{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FDWOZSOEJ64RONNEIBTZAAABAI","short_pith_number":"pith:FDWOZSOE","schema_version":"1.0","canonical_sha256":"28ececc9c44fb91735a440679000010205e18a7219b850d3d6ebb26c18fc23c1","source":{"kind":"arxiv","id":"2107.01995","version":1},"attestation_state":"computed","paper":{"title":"Here's What I've Learned: Asking Questions that Reveal Reward Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.HC","authors_text":"Ananth Jonnavittula, Dylan P. Losey, Soheil Habibian","submitted_at":"2021-07-02T14:58:35Z","abstract_excerpt":"Robots can learn from humans by asking questions. In these questions the robot demonstrates a few different behaviors and asks the human for their favorite. But how should robots choose which questions to ask? Today's robots optimize for informative questions that actively probe the human's preferences as efficiently as possible. But while informative questions make sense from the robot's perspective, human onlookers often find them arbitrary and misleading. In this paper we formalize active preference-based learning from the human's perspective. We hypothesize that -- from the human's point-o"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2107.01995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2021-07-02T14:58:35Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"5f9fc24a0c1ed0ee02964f64b5022989b0e2069dd480d3a4e0e6eed274aceafe","abstract_canon_sha256":"fa1d8f3327b7aaefca5602c1155184d3ef29f04389f4386c65306dd73d3fb5c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:02.708706Z","signature_b64":"qmj1kNwEppT2rLoyLBX8QlTBUGjtPAHHJ0VplBn70FmekZqSOlawPJuUclO3PMnWJKyyeC21eFNJ9ynmzV4LCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28ececc9c44fb91735a440679000010205e18a7219b850d3d6ebb26c18fc23c1","last_reissued_at":"2026-07-05T02:55:02.708174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:02.708174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Here's What I've Learned: Asking Questions that Reveal Reward Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.HC","authors_text":"Ananth Jonnavittula, Dylan P. Losey, Soheil Habibian","submitted_at":"2021-07-02T14:58:35Z","abstract_excerpt":"Robots can learn from humans by asking questions. In these questions the robot demonstrates a few different behaviors and asks the human for their favorite. But how should robots choose which questions to ask? Today's robots optimize for informative questions that actively probe the human's preferences as efficiently as possible. But while informative questions make sense from the robot's perspective, human onlookers often find them arbitrary and misleading. In this paper we formalize active preference-based learning from the human's perspective. We hypothesize that -- from the human's point-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01995","kind":"arxiv","version":1},"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/2107.01995/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2107.01995","created_at":"2026-07-05T02:55:02.708246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.01995v1","created_at":"2026-07-05T02:55:02.708246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01995","created_at":"2026-07-05T02:55:02.708246+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDWOZSOEJ64R","created_at":"2026-07-05T02:55:02.708246+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDWOZSOEJ64RONNE","created_at":"2026-07-05T02:55:02.708246+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDWOZSOE","created_at":"2026-07-05T02:55:02.708246+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12745","citing_title":"What Do You Think I Think? Accounting for Human Beliefs Using Second-Order Theory of Mind","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI","json":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI.json","graph_json":"https://pith.science/api/pith-number/FDWOZSOEJ64RONNEIBTZAAABAI/graph.json","events_json":"https://pith.science/api/pith-number/FDWOZSOEJ64RONNEIBTZAAABAI/events.json","paper":"https://pith.science/paper/FDWOZSOE"},"agent_actions":{"view_html":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI","download_json":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI.json","view_paper":"https://pith.science/paper/FDWOZSOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.01995&json=true","fetch_graph":"https://pith.science/api/pith-number/FDWOZSOEJ64RONNEIBTZAAABAI/graph.json","fetch_events":"https://pith.science/api/pith-number/FDWOZSOEJ64RONNEIBTZAAABAI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI/action/storage_attestation","attest_author":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI/action/author_attestation","sign_citation":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI/action/citation_signature","submit_replication":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI/action/replication_record"}},"created_at":"2026-07-05T02:55:02.708246+00:00","updated_at":"2026-07-05T02:55:02.708246+00:00"}