{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:24QUX2ZR2I52TTUNQBJ6OVXEPY","short_pith_number":"pith:24QUX2ZR","schema_version":"1.0","canonical_sha256":"d7214beb31d23ba9ce8d8053e756e47e09a2685b2f1edb9c86cf9ea8d544f231","source":{"kind":"arxiv","id":"2607.12466","version":1},"attestation_state":"computed","paper":{"title":"Deployable Human Preference Alignment in Robotics: Learning Representative Rewards from Diverse Human Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gwangmo Lee, Jongeun Choi, Minjun Chang, Sunghyun Lim, Taehyung Kim","submitted_at":"2026-07-14T07:50:43Z","abstract_excerpt":"Aligning robot policies with human preferences is essential for deployment to diverse end users. In per-user alignment approach, preference feedback is often sparse, so learning becomes unstable and vulnerable to human preference noise, and a growing number of individualized policies makes validation difficult before deployment. A single shared policy approach to user alignment avoids this cost but fails to capture heterogeneous preferences and often neglects minority preferences. To address these challenges, we introduce Preference-based REward Clustering (PREC), a novel framework that learns"},"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":"2607.12466","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-14T07:50:43Z","cross_cats_sorted":[],"title_canon_sha256":"c4631c72c5b2545784132ebf793dd49ce15cbdcf1204cd84dbca10ccf2b8e56c","abstract_canon_sha256":"97d98e7d80ce9ddc09ab08e26c8e9c38be6534034034f9515cab3fea03823d3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:21:36.635850Z","signature_b64":"pNPiHWArMsAkVt8N95Pg9pcu960VYG6LvI5twY0xBwrOHJ37jusuAMKJ9//pBa8ikvnXv+l/yP9rUBGLj2Q8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7214beb31d23ba9ce8d8053e756e47e09a2685b2f1edb9c86cf9ea8d544f231","last_reissued_at":"2026-07-15T01:21:36.634986Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:21:36.634986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deployable Human Preference Alignment in Robotics: Learning Representative Rewards from Diverse Human Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gwangmo Lee, Jongeun Choi, Minjun Chang, Sunghyun Lim, Taehyung Kim","submitted_at":"2026-07-14T07:50:43Z","abstract_excerpt":"Aligning robot policies with human preferences is essential for deployment to diverse end users. In per-user alignment approach, preference feedback is often sparse, so learning becomes unstable and vulnerable to human preference noise, and a growing number of individualized policies makes validation difficult before deployment. A single shared policy approach to user alignment avoids this cost but fails to capture heterogeneous preferences and often neglects minority preferences. To address these challenges, we introduce Preference-based REward Clustering (PREC), a novel framework that learns"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12466","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/2607.12466/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":"2607.12466","created_at":"2026-07-15T01:21:36.635421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.12466v1","created_at":"2026-07-15T01:21:36.635421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12466","created_at":"2026-07-15T01:21:36.635421+00:00"},{"alias_kind":"pith_short_12","alias_value":"24QUX2ZR2I52","created_at":"2026-07-15T01:21:36.635421+00:00"},{"alias_kind":"pith_short_16","alias_value":"24QUX2ZR2I52TTUN","created_at":"2026-07-15T01:21:36.635421+00:00"},{"alias_kind":"pith_short_8","alias_value":"24QUX2ZR","created_at":"2026-07-15T01:21:36.635421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24QUX2ZR2I52TTUNQBJ6OVXEPY","json":"https://pith.science/pith/24QUX2ZR2I52TTUNQBJ6OVXEPY.json","graph_json":"https://pith.science/api/pith-number/24QUX2ZR2I52TTUNQBJ6OVXEPY/graph.json","events_json":"https://pith.science/api/pith-number/24QUX2ZR2I52TTUNQBJ6OVXEPY/events.json","paper":"https://pith.science/paper/24QUX2ZR"},"agent_actions":{"view_html":"https://pith.science/pith/24QUX2ZR2I52TTUNQBJ6OVXEPY","download_json":"https://pith.science/pith/24QUX2ZR2I52TTUNQBJ6OVXEPY.json","view_paper":"https://pith.science/paper/24QUX2ZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.12466&json=true","fetch_graph":"https://pith.science/api/pith-number/24QUX2ZR2I52TTUNQBJ6OVXEPY/graph.json","fetch_events":"https://pith.science/api/pith-number/24QUX2ZR2I52TTUNQBJ6OVXEPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24QUX2ZR2I52TTUNQBJ6OVXEPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24QUX2ZR2I52TTUNQBJ6OVXEPY/action/storage_attestation","attest_author":"https://pith.science/pith/24QUX2ZR2I52TTUNQBJ6OVXEPY/action/author_attestation","sign_citation":"https://pith.science/pith/24QUX2ZR2I52TTUNQBJ6OVXEPY/action/citation_signature","submit_replication":"https://pith.science/pith/24QUX2ZR2I52TTUNQBJ6OVXEPY/action/replication_record"}},"created_at":"2026-07-15T01:21:36.635421+00:00","updated_at":"2026-07-15T01:21:36.635421+00:00"}