{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IITPMYRID35HSEB4OGJUXAW72O","short_pith_number":"pith:IITPMYRI","schema_version":"1.0","canonical_sha256":"4226f662281efa79103c71934b82dfd38c49f0c665927fdea20baf1f6919bed2","source":{"kind":"arxiv","id":"2312.09337","version":1},"attestation_state":"computed","paper":{"title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Aniruddha Kembhavi, Chanwoo Park, Kiana Ehsani, Kimin Lee, Luca Weihs, Minyoung Hwang","submitted_at":"2023-12-14T21:00:56Z","abstract_excerpt":"Customizing robotic behaviors to be aligned with diverse human preferences is an underexplored challenge in the field of embodied AI. In this paper, we present Promptable Behaviors, a novel framework that facilitates efficient personalization of robotic agents to diverse human preferences in complex environments. We use multi-objective reinforcement learning to train a single policy adaptable to a broad spectrum of preferences. We introduce three distinct methods to infer human preferences by leveraging different types of interactions: (1) human demonstrations, (2) preference feedback on traje"},"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":"2312.09337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T21:00:56Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"481e6407353d896015499c3e2830282e88d67e97186d11975873686bf5fc3c8d","abstract_canon_sha256":"6d5ed3116d287fedd360de0fe2aba2a5a9abfae3f5c452bacc6f465ba6c5ffbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:23.527511Z","signature_b64":"IMCXUQyg0mBaUSXfySaXBgo8wV4us/mS/B+eGDsAq75bVzzPO++147q7qZJ99FUCOZx6np2rtWMaAyejQuwcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4226f662281efa79103c71934b82dfd38c49f0c665927fdea20baf1f6919bed2","last_reissued_at":"2026-07-05T07:24:23.526941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:23.526941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Aniruddha Kembhavi, Chanwoo Park, Kiana Ehsani, Kimin Lee, Luca Weihs, Minyoung Hwang","submitted_at":"2023-12-14T21:00:56Z","abstract_excerpt":"Customizing robotic behaviors to be aligned with diverse human preferences is an underexplored challenge in the field of embodied AI. In this paper, we present Promptable Behaviors, a novel framework that facilitates efficient personalization of robotic agents to diverse human preferences in complex environments. We use multi-objective reinforcement learning to train a single policy adaptable to a broad spectrum of preferences. We introduce three distinct methods to infer human preferences by leveraging different types of interactions: (1) human demonstrations, (2) preference feedback on traje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09337","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/2312.09337/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":"2312.09337","created_at":"2026-07-05T07:24:23.527011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.09337v1","created_at":"2026-07-05T07:24:23.527011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09337","created_at":"2026-07-05T07:24:23.527011+00:00"},{"alias_kind":"pith_short_12","alias_value":"IITPMYRID35H","created_at":"2026-07-05T07:24:23.527011+00:00"},{"alias_kind":"pith_short_16","alias_value":"IITPMYRID35HSEB4","created_at":"2026-07-05T07:24:23.527011+00:00"},{"alias_kind":"pith_short_8","alias_value":"IITPMYRI","created_at":"2026-07-05T07:24:23.527011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.29559","citing_title":"LEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IITPMYRID35HSEB4OGJUXAW72O","json":"https://pith.science/pith/IITPMYRID35HSEB4OGJUXAW72O.json","graph_json":"https://pith.science/api/pith-number/IITPMYRID35HSEB4OGJUXAW72O/graph.json","events_json":"https://pith.science/api/pith-number/IITPMYRID35HSEB4OGJUXAW72O/events.json","paper":"https://pith.science/paper/IITPMYRI"},"agent_actions":{"view_html":"https://pith.science/pith/IITPMYRID35HSEB4OGJUXAW72O","download_json":"https://pith.science/pith/IITPMYRID35HSEB4OGJUXAW72O.json","view_paper":"https://pith.science/paper/IITPMYRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.09337&json=true","fetch_graph":"https://pith.science/api/pith-number/IITPMYRID35HSEB4OGJUXAW72O/graph.json","fetch_events":"https://pith.science/api/pith-number/IITPMYRID35HSEB4OGJUXAW72O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IITPMYRID35HSEB4OGJUXAW72O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IITPMYRID35HSEB4OGJUXAW72O/action/storage_attestation","attest_author":"https://pith.science/pith/IITPMYRID35HSEB4OGJUXAW72O/action/author_attestation","sign_citation":"https://pith.science/pith/IITPMYRID35HSEB4OGJUXAW72O/action/citation_signature","submit_replication":"https://pith.science/pith/IITPMYRID35HSEB4OGJUXAW72O/action/replication_record"}},"created_at":"2026-07-05T07:24:23.527011+00:00","updated_at":"2026-07-05T07:24:23.527011+00:00"}