{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:673HPHQAODZJIAUXVPQXIQ5LYA","short_pith_number":"pith:673HPHQA","canonical_record":{"source":{"id":"2508.08509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T22:40:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c5fff1826f256df152a43955364e368e9036ab92bd2fde8841936c8899f781e","abstract_canon_sha256":"de124a1369a016d258b92ccb8ecdb8aab369abc6657ed6c663685b44abb1fceb"},"schema_version":"1.0"},"canonical_sha256":"f7f6779e0070f2940297abe17443abc00d056841aadb5d61aedf4a969024385e","source":{"kind":"arxiv","id":"2508.08509","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.08509","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"2508.08509v1","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08509","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"673HPHQAODZJ","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"pith_short_16","alias_value":"673HPHQAODZJIAUX","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"pith_short_8","alias_value":"673HPHQA","created_at":"2026-07-05T11:52:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:673HPHQAODZJIAUXVPQXIQ5LYA","target":"record","payload":{"canonical_record":{"source":{"id":"2508.08509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T22:40:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c5fff1826f256df152a43955364e368e9036ab92bd2fde8841936c8899f781e","abstract_canon_sha256":"de124a1369a016d258b92ccb8ecdb8aab369abc6657ed6c663685b44abb1fceb"},"schema_version":"1.0"},"canonical_sha256":"f7f6779e0070f2940297abe17443abc00d056841aadb5d61aedf4a969024385e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:29.830035Z","signature_b64":"F58zL4R6HeW/CL82GEMhj5hAB98mqKSppaGR4ObIgkFWSbB4IttKCu5d/9tMWAucufhg6bZ60MXZU4cDa4CYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7f6779e0070f2940297abe17443abc00d056841aadb5d61aedf4a969024385e","last_reissued_at":"2026-07-05T11:52:29.829559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:29.829559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.08509","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:52:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xvtaOd8TnRR04kD6xK2tZXd4aT43iueex5wca/e5TdsR6bdKJRCnhbUvHLEo09VSHGM8GWcGo6uTf3Gtykw6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:43:54.699967Z"},"content_sha256":"a7aa18d07f66ff8af37cef698db1396261c845af7e3beb750a7950ffa143d20a","schema_version":"1.0","event_id":"sha256:a7aa18d07f66ff8af37cef698db1396261c845af7e3beb750a7950ffa143d20a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:673HPHQAODZJIAUXVPQXIQ5LYA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aaron Bray, Anthony Hoogs, Arslan Basharat, Bharadwaj Ravichandran, Brian Hu, David Joy, Emily Veenhuis, Jadie Adams","submitted_at":"2025-08-11T22:40:31Z","abstract_excerpt":"Large language models (LLMs) are currently aligned using techniques such as reinforcement learning from human feedback (RLHF). However, these methods use scalar rewards that can only reflect user preferences on average. Pluralistic alignment instead seeks to capture diverse user preferences across a set of attributes, moving beyond just helpfulness and harmlessness. Toward this end, we propose a steerable pluralistic model based on few-shot comparative regression that can adapt to individual user preferences. Our approach leverages in-context learning and reasoning, grounded in a set of fine-g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08509","kind":"arxiv","version":1},"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/2508.08509/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":"2026-07-05T11:52:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sVxpHIAWs1NCzP8JwoAiBDRmt/MNNkeNvC5dWcK+lfJPAywaWBSS7gwep7XaVZMotF4zWQBjP0HwqkFYZPOHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:43:54.700268Z"},"content_sha256":"bd4231ce300cb08f34973ef8566bb53a325e554631cae16f27eb88dcc6840814","schema_version":"1.0","event_id":"sha256:bd4231ce300cb08f34973ef8566bb53a325e554631cae16f27eb88dcc6840814"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/673HPHQAODZJIAUXVPQXIQ5LYA/bundle.json","state_url":"https://pith.science/pith/673HPHQAODZJIAUXVPQXIQ5LYA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/673HPHQAODZJIAUXVPQXIQ5LYA/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":"2026-08-17T15:43:54Z","links":{"resolver":"https://pith.science/pith/673HPHQAODZJIAUXVPQXIQ5LYA","bundle":"https://pith.science/pith/673HPHQAODZJIAUXVPQXIQ5LYA/bundle.json","state":"https://pith.science/pith/673HPHQAODZJIAUXVPQXIQ5LYA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/673HPHQAODZJIAUXVPQXIQ5LYA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:673HPHQAODZJIAUXVPQXIQ5LYA","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":"de124a1369a016d258b92ccb8ecdb8aab369abc6657ed6c663685b44abb1fceb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T22:40:31Z","title_canon_sha256":"8c5fff1826f256df152a43955364e368e9036ab92bd2fde8841936c8899f781e"},"schema_version":"1.0","source":{"id":"2508.08509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.08509","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"2508.08509v1","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08509","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"673HPHQAODZJ","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"pith_short_16","alias_value":"673HPHQAODZJIAUX","created_at":"2026-07-05T11:52:29Z"},{"alias_kind":"pith_short_8","alias_value":"673HPHQA","created_at":"2026-07-05T11:52:29Z"}],"graph_snapshots":[{"event_id":"sha256:bd4231ce300cb08f34973ef8566bb53a325e554631cae16f27eb88dcc6840814","target":"graph","created_at":"2026-07-05T11:52:29Z","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/2508.08509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are currently aligned using techniques such as reinforcement learning from human feedback (RLHF). However, these methods use scalar rewards that can only reflect user preferences on average. Pluralistic alignment instead seeks to capture diverse user preferences across a set of attributes, moving beyond just helpfulness and harmlessness. Toward this end, we propose a steerable pluralistic model based on few-shot comparative regression that can adapt to individual user preferences. Our approach leverages in-context learning and reasoning, grounded in a set of fine-g","authors_text":"Aaron Bray, Anthony Hoogs, Arslan Basharat, Bharadwaj Ravichandran, Brian Hu, David Joy, Emily Veenhuis, Jadie Adams","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T22:40:31Z","title":"Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08509","kind":"arxiv","version":1},"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:a7aa18d07f66ff8af37cef698db1396261c845af7e3beb750a7950ffa143d20a","target":"record","created_at":"2026-07-05T11:52:29Z","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":"de124a1369a016d258b92ccb8ecdb8aab369abc6657ed6c663685b44abb1fceb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-11T22:40:31Z","title_canon_sha256":"8c5fff1826f256df152a43955364e368e9036ab92bd2fde8841936c8899f781e"},"schema_version":"1.0","source":{"id":"2508.08509","kind":"arxiv","version":1}},"canonical_sha256":"f7f6779e0070f2940297abe17443abc00d056841aadb5d61aedf4a969024385e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7f6779e0070f2940297abe17443abc00d056841aadb5d61aedf4a969024385e","first_computed_at":"2026-07-05T11:52:29.829559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:29.829559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F58zL4R6HeW/CL82GEMhj5hAB98mqKSppaGR4ObIgkFWSbB4IttKCu5d/9tMWAucufhg6bZ60MXZU4cDa4CYAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:29.830035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.08509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7aa18d07f66ff8af37cef698db1396261c845af7e3beb750a7950ffa143d20a","sha256:bd4231ce300cb08f34973ef8566bb53a325e554631cae16f27eb88dcc6840814"],"state_sha256":"0fe8ff1384526d212dd07fffe0cfd48109abf1fc390febe46564c2bc52829dee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQMMN7dEQNKXtR5kK7GfysqjtjfW8+8V5veelM6ekI/yfiw5cuvH37/O69RP+y/XhyxUfvVtt2z5Y4C2u4fXDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T15:43:54.702850Z","bundle_sha256":"5192be37b3a51539da7fd963b4d4340a4b6df1e8e2729612186ff925ce537b90"}}