{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EIVUBE5MM3MNJQBLSULTVKBKL5","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":"5e08e2bb1c39ebd2318aec79e5b8dfcc02d47c5dfdfb9a97c59953fb7cc896ab","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-18T16:46:16Z","title_canon_sha256":"d4fec1698fb0f95d2aec699e99c972fe003e354dfbcf9ecc1bb9af5505663038"},"schema_version":"1.0","source":{"id":"2310.12103","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12103","created_at":"2026-07-05T08:26:59Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12103v3","created_at":"2026-07-05T08:26:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12103","created_at":"2026-07-05T08:26:59Z"},{"alias_kind":"pith_short_12","alias_value":"EIVUBE5MM3MN","created_at":"2026-07-05T08:26:59Z"},{"alias_kind":"pith_short_16","alias_value":"EIVUBE5MM3MNJQBL","created_at":"2026-07-05T08:26:59Z"},{"alias_kind":"pith_short_8","alias_value":"EIVUBE5M","created_at":"2026-07-05T08:26:59Z"}],"graph_snapshots":[{"event_id":"sha256:9fc6171edd995db860bc80966d1c685f1bcb8c47cd56219511c6c12232791c05","target":"graph","created_at":"2026-07-05T08:26:59Z","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/2310.12103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has shown potential in qualitative tasks where easily defined performance measures are lacking. However, there are drawbacks when RLHF is commonly used to optimize for average human preferences, especially in generative tasks that demand diverse model responses. Meanwhile, Quality Diversity (QD) algorithms excel at identifying diverse and high-quality solutions but often rely on manually crafted diversity metrics. This paper introduces Quality Diversity through Human Feedback (QDHF), a novel approach that progressively infers diversity metrics ","authors_text":"Jeff Clune, Jenny Zhang, Joel Lehman, Lee Spector, Li Ding","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-18T16:46:16Z","title":"Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12103","kind":"arxiv","version":3},"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":"sha256:242e7f8f7f2f1f25e6fa894962a831316e34ea5f3e7c5ba2976272630ddcf080","target":"record","created_at":"2026-07-05T08:26:59Z","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":"5e08e2bb1c39ebd2318aec79e5b8dfcc02d47c5dfdfb9a97c59953fb7cc896ab","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-18T16:46:16Z","title_canon_sha256":"d4fec1698fb0f95d2aec699e99c972fe003e354dfbcf9ecc1bb9af5505663038"},"schema_version":"1.0","source":{"id":"2310.12103","kind":"arxiv","version":3}},"canonical_sha256":"222b4093ac66d8d4c02b95173aa82a5f7a5a0093ceaa5df1c0ef56e5ebcff001","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"222b4093ac66d8d4c02b95173aa82a5f7a5a0093ceaa5df1c0ef56e5ebcff001","first_computed_at":"2026-07-05T08:26:59.582680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:59.582680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fVowbKJ+weIU6zWTfl/vr/ZTYY/J/lRrlUT6JvdA8IpfBmkAUDHVB4ZVJi3+w3Ep5qxcinAMvxgHqAaGyIJBDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:59.583100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12103","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:242e7f8f7f2f1f25e6fa894962a831316e34ea5f3e7c5ba2976272630ddcf080","sha256:9fc6171edd995db860bc80966d1c685f1bcb8c47cd56219511c6c12232791c05"],"state_sha256":"db3a2ea14502d39ea2e9c1c454b7e54db747132cf695656d05d779d7158399eb"}