_canon_sha256":"4628beaa4e2aa1acb53750d94d8d4089713a54c2311cb9e189e15cd6b86298c4"},"schema_version":"1.0"},"canonical_sha256":"90ba97fbfc12297abea6b9adae5d87f2ecde644e3edff7d32000398c83f19916","source":{"kind":"arxiv","id":"2406.15599","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15599","created_at":"2026-07-05T10:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15599v2","created_at":"2026-07-05T10:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15599","created_at":"2026-07-05T10:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"SC5JP674CIUX","created_at":"2026-07-05T10:10:41Z"},{"alias_kind":"pith_short_16","alias_value":"SC5JP674CIUXVPVG","created_at":"2026-07-05T10:10:41Z"},{"alias_kind":"pith_short_8","alias_value":"SC5JP674","created_at":"2026-07-05T10:10:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SC5JP674CIUXVPVGXGW24XMH6L","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T18:57:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48d1a26caf8152e778f210930d216ea8a54f801b5b83d28c05ab4303d4f95d5c","abstract_canon_sha256":"4628beaa4e2aa1acb53750d94d8d4089713a54c2311cb9e189e15cd6b86298c4"},"schema_version":"1.0"},"canonical_sha256":"90ba97fbfc12297abea6b9adae5d87f2ecde644e3edff7d32000398c83f19916","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:41.407271Z","signature_b64":"Qeyl5G54NWT9phWUGIglKgu8edeb0huQHC7dSwwFC6SEo8Obk1QzFNhmCJbhmo/RABtHSFGCNf6yWQRjalWqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90ba97fbfc12297abea6b9adae5d87f2ecde644e3edff7d32000398c83f19916","last_reissued_at":"2026-07-05T10:10:41.406854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:41.406854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15599","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":"2026-07-05T10:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M0LnJQYNfEYpvtGNNWADiIzYHc/Gk/GwVG4jmK6hrdMaKCrftjlN8ZgBJrzO2ypFD87VqzcLXRlynCfAymF/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:03:47.816336Z"},"content_sha256":"c34974c4b6319f7e52a0389c2a50f6769ba4e045673a917ede7ce137bee3f20f","schema_version":"1.0","event_id":"sha256:c34974c4b6319f7e52a0389c2a50f6769ba4e045673a917ede7ce137bee3f20f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SC5JP674CIUXVPVGXGW24XMH6L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pareto-Optimal Learning from Preferences with Hidden Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lee Spector, Li Ding, Ryan Bahlous-Boldi, Scott Niekum","submitted_at":"2024-06-21T18:57:38Z","abstract_excerpt":"Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) leverages human preferences to achieve this alignment. However, when preferences are sourced from diverse populations, point estimates of reward can result in suboptimal performance or be unfair to specific groups. We propose Pareto Optimal Preference Learning (POPL), which enables pluralistic alignment by framing discrepant group preferences as objectives with potential trade-offs, aiming for policies that are Pareto-optimal on the preference dataset. P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15599","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/2406.15599/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":"2026-07-05T10:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f0JOpwlkm8/jIarYq/BXzmrRfh8y+AMgvB7ewP9bZXTW2bpLeJ5IwX5yG4ff6nMtTKOZqFsDla5E7WqaL4pHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:03:47.818330Z"},"content_sha256":"dbdb64d5d7a4477fe35ea30293251eccb14efb04f26aa2adbd1e4ce76f056eee","schema_version":"1.0","event_id":"sha256:dbdb64d5d7a4477fe35ea30293251eccb14efb04f26aa2adbd1e4ce76f056eee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SC5JP674CIUXVPVGXGW24XMH6L/bundle.json","state_url":"https://pith.science/pith/SC5JP674CIUXVPVGXGW24XMH6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SC5JP674CIUXVPVGXGW24XMH6L/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":"2026-08-16T07:03:47Z","links":{"resolver":"https://pith.science/pith/SC5JP674CIUXVPVGXGW24XMH6L","bundle":"https://pith.science/pith/SC5JP674CIUXVPVGXGW24XMH6L/bundle.json","state":"https://pith.science/pith/SC5JP674CIUXVPVGXGW24XMH6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SC5JP674CIUXVPVGXGW24XMH6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SC5JP674CIUXVPVGXGW24XMH6L","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":"4628beaa4e2aa1acb53750d94d8d4089713a54c2311cb9e189e15cd6b86298c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T18:57:38Z","title_canon_sha256":"48d1a26caf8152e778f210930d216ea8a54f801b5b83d28c05ab4303d4f95d5c"},"schema_version":"1.0","source":{"id":"2406.15599","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15599","created_at":"2026-07-05T10:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15599v2","created_at":"2026-07-05T10:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15599","created_at":"2026-07-05T10:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"SC5JP674CIUX","created_at":"2026-07-05T10:10:41Z"},{"alias_kind":"pith_short_16","alias_value":"SC5JP674CIUXVPVG","created_at":"2026-07-05T10:10:41Z"},{"alias_kind":"pith_short_8","alias_value":"SC5JP674","created_at":"2026-07-05T10:10:41Z"}],"graph_snapshots":[{"event_id":"sha256:dbdb64d5d7a4477fe35ea30293251eccb14efb04f26aa2adbd1e4ce76f056eee","target":"graph","created_at":"2026-07-05T10:10:41Z","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/2406.15599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) leverages human preferences to achieve this alignment. However, when preferences are sourced from diverse populations, point estimates of reward can result in suboptimal performance or be unfair to specific groups. We propose Pareto Optimal Preference Learning (POPL), which enables pluralistic alignment by framing discrepant group preferences as objectives with potential trade-offs, aiming for policies that are Pareto-optimal on the preference dataset. P","authors_text":"Lee Spector, Li Ding, Ryan Bahlous-Boldi, Scott Niekum","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T18:57:38Z","title":"Pareto-Optimal Learning from Preferences with Hidden Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15599","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:c34974c4b6319f7e52a0389c2a50f6769ba4e045673a917ede7ce137bee3f20f","target":"record","created_at":"2026-07-05T10:10:41Z","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":"4628beaa4e2aa1acb53750d94d8d4089713a54c2311cb9e189e15cd6b86298c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-21T18:57:38Z","title_canon_sha256":"48d1a26caf8152e778f210930d216ea8a54f801b5b83d28c05ab4303d4f95d5c"},"schema_version":"1.0","source":{"id":"2406.15599","kind":"arxiv","version":2}},"canonical_sha256":"90ba97fbfc12297abea6b9adae5d87f2ecde644e3edff7d32000398c83f19916","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90ba97fbfc12297abea6b9adae5d87f2ecde644e3edff7d32000398c83f19916","first_computed_at":"2026-07-05T10:10:41.406854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:41.406854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qeyl5G54NWT9phWUGIglKgu8edeb0huQHC7dSwwFC6SEo8Obk1QzFNhmCJbhmo/RABtHSFGCNf6yWQRjalWqAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:41.407271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15599","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c34974c4b6319f7e52a0389c2a50f6769ba4e045673a917ede7ce137bee3f20f","sha256:dbdb64d5d7a4477fe35ea30293251eccb14efb04f26aa2adbd1e4ce76f056eee"],"state_sha256":"b4dc32bb81aef38a12bd5bd33a85b28ed529732d9bba46a62bbe7c07f822b4f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eehiNZtAX9aSvhKj9JQNAfMd2piJZp4c1q665zsYXQCBfB2IQZzIR49OWHLOajugS/2jL/4DKgR1X2zXW+1mDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T07:03:47.825278Z","bundle_sha256":"1ad748541deb342cd316b98fe2fe529fd3895f2b805443f35da5c261509e1d4d"}}