{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P6UFL323NDD6MHHGLZUR5DYKG2","short_pith_number":"pith:P6UFL323","schema_version":"1.0","canonical_sha256":"7fa855ef5b68c7e61ce65e691e8f0a368ee34ba36c5d274e9835ab249be65793","source":{"kind":"arxiv","id":"2411.11182","version":1},"attestation_state":"computed","paper":{"title":"Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.RO","authors_text":"Maja Matari\\'c, Nathaniel Dennler, Stefanos Nikolaidis, Zhonghao Shi","submitted_at":"2024-11-17T21:52:58Z","abstract_excerpt":"Assistive robots interact with humans and must adapt to different users' preferences to be effective. An easy and effective technique to learn non-expert users' preferences is through rankings of robot behaviors, for example, robot movement trajectories or gestures. Existing techniques focus on generating trajectories for users to rank that maximize the outcome of the preference learning process. However, the generated trajectories do not appear to reflect the user's preference over repeated interactions. In this work, we design an algorithm to generate trajectories for users to rank that we c"},"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":"2411.11182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-17T21:52:58Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"fa85e88e7ea3f051bc8af4cee42021446ce49ce8879328a66f451217c777494a","abstract_canon_sha256":"d14cfa2ace488c45b711accfe76a84e6fdb3bd1902ea4cb631643f343d039937"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:52.655175Z","signature_b64":"m4L57nd4/EDCzwq5MNLTxXMXoucIitsSP2Q8+ONTPNJhUETNXmdhTTQyrhZ52W9+grRQRM4s5Ml9VjXV2NjTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fa855ef5b68c7e61ce65e691e8f0a368ee34ba36c5d274e9835ab249be65793","last_reissued_at":"2026-07-05T09:36:52.654656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:52.654656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.RO","authors_text":"Maja Matari\\'c, Nathaniel Dennler, Stefanos Nikolaidis, Zhonghao Shi","submitted_at":"2024-11-17T21:52:58Z","abstract_excerpt":"Assistive robots interact with humans and must adapt to different users' preferences to be effective. An easy and effective technique to learn non-expert users' preferences is through rankings of robot behaviors, for example, robot movement trajectories or gestures. Existing techniques focus on generating trajectories for users to rank that maximize the outcome of the preference learning process. However, the generated trajectories do not appear to reflect the user's preference over repeated interactions. In this work, we design an algorithm to generate trajectories for users to rank that we c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11182","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/2411.11182/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":"2411.11182","created_at":"2026-07-05T09:36:52.654710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11182v1","created_at":"2026-07-05T09:36:52.654710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11182","created_at":"2026-07-05T09:36:52.654710+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6UFL323NDD6","created_at":"2026-07-05T09:36:52.654710+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6UFL323NDD6MHHG","created_at":"2026-07-05T09:36:52.654710+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6UFL323","created_at":"2026-07-05T09:36:52.654710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.17855","citing_title":"QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17855","citing_title":"QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6UFL323NDD6MHHGLZUR5DYKG2","json":"https://pith.science/pith/P6UFL323NDD6MHHGLZUR5DYKG2.json","graph_json":"https://pith.science/api/pith-number/P6UFL323NDD6MHHGLZUR5DYKG2/graph.json","events_json":"https://pith.science/api/pith-number/P6UFL323NDD6MHHGLZUR5DYKG2/events.json","paper":"https://pith.science/paper/P6UFL323"},"agent_actions":{"view_html":"https://pith.science/pith/P6UFL323NDD6MHHGLZUR5DYKG2","download_json":"https://pith.science/pith/P6UFL323NDD6MHHGLZUR5DYKG2.json","view_paper":"https://pith.science/paper/P6UFL323","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11182&json=true","fetch_graph":"https://pith.science/api/pith-number/P6UFL323NDD6MHHGLZUR5DYKG2/graph.json","fetch_events":"https://pith.science/api/pith-number/P6UFL323NDD6MHHGLZUR5DYKG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6UFL323NDD6MHHGLZUR5DYKG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6UFL323NDD6MHHGLZUR5DYKG2/action/storage_attestation","attest_author":"https://pith.science/pith/P6UFL323NDD6MHHGLZUR5DYKG2/action/author_attestation","sign_citation":"https://pith.science/pith/P6UFL323NDD6MHHGLZUR5DYKG2/action/citation_signature","submit_replication":"https://pith.science/pith/P6UFL323NDD6MHHGLZUR5DYKG2/action/replication_record"}},"created_at":"2026-07-05T09:36:52.654710+00:00","updated_at":"2026-07-05T09:36:52.654710+00:00"}