{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:L7KCFHCAIIPZP2ZDHOHQMBEJFZ","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":"4bd2f1615d8e6cce99b266588a083760c91847a4ab79cb7d4248d209b9cd6a02","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-03T11:30:10Z","title_canon_sha256":"61fa15bd4016b2111f056e4579fbe57ac53ee30e54be2d45af60c15640aa7537"},"schema_version":"1.0","source":{"id":"2606.04749","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04749","created_at":"2026-06-04T01:09:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04749v1","created_at":"2026-06-04T01:09:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04749","created_at":"2026-06-04T01:09:28Z"},{"alias_kind":"pith_short_12","alias_value":"L7KCFHCAIIPZ","created_at":"2026-06-04T01:09:28Z"},{"alias_kind":"pith_short_16","alias_value":"L7KCFHCAIIPZP2ZD","created_at":"2026-06-04T01:09:28Z"},{"alias_kind":"pith_short_8","alias_value":"L7KCFHCA","created_at":"2026-06-04T01:09:28Z"}],"graph_snapshots":[{"event_id":"sha256:a1106231665c8238b388c4769ee1a7828c2003f6b7f65bc7a55a551edf310e7b","target":"graph","created_at":"2026-06-04T01:09:28Z","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/2606.04749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe robot control requires maximizing return while satisfying safety constraints. In off-policy safe reinforcement learning, reward and safety Q-values are commonly learned by separate critic ensembles, with uncertainty handled independently for each objective. This objective-wise treatment neglects inter-objective correlation and can lead to overly conservative value estimates, thereby reducing sample efficiency. To address this issue, we propose Cholesky-Ordered Projection Q-learning (COP-Q), a safety-first method that incorporates inter-objective covariance into vector-valued Q-value estim","authors_text":"Guopeng Li, Julian F. P. Kooij, Matthijs T. J. Spaan, Moritz A. Zanger","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-03T11:30:10Z","title":"COP-Q: Safety-First Reinforcement Learning for Robot Control via Cholesky-Ordered Projection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04749","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":"sha256:8744dbe377b9c901bfa665c57e23602811051b958635ea0969bbf6da615ca2a1","target":"record","created_at":"2026-06-04T01:09:28Z","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":"4bd2f1615d8e6cce99b266588a083760c91847a4ab79cb7d4248d209b9cd6a02","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-03T11:30:10Z","title_canon_sha256":"61fa15bd4016b2111f056e4579fbe57ac53ee30e54be2d45af60c15640aa7537"},"schema_version":"1.0","source":{"id":"2606.04749","kind":"arxiv","version":1}},"canonical_sha256":"5fd4229c40421f97eb233b8f0604892e759c987b7fcd61dd875c4e422fd314bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fd4229c40421f97eb233b8f0604892e759c987b7fcd61dd875c4e422fd314bf","first_computed_at":"2026-06-04T01:09:28.418270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:28.418270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gmq0bNyjZWOZA2oVAz47j//6vzErsrexR6dOd33sF52RntZdXD9gwRyaZNz0JhADfGrqc0RPmlUayR+DMjj1Bg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:28.418997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04749","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8744dbe377b9c901bfa665c57e23602811051b958635ea0969bbf6da615ca2a1","sha256:a1106231665c8238b388c4769ee1a7828c2003f6b7f65bc7a55a551edf310e7b"],"state_sha256":"92549b17bb76115136c1b00519da78417a260ad840b9c7f5379a9dc5ccb2b374"}