{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:V7DIRKHF63DV4UZRGGQ3RZHDUF","short_pith_number":"pith:V7DIRKHF","canonical_record":{"source":{"id":"2402.08925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T03:56:27Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"ce17d20d5e051d979c0f9718567004098839f8a9c0c00e9b16aed7cd5051eb75","abstract_canon_sha256":"51ba2dfdf9f4f0b249e052bae31dfbf2a07d67af960f9f29358f8afe0746466b"},"schema_version":"1.0"},"canonical_sha256":"afc688a8e5f6c75e533131a1b8e4e3a1549661de586e241ce589ec2255a08724","source":{"kind":"arxiv","id":"2402.08925","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08925","created_at":"2026-07-05T09:54:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08925v2","created_at":"2026-07-05T09:54:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08925","created_at":"2026-07-05T09:54:01Z"},{"alias_kind":"pith_short_12","alias_value":"V7DIRKHF63DV","created_at":"2026-07-05T09:54:01Z"},{"alias_kind":"pith_short_16","alias_value":"V7DIRKHF63DV4UZR","created_at":"2026-07-05T09:54:01Z"},{"alias_kind":"pith_short_8","alias_value":"V7DIRKHF","created_at":"2026-07-05T09:54:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:V7DIRKHF63DV4UZRGGQ3RZHDUF","target":"record","payload":{"canonical_record":{"source":{"id":"2402.08925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T03:56:27Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"ce17d20d5e051d979c0f9718567004098839f8a9c0c00e9b16aed7cd5051eb75","abstract_canon_sha256":"51ba2dfdf9f4f0b249e052bae31dfbf2a07d67af960f9f29358f8afe0746466b"},"schema_version":"1.0"},"canonical_sha256":"afc688a8e5f6c75e533131a1b8e4e3a1549661de586e241ce589ec2255a08724","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:01.061438Z","signature_b64":"I9Ai+6w3Tm2GIdAtb0oHPi/i4GcAkfB9q38Q1uRq4ytt53EFeaY0Oa3YMwGFyVJHOuTitEE/wPyuBN0xwG8CAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afc688a8e5f6c75e533131a1b8e4e3a1549661de586e241ce589ec2255a08724","last_reissued_at":"2026-07-05T09:54:01.060976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:01.060976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.08925","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":"2026-07-05T09:54:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iVYhSqblNsTYVMexEwZ9lzGCWsWjIIRoj0YPDVyrlZmXP4n97eDQV3vAWmrXUdS9OJtSsPKLj6beUPAP34bEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:26:11.038618Z"},"content_sha256":"d812801fc4ba5a12948f6bb4c34b4618dc4640a3d3aba40d161091ea86fa06f7","schema_version":"1.0","event_id":"sha256:d812801fc4ba5a12948f6bb4c34b4618dc4640a3d3aba40d161091ea86fa06f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:V7DIRKHF63DV4UZRGGQ3RZHDUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaxMin-RLHF: Alignment with Diverse Human Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CL","authors_text":"Alec Koppel, Amrit Singh Bedi, Dinesh Manocha, Furong Huang, Hui Yuan, Jiahao Qiu, Mengdi Wang, Souradip Chakraborty","submitted_at":"2024-02-14T03:56:27Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an approach overlooks the rich diversity of human preferences inherent in data collected from multiple users. In this work, we first derive an impossibility result of alignment with single reward RLHF, thereby highlighting its insufficiency in representing diverse human preferences. To provide an equitable solution to the problem, we learn a mixture of preference distributions via an expectation-maximization algorithm and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08925","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/2402.08925/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":"2026-07-05T09:54:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pDNuhyTUxZ+uDCZapI1sLoyWg6WzPzUFr6GbExyoICgy+j9O/fCgkIZZdqY7XH0PdA8Uy71PrEBkf5TVzV52Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:26:11.039147Z"},"content_sha256":"4b1fc59903d0ae36996bbd16af837bb85a965f42268f4a4260a312065ef0fbd1","schema_version":"1.0","event_id":"sha256:4b1fc59903d0ae36996bbd16af837bb85a965f42268f4a4260a312065ef0fbd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V7DIRKHF63DV4UZRGGQ3RZHDUF/bundle.json","state_url":"https://pith.science/pith/V7DIRKHF63DV4UZRGGQ3RZHDUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V7DIRKHF63DV4UZRGGQ3RZHDUF/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":"2026-08-09T17:26:11Z","links":{"resolver":"https://pith.science/pith/V7DIRKHF63DV4UZRGGQ3RZHDUF","bundle":"https://pith.science/pith/V7DIRKHF63DV4UZRGGQ3RZHDUF/bundle.json","state":"https://pith.science/pith/V7DIRKHF63DV4UZRGGQ3RZHDUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V7DIRKHF63DV4UZRGGQ3RZHDUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V7DIRKHF63DV4UZRGGQ3RZHDUF","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":"51ba2dfdf9f4f0b249e052bae31dfbf2a07d67af960f9f29358f8afe0746466b","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T03:56:27Z","title_canon_sha256":"ce17d20d5e051d979c0f9718567004098839f8a9c0c00e9b16aed7cd5051eb75"},"schema_version":"1.0","source":{"id":"2402.08925","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08925","created_at":"2026-07-05T09:54:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08925v2","created_at":"2026-07-05T09:54:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08925","created_at":"2026-07-05T09:54:01Z"},{"alias_kind":"pith_short_12","alias_value":"V7DIRKHF63DV","created_at":"2026-07-05T09:54:01Z"},{"alias_kind":"pith_short_16","alias_value":"V7DIRKHF63DV4UZR","created_at":"2026-07-05T09:54:01Z"},{"alias_kind":"pith_short_8","alias_value":"V7DIRKHF","created_at":"2026-07-05T09:54:01Z"}],"graph_snapshots":[{"event_id":"sha256:4b1fc59903d0ae36996bbd16af837bb85a965f42268f4a4260a312065ef0fbd1","target":"graph","created_at":"2026-07-05T09:54:01Z","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/2402.08925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an approach overlooks the rich diversity of human preferences inherent in data collected from multiple users. In this work, we first derive an impossibility result of alignment with single reward RLHF, thereby highlighting its insufficiency in representing diverse human preferences. To provide an equitable solution to the problem, we learn a mixture of preference distributions via an expectation-maximization algorithm and","authors_text":"Alec Koppel, Amrit Singh Bedi, Dinesh Manocha, Furong Huang, Hui Yuan, Jiahao Qiu, Mengdi Wang, Souradip Chakraborty","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T03:56:27Z","title":"MaxMin-RLHF: Alignment with Diverse Human Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08925","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:d812801fc4ba5a12948f6bb4c34b4618dc4640a3d3aba40d161091ea86fa06f7","target":"record","created_at":"2026-07-05T09:54:01Z","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":"51ba2dfdf9f4f0b249e052bae31dfbf2a07d67af960f9f29358f8afe0746466b","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-14T03:56:27Z","title_canon_sha256":"ce17d20d5e051d979c0f9718567004098839f8a9c0c00e9b16aed7cd5051eb75"},"schema_version":"1.0","source":{"id":"2402.08925","kind":"arxiv","version":2}},"canonical_sha256":"afc688a8e5f6c75e533131a1b8e4e3a1549661de586e241ce589ec2255a08724","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afc688a8e5f6c75e533131a1b8e4e3a1549661de586e241ce589ec2255a08724","first_computed_at":"2026-07-05T09:54:01.060976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:01.060976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I9Ai+6w3Tm2GIdAtb0oHPi/i4GcAkfB9q38Q1uRq4ytt53EFeaY0Oa3YMwGFyVJHOuTitEE/wPyuBN0xwG8CAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:01.061438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08925","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d812801fc4ba5a12948f6bb4c34b4618dc4640a3d3aba40d161091ea86fa06f7","sha256:4b1fc59903d0ae36996bbd16af837bb85a965f42268f4a4260a312065ef0fbd1"],"state_sha256":"14f1e67e68eb30ca4083f00d855a1d43afa3fb9d44aadafe590498130320d8f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0LaD5GWKJAg7Segsa7aW9wVht8x5w7Gknbc2bq1507K54HGO1MW5qqrIf8ZROfmdsF/ClHbdnpAC+vnSWYPKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:26:11.043480Z","bundle_sha256":"5fc35184ab5c20c51f2fede7a1b6dcb9718768b415392a9ffe52e13688043b2b"}}