{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R6ZQDSCQ2XKNV32OAMEW7KHY2C","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":"d041ddd80fd5ec9f9cc523d897dbaaf287e06778ecc8227890dcee0ec92cd9a5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-16T12:16:10Z","title_canon_sha256":"7ecd0f2d7245c7ce57b1d6a0013bf08cbcc4ec6222fc35812a66747884fdb2ed"},"schema_version":"1.0","source":{"id":"2504.12016","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12016","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12016v2","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12016","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_12","alias_value":"R6ZQDSCQ2XKN","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_16","alias_value":"R6ZQDSCQ2XKNV32O","created_at":"2026-07-05T11:38:28Z"},{"alias_kind":"pith_short_8","alias_value":"R6ZQDSCQ","created_at":"2026-07-05T11:38:28Z"}],"graph_snapshots":[{"event_id":"sha256:4338b91c8eff53a425b4d1eab35fefc2871a2b76a76da35370fd6bd4f77c626b","target":"graph","created_at":"2026-07-05T11:38:28Z","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/2504.12016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Collecting human preference feedback is often expensive, leading recent works to develop principled algorithms to select them more efficiently. However, these works assume that the underlying reward function is linear, an assumption that does not hold in many real-life applications, such as online recommendation and LLM alignment. To address this limitation, we propose Neural-ADB, an algorithm based on the neural contextual dueling bandit framework that provides a principled and practical method for collecting human preference feedback when the underlying latent reward function is non-linear. ","authors_text":"Arun Verma, Bryan Kian Hsiang Low, Daniela Rus, Xiaoqiang Lin, Zhongxiang Dai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-16T12:16:10Z","title":"Active Human Feedback Collection via Neural Contextual Dueling Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12016","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:b6ce28b35558dfca364c3149464299e7ee1c4fd09378ef91973e4dcd84ad7589","target":"record","created_at":"2026-07-05T11:38:28Z","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":"d041ddd80fd5ec9f9cc523d897dbaaf287e06778ecc8227890dcee0ec92cd9a5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-16T12:16:10Z","title_canon_sha256":"7ecd0f2d7245c7ce57b1d6a0013bf08cbcc4ec6222fc35812a66747884fdb2ed"},"schema_version":"1.0","source":{"id":"2504.12016","kind":"arxiv","version":2}},"canonical_sha256":"8fb301c850d5d4daef4e03096fa8f8d08146251ffdc770eb98cdefdd348cc678","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fb301c850d5d4daef4e03096fa8f8d08146251ffdc770eb98cdefdd348cc678","first_computed_at":"2026-07-05T11:38:28.756435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:28.756435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iy6mAWftLxGkeBDovbIxefqavHv9uUJ3OM32XZsBTPWLNHJASSC7rwpzBRBg6YigG7lsh0N6dQuyXijo7k9aAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:28.756985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12016","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6ce28b35558dfca364c3149464299e7ee1c4fd09378ef91973e4dcd84ad7589","sha256:4338b91c8eff53a425b4d1eab35fefc2871a2b76a76da35370fd6bd4f77c626b"],"state_sha256":"66290dbbe5be1427a5aac2b8c4b4a2f0d3fd001bb5eea913c27877f12f345387"}