{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M3UQAD2P3JVL2VV55JLPU5PG3E","short_pith_number":"pith:M3UQAD2P","schema_version":"1.0","canonical_sha256":"66e9000f4fda6abd56bdea56fa75e6d933fdc3f2f918904454a3565887ac7640","source":{"kind":"arxiv","id":"2403.19795","version":1},"attestation_state":"computed","paper":{"title":"Learning Human Preferences Over Robot Behavior as Soft Planning Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"(2) Meta AI), Austin Narcomey (1), Marynel V\\'azquez (1) ((1) Yale University, Nathan Tsoi (1), Ruta Desai (2)","submitted_at":"2024-03-28T19:21:57Z","abstract_excerpt":"Preference learning has long been studied in Human-Robot Interaction (HRI) in order to adapt robot behavior to specific user needs and desires. Typically, human preferences are modeled as a scalar function; however, such a formulation confounds critical considerations on how the robot should behave for a given task, with desired -- but not required -- robot behavior. In this work, we distinguish between such required and desired robot behavior by leveraging a planning framework. Specifically, we propose a novel problem formulation for preference learning in HRI where various types of human pre"},"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":"2403.19795","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-28T19:21:57Z","cross_cats_sorted":[],"title_canon_sha256":"d69329e84372f68cf609434fe24663dd1b51daa2c9e96067be5d7a206524bcc9","abstract_canon_sha256":"cfe2abe31b53ec0c01a1e970e589cda5789635ad7be7ff7a5b9bc595b5535528"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:08.899649Z","signature_b64":"uL6x0e1xTE/u3WP/2kJ1pOJbXfm0OJp07JQRyUysnpV6SqW2uPT9ENk9vJ9zxjnnryllRjxZ8o/rOwdq/OBjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e9000f4fda6abd56bdea56fa75e6d933fdc3f2f918904454a3565887ac7640","last_reissued_at":"2026-07-05T08:02:08.899260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:08.899260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Human Preferences Over Robot Behavior as Soft Planning Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"(2) Meta AI), Austin Narcomey (1), Marynel V\\'azquez (1) ((1) Yale University, Nathan Tsoi (1), Ruta Desai (2)","submitted_at":"2024-03-28T19:21:57Z","abstract_excerpt":"Preference learning has long been studied in Human-Robot Interaction (HRI) in order to adapt robot behavior to specific user needs and desires. Typically, human preferences are modeled as a scalar function; however, such a formulation confounds critical considerations on how the robot should behave for a given task, with desired -- but not required -- robot behavior. In this work, we distinguish between such required and desired robot behavior by leveraging a planning framework. Specifically, we propose a novel problem formulation for preference learning in HRI where various types of human pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19795","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/2403.19795/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":"2403.19795","created_at":"2026-07-05T08:02:08.899322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19795v1","created_at":"2026-07-05T08:02:08.899322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19795","created_at":"2026-07-05T08:02:08.899322+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3UQAD2P3JVL","created_at":"2026-07-05T08:02:08.899322+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3UQAD2P3JVL2VV5","created_at":"2026-07-05T08:02:08.899322+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3UQAD2P","created_at":"2026-07-05T08:02:08.899322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10601","citing_title":"Learning Quantitative Automata Modulo Theories","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3UQAD2P3JVL2VV55JLPU5PG3E","json":"https://pith.science/pith/M3UQAD2P3JVL2VV55JLPU5PG3E.json","graph_json":"https://pith.science/api/pith-number/M3UQAD2P3JVL2VV55JLPU5PG3E/graph.json","events_json":"https://pith.science/api/pith-number/M3UQAD2P3JVL2VV55JLPU5PG3E/events.json","paper":"https://pith.science/paper/M3UQAD2P"},"agent_actions":{"view_html":"https://pith.science/pith/M3UQAD2P3JVL2VV55JLPU5PG3E","download_json":"https://pith.science/pith/M3UQAD2P3JVL2VV55JLPU5PG3E.json","view_paper":"https://pith.science/paper/M3UQAD2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19795&json=true","fetch_graph":"https://pith.science/api/pith-number/M3UQAD2P3JVL2VV55JLPU5PG3E/graph.json","fetch_events":"https://pith.science/api/pith-number/M3UQAD2P3JVL2VV55JLPU5PG3E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3UQAD2P3JVL2VV55JLPU5PG3E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3UQAD2P3JVL2VV55JLPU5PG3E/action/storage_attestation","attest_author":"https://pith.science/pith/M3UQAD2P3JVL2VV55JLPU5PG3E/action/author_attestation","sign_citation":"https://pith.science/pith/M3UQAD2P3JVL2VV55JLPU5PG3E/action/citation_signature","submit_replication":"https://pith.science/pith/M3UQAD2P3JVL2VV55JLPU5PG3E/action/replication_record"}},"created_at":"2026-07-05T08:02:08.899322+00:00","updated_at":"2026-07-05T08:02:08.899322+00:00"}