{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BLTQSWJLL6MIARSL622J73OABR","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":"d65092d7ef5d4ca74a8f7d5154000865ce0c330a2d86a1008c5c7cbf1d9dc520","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-27T04:06:17Z","title_canon_sha256":"64bb72c5d176f300020d40c031be2e605ae3985770d0df7e77408dea13d7a0b9"},"schema_version":"1.0","source":{"id":"2302.13507","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.13507","created_at":"2026-07-05T05:45:47Z"},{"alias_kind":"arxiv_version","alias_value":"2302.13507v1","created_at":"2026-07-05T05:45:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13507","created_at":"2026-07-05T05:45:47Z"},{"alias_kind":"pith_short_12","alias_value":"BLTQSWJLL6MI","created_at":"2026-07-05T05:45:47Z"},{"alias_kind":"pith_short_16","alias_value":"BLTQSWJLL6MIARSL","created_at":"2026-07-05T05:45:47Z"},{"alias_kind":"pith_short_8","alias_value":"BLTQSWJL","created_at":"2026-07-05T05:45:47Z"}],"graph_snapshots":[{"event_id":"sha256:665ae7a60848ae9488cca88d7bd00bfa44f388345ae16fe4baac9d68de6f0935","target":"graph","created_at":"2026-07-05T05:45:47Z","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/2302.13507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robot policies need to adapt to human preferences and/or new environments. Human experts may have the domain knowledge required to help robots achieve this adaptation. However, existing works often require costly offline re-training on human feedback, and those feedback usually need to be frequent and too complex for the humans to reliably provide. To avoid placing undue burden on human experts and allow quick adaptation in critical real-world situations, we propose designing and sparingly presenting easy-to-answer pairwise action preference queries in an online fashion. Our approach designs q","authors_text":"Dorsa Sadigh, Erdem B{\\i}y{\\i}k, Vivek Myers","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-27T04:06:17Z","title":"Active Reward Learning from Online Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13507","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":"sha256:35f691ea26b0eff5bdbf096fa3c033bc584984bb6de7ff26e084635b98b0a59d","target":"record","created_at":"2026-07-05T05:45:47Z","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":"d65092d7ef5d4ca74a8f7d5154000865ce0c330a2d86a1008c5c7cbf1d9dc520","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-27T04:06:17Z","title_canon_sha256":"64bb72c5d176f300020d40c031be2e605ae3985770d0df7e77408dea13d7a0b9"},"schema_version":"1.0","source":{"id":"2302.13507","kind":"arxiv","version":1}},"canonical_sha256":"0ae709592b5f9880464bf6b49fedc00c63c74f1aa1c9b06a7aeee27bb627e1e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ae709592b5f9880464bf6b49fedc00c63c74f1aa1c9b06a7aeee27bb627e1e5","first_computed_at":"2026-07-05T05:45:47.947960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:47.947960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hcJ+Up5KIEt09Ako6Nfbd01UYoUu7pxF/wnw/6UbIMwYu1GW0kD1v7Z+KWo+8Z06tliZ1C+f69yjZ/jmAUm9DA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:47.948422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.13507","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35f691ea26b0eff5bdbf096fa3c033bc584984bb6de7ff26e084635b98b0a59d","sha256:665ae7a60848ae9488cca88d7bd00bfa44f388345ae16fe4baac9d68de6f0935"],"state_sha256":"a7e7c19622f3b405db03551b561f0593f87c9fbcb6aa83da4880ff91f84c6d80"}