{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:676OM7FULB2XCHZTGNMAELWFDX","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":"15139dbc0aff361922256b0d2a830e203b7c08ecb570fbcd0860a40bde1426f5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-14T09:04:14Z","title_canon_sha256":"5aa79f8a50ba18e453829f90b89d1310730bd8ad7e62bd6d664862b6e90cb4f3"},"schema_version":"1.0","source":{"id":"2504.10002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.10002","created_at":"2026-07-05T10:48:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.10002v1","created_at":"2026-07-05T10:48:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10002","created_at":"2026-07-05T10:48:46Z"},{"alias_kind":"pith_short_12","alias_value":"676OM7FULB2X","created_at":"2026-07-05T10:48:46Z"},{"alias_kind":"pith_short_16","alias_value":"676OM7FULB2XCHZT","created_at":"2026-07-05T10:48:46Z"},{"alias_kind":"pith_short_8","alias_value":"676OM7FU","created_at":"2026-07-05T10:48:46Z"}],"graph_snapshots":[{"event_id":"sha256:afd4f604c4689693f046f8c736380c5a35e6740e951ac7c5e1edd6b2ef6f2d55","target":"graph","created_at":"2026-07-05T10:48:46Z","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/2504.10002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reinforcement learning (PbRL) is a suitable approach for style adaptation of pre-trained robotic behavior: adapting the robot's policy to follow human user preferences while still being able to perform the original task. However, collecting preferences for the adaptation process in robotics is often challenging and time-consuming. In this work we explore the adaptation of pre-trained robots in the low-preference-data regime. We show that, in this regime, recent adaptation approaches suffer from catastrophic reward forgetting (CRF), where the updated reward model overfits to th","authors_text":"Danica Kragic, Daniel Marta, Finn Busch, Iolanda Leite, Jens Lundell, Miguel Vasco, Olov Andersson, Simon Holk, Timon Homberger","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-14T09:04:14Z","title":"FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10002","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:ab7292f6a58a63ad58857830f5e5d208550223ab5ddc6e0bda01144659e25783","target":"record","created_at":"2026-07-05T10:48:46Z","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":"15139dbc0aff361922256b0d2a830e203b7c08ecb570fbcd0860a40bde1426f5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-14T09:04:14Z","title_canon_sha256":"5aa79f8a50ba18e453829f90b89d1310730bd8ad7e62bd6d664862b6e90cb4f3"},"schema_version":"1.0","source":{"id":"2504.10002","kind":"arxiv","version":1}},"canonical_sha256":"f7fce67cb45875711f333358022ec51de2b66863ae8bbaf395a9615fe56798b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7fce67cb45875711f333358022ec51de2b66863ae8bbaf395a9615fe56798b6","first_computed_at":"2026-07-05T10:48:46.271563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:46.271563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VsMSNydqID/r0eMnvfJBz48HoDEuO0dNiIJSpeHvMEsK9dGRNidTHrUNhmei+yqCU60LzS0qcyvwLXfBuXHoAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:46.272096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.10002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab7292f6a58a63ad58857830f5e5d208550223ab5ddc6e0bda01144659e25783","sha256:afd4f604c4689693f046f8c736380c5a35e6740e951ac7c5e1edd6b2ef6f2d55"],"state_sha256":"192e0f36cd2075e2951e337c249ef7ec15df01e38f76cf8e0f59b7b76c7aef63"}