{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E6HQPHG5FLFJU2C4ST7YGNYHR7","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":"58927a32056ed7bf0d06c941bf4ce450a085ce620f4af2ff390e07c614b9f777","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-10T14:13:59Z","title_canon_sha256":"44028748e4fc36c8cbbc804c715f9dae7307a3da4c36310dc5efb8037c1cf859"},"schema_version":"1.0","source":{"id":"2310.06648","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06648","created_at":"2026-07-05T11:17:31Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06648v3","created_at":"2026-07-05T11:17:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06648","created_at":"2026-07-05T11:17:31Z"},{"alias_kind":"pith_short_12","alias_value":"E6HQPHG5FLFJ","created_at":"2026-07-05T11:17:31Z"},{"alias_kind":"pith_short_16","alias_value":"E6HQPHG5FLFJU2C4","created_at":"2026-07-05T11:17:31Z"},{"alias_kind":"pith_short_8","alias_value":"E6HQPHG5","created_at":"2026-07-05T11:17:31Z"}],"graph_snapshots":[{"event_id":"sha256:44aab95daf8763d5474e0abd45884971faa7e7f7cfeb353dfdf214594e3b4145","target":"graph","created_at":"2026-07-05T11:17:31Z","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/2310.06648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diversity plays a significant role in many problems, such as ensemble learning, reinforcement learning, and combinatorial optimization. How to define the diversity measure is a longstanding problem. Many methods rely on expert experience to define a proper behavior space and then obtain the diversity measure, which is, however, challenging in many scenarios. In this paper, we propose the problem of learning a behavior space from human feedback and present a general method called Diversity from Human Feedback (DivHF) to solve it. DivHF learns a behavior descriptor consistent with human preferen","authors_text":"Chao Qian, Haobo Fu, Ke Xue, Peng Yang, Qiang Fu, Ren-Jian Wang, Yutong Wang","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-10T14:13:59Z","title":"Diversity from Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06648","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":"sha256:09db42d429e45b8aa8787fdc2141f2f029ad8b35a7a990c8c366586a99fb1506","target":"record","created_at":"2026-07-05T11:17:31Z","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":"58927a32056ed7bf0d06c941bf4ce450a085ce620f4af2ff390e07c614b9f777","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-10T14:13:59Z","title_canon_sha256":"44028748e4fc36c8cbbc804c715f9dae7307a3da4c36310dc5efb8037c1cf859"},"schema_version":"1.0","source":{"id":"2310.06648","kind":"arxiv","version":3}},"canonical_sha256":"278f079cdd2aca9a685c94ff8337078fd50155bd4534577a05b44f80c22905fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"278f079cdd2aca9a685c94ff8337078fd50155bd4534577a05b44f80c22905fc","first_computed_at":"2026-07-05T11:17:31.403929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:31.403929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lo0euObF3VWdudv5H8plahejyQokqF06T1NtDNimytnnSfGvcWykbEU9iio/bfb5H+1lxXmBX5K58ckOSMCDCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:31.404449Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06648","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09db42d429e45b8aa8787fdc2141f2f029ad8b35a7a990c8c366586a99fb1506","sha256:44aab95daf8763d5474e0abd45884971faa7e7f7cfeb353dfdf214594e3b4145"],"state_sha256":"70c053a137842f6f79484142c69cf722e70e47300cf8f6a4be6fe5c680fffea6"}