{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BQDRAK3RB72CMOIY3L4HVABUN6","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":"81af67a23f12c2e7259a404a8b584c49c34552d8bd9de8cb65f8746299b93927","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-20T18:02:31Z","title_canon_sha256":"be831d7be9f839654c91c2c84e0ca4c846d6fce28dd35594f2f19a286a36ef56"},"schema_version":"1.0","source":{"id":"2409.13822","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13822","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13822v2","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13822","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"pith_short_12","alias_value":"BQDRAK3RB72C","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"pith_short_16","alias_value":"BQDRAK3RB72CMOIY","created_at":"2026-07-05T10:28:22Z"},{"alias_kind":"pith_short_8","alias_value":"BQDRAK3R","created_at":"2026-07-05T10:28:22Z"}],"graph_snapshots":[{"event_id":"sha256:add0f4982a4752fdfd900cf8b38ad5309e26c35aa5fa74cfbfffc0b86e6332cd","target":"graph","created_at":"2026-07-05T10:28:22Z","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/2409.13822/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reinforcement learning (PbRL) has shown significant promise for personalization in human-robot interaction (HRI) by explicitly integrating human preferences into the robot learning process. However, existing practices often require training a personalized robot policy from scratch, resulting in inefficient use of human feedback. In this paper, we propose preference-based action representation learning (PbARL), an efficient fine-tuning method that decouples common task structure from preference by leveraging pre-trained robot policies. Instead of directly fine-tuning the pre-tr","authors_text":"Byung-Cheol Min, Dayoon Suh, Dezhong Zhao, Guohua Chen, Ruiqi Wang, Ziqin Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-20T18:02:31Z","title":"Personalization in Human-Robot Interaction through Preference-based Action Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13822","kind":"arxiv","version":2},"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":"sha256:61932fd53bef812957e13b0194f3892ab80c75d137b0dbbe3b6edae5d249311a","target":"record","created_at":"2026-07-05T10:28:22Z","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":"81af67a23f12c2e7259a404a8b584c49c34552d8bd9de8cb65f8746299b93927","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-20T18:02:31Z","title_canon_sha256":"be831d7be9f839654c91c2c84e0ca4c846d6fce28dd35594f2f19a286a36ef56"},"schema_version":"1.0","source":{"id":"2409.13822","kind":"arxiv","version":2}},"canonical_sha256":"0c07102b710ff4263918daf87a80346faf2ac42d2ae1dc74ef9b88208f799f18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c07102b710ff4263918daf87a80346faf2ac42d2ae1dc74ef9b88208f799f18","first_computed_at":"2026-07-05T10:28:22.197313Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:22.197313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9n+yR1xT8eisAWQKdVLBnMFWI9sa0wTn6Frlf12pKaLV9ukTm9+UzBLZKSFsd5LQAZtBe98mwQGCj/rHRv/GAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:22.197746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13822","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61932fd53bef812957e13b0194f3892ab80c75d137b0dbbe3b6edae5d249311a","sha256:add0f4982a4752fdfd900cf8b38ad5309e26c35aa5fa74cfbfffc0b86e6332cd"],"state_sha256":"4dc1b2a077e1688d1e119db83754055dc0ad146c81fcdd289d8c169ac6add14c"}