{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FDWOZSOEJ64RONNEIBTZAAABAI","short_pith_number":"pith:FDWOZSOE","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"},"canonical_sha256":"28ececc9c44fb91735a440679000010205e18a7219b850d3d6ebb26c18fc23c1","source":{"kind":"arxiv","id":"2107.01995","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01995","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01995v1","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01995","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_12","alias_value":"FDWOZSOEJ64R","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_16","alias_value":"FDWOZSOEJ64RONNE","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_8","alias_value":"FDWOZSOE","created_at":"2026-07-05T02:55:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FDWOZSOEJ64RONNEIBTZAAABAI","target":"record","payload":{"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"},"canonical_sha256":"28ececc9c44fb91735a440679000010205e18a7219b850d3d6ebb26c18fc23c1","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"},"source_kind":"arxiv","source_id":"2107.01995","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:55:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fd37pH2w5UK1UEddq7E8MdC0f+ApV3ayawAloB3i9kYPkYMosYd3HK8wO2Ag+/h2GQzWb9Sasp02EbXDtcvYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:30:01.227570Z"},"content_sha256":"5805d17e656e76d960ee7002f1ffada52b8a0c4d063df825a8bcc5462112da5b","schema_version":"1.0","event_id":"sha256:5805d17e656e76d960ee7002f1ffada52b8a0c4d063df825a8bcc5462112da5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FDWOZSOEJ64RONNEIBTZAAABAI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:55:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+Fg++KUvKvHvasHTM7f7IvPIMqietdvSJn5VFFh0tS8zYlAcG+IXLxiidOmd01/1CJrHgQQ3VvdRXCpstp2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:30:01.228183Z"},"content_sha256":"f1b90081f3c7b7c441f51c7b69a334824754cb6af56000d930e77339ff72f05a","schema_version":"1.0","event_id":"sha256:f1b90081f3c7b7c441f51c7b69a334824754cb6af56000d930e77339ff72f05a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI/bundle.json","state_url":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FDWOZSOEJ64RONNEIBTZAAABAI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T21:30:01Z","links":{"resolver":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI","bundle":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI/bundle.json","state":"https://pith.science/pith/FDWOZSOEJ64RONNEIBTZAAABAI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FDWOZSOEJ64RONNEIBTZAAABAI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FDWOZSOEJ64RONNEIBTZAAABAI","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":"fa1d8f3327b7aaefca5602c1155184d3ef29f04389f4386c65306dd73d3fb5c0","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2021-07-02T14:58:35Z","title_canon_sha256":"5f9fc24a0c1ed0ee02964f64b5022989b0e2069dd480d3a4e0e6eed274aceafe"},"schema_version":"1.0","source":{"id":"2107.01995","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01995","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01995v1","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01995","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_12","alias_value":"FDWOZSOEJ64R","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_16","alias_value":"FDWOZSOEJ64RONNE","created_at":"2026-07-05T02:55:02Z"},{"alias_kind":"pith_short_8","alias_value":"FDWOZSOE","created_at":"2026-07-05T02:55:02Z"}],"graph_snapshots":[{"event_id":"sha256:f1b90081f3c7b7c441f51c7b69a334824754cb6af56000d930e77339ff72f05a","target":"graph","created_at":"2026-07-05T02:55:02Z","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/2107.01995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ananth Jonnavittula, Dylan P. Losey, Soheil Habibian","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2021-07-02T14:58:35Z","title":"Here's What I've Learned: Asking Questions that Reveal Reward Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01995","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":"sha256:5805d17e656e76d960ee7002f1ffada52b8a0c4d063df825a8bcc5462112da5b","target":"record","created_at":"2026-07-05T02:55:02Z","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":"fa1d8f3327b7aaefca5602c1155184d3ef29f04389f4386c65306dd73d3fb5c0","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2021-07-02T14:58:35Z","title_canon_sha256":"5f9fc24a0c1ed0ee02964f64b5022989b0e2069dd480d3a4e0e6eed274aceafe"},"schema_version":"1.0","source":{"id":"2107.01995","kind":"arxiv","version":1}},"canonical_sha256":"28ececc9c44fb91735a440679000010205e18a7219b850d3d6ebb26c18fc23c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28ececc9c44fb91735a440679000010205e18a7219b850d3d6ebb26c18fc23c1","first_computed_at":"2026-07-05T02:55:02.708174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:55:02.708174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qmj1kNwEppT2rLoyLBX8QlTBUGjtPAHHJ0VplBn70FmekZqSOlawPJuUclO3PMnWJKyyeC21eFNJ9ynmzV4LCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:55:02.708706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.01995","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5805d17e656e76d960ee7002f1ffada52b8a0c4d063df825a8bcc5462112da5b","sha256:f1b90081f3c7b7c441f51c7b69a334824754cb6af56000d930e77339ff72f05a"],"state_sha256":"18e7ae6b39375698257d5040af6ea5add85a85ed78f83aef57ea69110e944fc1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZWRkGyxkf+lm2wG6olWWjn+3p2C/LGNCser4Q1aX8A4beSThx5aq95AFRBAiX08Bla2/Utl+yarIHXutGihMAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:30:01.233427Z","bundle_sha256":"c43360dd91dcc7fec31b1dcb0ca89a1b72d34171e5eea71e4a43851a2b1a6f89"}}