{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SVCSQVGDMJL2RJ7AEAD4BOJFDS","short_pith_number":"pith:SVCSQVGD","canonical_record":{"source":{"id":"2405.14758","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2024-05-23T16:29:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"563d0af19d80374d62356907ad180f4ddc58c712e218fa1992fb6004c07bef78","abstract_canon_sha256":"3b08b6b889f5863c37c281c3ac34e2c8799a989d945600e1e297307e39835f7a"},"schema_version":"1.0"},"canonical_sha256":"95452854c36257a8a7e02007c0b9251ca2ed3e5c0870431d36fa7b9ef69eeb87","source":{"kind":"arxiv","id":"2405.14758","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14758","created_at":"2026-07-05T09:32:31Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14758v2","created_at":"2026-07-05T09:32:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14758","created_at":"2026-07-05T09:32:31Z"},{"alias_kind":"pith_short_12","alias_value":"SVCSQVGDMJL2","created_at":"2026-07-05T09:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"SVCSQVGDMJL2RJ7A","created_at":"2026-07-05T09:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"SVCSQVGD","created_at":"2026-07-05T09:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SVCSQVGDMJL2RJ7AEAD4BOJFDS","target":"record","payload":{"canonical_record":{"source":{"id":"2405.14758","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2024-05-23T16:29:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"563d0af19d80374d62356907ad180f4ddc58c712e218fa1992fb6004c07bef78","abstract_canon_sha256":"3b08b6b889f5863c37c281c3ac34e2c8799a989d945600e1e297307e39835f7a"},"schema_version":"1.0"},"canonical_sha256":"95452854c36257a8a7e02007c0b9251ca2ed3e5c0870431d36fa7b9ef69eeb87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:31.917461Z","signature_b64":"zJYDClx7f115poHtkvqARP+WmqLq3Rq2O3JQfxm6HHeSv7D+XEmdvo1oj6O9NRg+FVu1+S3Mj2mvVFhFlMiwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95452854c36257a8a7e02007c0b9251ca2ed3e5c0870431d36fa7b9ef69eeb87","last_reissued_at":"2026-07-05T09:32:31.916938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:31.916938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.14758","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":"2026-07-05T09:32:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IzDTKe1Vw3VwORHkfNiJPA+Yy8gxw4r3uZOWVofvY1gdcFt3rhXM/ea/XzS3lJnUnvvsSw8BVAxu35CRucNOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:39:07.027038Z"},"content_sha256":"106c1ff1df38896d22b87287c687f96c773375cac92d3ec483c4009711772836","schema_version":"1.0","event_id":"sha256:106c1ff1df38896d22b87287c687f96c773375cac92d3ec483c4009711772836"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SVCSQVGDMJL2RJ7AEAD4BOJFDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Axioms for AI Alignment from Human Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.GT","authors_text":"Ariel D. Procaccia, Daniel Halpern, Evi Micha, Itai Shapira, Junlin Wu, Luise Ge, Yevgeniy Vorobeychik","submitted_at":"2024-05-23T16:29:29Z","abstract_excerpt":"In the context of reinforcement learning from human feedback (RLHF), the reward function is generally derived from maximum likelihood estimation of a random utility model based on pairwise comparisons made by humans. The problem of learning a reward function is one of preference aggregation that, we argue, largely falls within the scope of social choice theory. From this perspective, we can evaluate different aggregation methods via established axioms, examining whether these methods meet or fail well-known standards. We demonstrate that both the Bradley-Terry-Luce Model and its broad generali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14758","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/2405.14758/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":"2026-07-05T09:32:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3HddgeGri1ctY8Yb5wubGQ1eF64S4TTHPXLkQXgubfIqnLxunJd7udlbXt2t65mM7FqoSqYtojias6QCK44IDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:39:07.028966Z"},"content_sha256":"1058d6b50cb647431fc09113b2f7d5a42cbe535fd6b4aebe4d888e42662b5e82","schema_version":"1.0","event_id":"sha256:1058d6b50cb647431fc09113b2f7d5a42cbe535fd6b4aebe4d888e42662b5e82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SVCSQVGDMJL2RJ7AEAD4BOJFDS/bundle.json","state_url":"https://pith.science/pith/SVCSQVGDMJL2RJ7AEAD4BOJFDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SVCSQVGDMJL2RJ7AEAD4BOJFDS/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":"2026-08-08T21:39:07Z","links":{"resolver":"https://pith.science/pith/SVCSQVGDMJL2RJ7AEAD4BOJFDS","bundle":"https://pith.science/pith/SVCSQVGDMJL2RJ7AEAD4BOJFDS/bundle.json","state":"https://pith.science/pith/SVCSQVGDMJL2RJ7AEAD4BOJFDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SVCSQVGDMJL2RJ7AEAD4BOJFDS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SVCSQVGDMJL2RJ7AEAD4BOJFDS","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":"3b08b6b889f5863c37c281c3ac34e2c8799a989d945600e1e297307e39835f7a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2024-05-23T16:29:29Z","title_canon_sha256":"563d0af19d80374d62356907ad180f4ddc58c712e218fa1992fb6004c07bef78"},"schema_version":"1.0","source":{"id":"2405.14758","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14758","created_at":"2026-07-05T09:32:31Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14758v2","created_at":"2026-07-05T09:32:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14758","created_at":"2026-07-05T09:32:31Z"},{"alias_kind":"pith_short_12","alias_value":"SVCSQVGDMJL2","created_at":"2026-07-05T09:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"SVCSQVGDMJL2RJ7A","created_at":"2026-07-05T09:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"SVCSQVGD","created_at":"2026-07-05T09:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:1058d6b50cb647431fc09113b2f7d5a42cbe535fd6b4aebe4d888e42662b5e82","target":"graph","created_at":"2026-07-05T09:32:31Z","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/2405.14758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the context of reinforcement learning from human feedback (RLHF), the reward function is generally derived from maximum likelihood estimation of a random utility model based on pairwise comparisons made by humans. The problem of learning a reward function is one of preference aggregation that, we argue, largely falls within the scope of social choice theory. From this perspective, we can evaluate different aggregation methods via established axioms, examining whether these methods meet or fail well-known standards. We demonstrate that both the Bradley-Terry-Luce Model and its broad generali","authors_text":"Ariel D. Procaccia, Daniel Halpern, Evi Micha, Itai Shapira, Junlin Wu, Luise Ge, Yevgeniy Vorobeychik","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2024-05-23T16:29:29Z","title":"Axioms for AI Alignment from Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14758","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":"sha256:106c1ff1df38896d22b87287c687f96c773375cac92d3ec483c4009711772836","target":"record","created_at":"2026-07-05T09:32:31Z","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":"3b08b6b889f5863c37c281c3ac34e2c8799a989d945600e1e297307e39835f7a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2024-05-23T16:29:29Z","title_canon_sha256":"563d0af19d80374d62356907ad180f4ddc58c712e218fa1992fb6004c07bef78"},"schema_version":"1.0","source":{"id":"2405.14758","kind":"arxiv","version":2}},"canonical_sha256":"95452854c36257a8a7e02007c0b9251ca2ed3e5c0870431d36fa7b9ef69eeb87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95452854c36257a8a7e02007c0b9251ca2ed3e5c0870431d36fa7b9ef69eeb87","first_computed_at":"2026-07-05T09:32:31.916938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:31.916938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zJYDClx7f115poHtkvqARP+WmqLq3Rq2O3JQfxm6HHeSv7D+XEmdvo1oj6O9NRg+FVu1+S3Mj2mvVFhFlMiwCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:31.917461Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14758","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:106c1ff1df38896d22b87287c687f96c773375cac92d3ec483c4009711772836","sha256:1058d6b50cb647431fc09113b2f7d5a42cbe535fd6b4aebe4d888e42662b5e82"],"state_sha256":"2ea19cdd773978de51eb40bb423dbe5cc41e4a4746155352c9a4777a73367f86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zRVoFjlFkvTiYH0ZLKTPczScyVIDcGwFcwWGv1JjBsk1y/crWWQHxuF1UsKVRDGiJrjWFDjZ46B5acQCSdS2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:39:07.181777Z","bundle_sha256":"8536140b0081e4fb42931ffb4cf59017eb293a76aead7f9116cc3c4a3e9eae26"}}