{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:24QUX2ZR2I52TTUNQBJ6OVXEPY","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":"97d98e7d80ce9ddc09ab08e26c8e9c38be6534034034f9515cab3fea03823d3c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-14T07:50:43Z","title_canon_sha256":"c4631c72c5b2545784132ebf793dd49ce15cbdcf1204cd84dbca10ccf2b8e56c"},"schema_version":"1.0","source":{"id":"2607.12466","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.12466","created_at":"2026-07-15T01:21:36Z"},{"alias_kind":"arxiv_version","alias_value":"2607.12466v1","created_at":"2026-07-15T01:21:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12466","created_at":"2026-07-15T01:21:36Z"},{"alias_kind":"pith_short_12","alias_value":"24QUX2ZR2I52","created_at":"2026-07-15T01:21:36Z"},{"alias_kind":"pith_short_16","alias_value":"24QUX2ZR2I52TTUN","created_at":"2026-07-15T01:21:36Z"},{"alias_kind":"pith_short_8","alias_value":"24QUX2ZR","created_at":"2026-07-15T01:21:36Z"}],"graph_snapshots":[{"event_id":"sha256:33b2c4b3bbfbfcc0ebf001c0e8936f7a0088a177424059a28d7aa0ab39dd1fce","target":"graph","created_at":"2026-07-15T01:21:36Z","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/2607.12466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gwangmo Lee, Jongeun Choi, Minjun Chang, Sunghyun Lim, Taehyung Kim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-14T07:50:43Z","title":"Deployable Human Preference Alignment in Robotics: Learning Representative Rewards from Diverse Human Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12466","kind":"arxiv","version":1},"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":"sha256:3d6d8dc10ff6b93a348e2b1065b4caa8369332bbbe4995d486b85795bb137276","target":"record","created_at":"2026-07-15T01:21:36Z","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":"97d98e7d80ce9ddc09ab08e26c8e9c38be6534034034f9515cab3fea03823d3c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-14T07:50:43Z","title_canon_sha256":"c4631c72c5b2545784132ebf793dd49ce15cbdcf1204cd84dbca10ccf2b8e56c"},"schema_version":"1.0","source":{"id":"2607.12466","kind":"arxiv","version":1}},"canonical_sha256":"d7214beb31d23ba9ce8d8053e756e47e09a2685b2f1edb9c86cf9ea8d544f231","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7214beb31d23ba9ce8d8053e756e47e09a2685b2f1edb9c86cf9ea8d544f231","first_computed_at":"2026-07-15T01:21:36.634986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T01:21:36.634986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pNPiHWArMsAkVt8N95Pg9pcu960VYG6LvI5twY0xBwrOHJ37jusuAMKJ9//pBa8ikvnXv+l/yP9rUBGLj2Q8AA==","signature_status":"signed_v1","signed_at":"2026-07-15T01:21:36.635850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.12466","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d6d8dc10ff6b93a348e2b1065b4caa8369332bbbe4995d486b85795bb137276","sha256:33b2c4b3bbfbfcc0ebf001c0e8936f7a0088a177424059a28d7aa0ab39dd1fce"],"state_sha256":"28687739593148efb017e44b2dfba7993d026cb04950288d95bf97834ce2ab82"}