{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EVLMNV2SN22WXTTMPZHSYRCJLR","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":"d18ac02df8a44e921d451fac570d9e4c5261c3af468ad372b1ec010a77396e89","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T21:45:28Z","title_canon_sha256":"9f1fd48fa173fc1888a3676c0874ace5e1205a1a15add982800f532b460c3877"},"schema_version":"1.0","source":{"id":"2605.25267","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25267","created_at":"2026-05-26T02:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25267v1","created_at":"2026-05-26T02:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25267","created_at":"2026-05-26T02:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"EVLMNV2SN22W","created_at":"2026-05-26T02:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"EVLMNV2SN22WXTTM","created_at":"2026-05-26T02:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"EVLMNV2S","created_at":"2026-05-26T02:04:26Z"}],"graph_snapshots":[{"event_id":"sha256:f547efa9c81c4829dd0c9d06c1325f6a2b05ead4ca96639172f6b9f5b2d4bb26","target":"graph","created_at":"2026-05-26T02:04:26Z","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/2605.25267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cost under a safety budget. Under out-of-distribution (OOD) deployment shifts, pretraining-only safe ICRL can give poor reward-safety tradeoffs because the remaining budget affects behavior only through frozen policy conditioning, not an explicit action-level check against predicted future cost. We propose a latent Q-Barrier shield that learns a context representation, latent dynamics, and an ensemble cost critic before deployment. Without parameter","authors_text":"Amir Moeini, Lu Feng, Minjae Kwon, Shangtong Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T21:45:28Z","title":"Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25267","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":"sha256:5b2c3485616be73c2f0c4b75326dc2b277af17e23d9bb6e9330f35ed787624e1","target":"record","created_at":"2026-05-26T02:04:26Z","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":"d18ac02df8a44e921d451fac570d9e4c5261c3af468ad372b1ec010a77396e89","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T21:45:28Z","title_canon_sha256":"9f1fd48fa173fc1888a3676c0874ace5e1205a1a15add982800f532b460c3877"},"schema_version":"1.0","source":{"id":"2605.25267","kind":"arxiv","version":1}},"canonical_sha256":"2556c6d7526eb56bce6c7e4f2c44495c5d82baebb9b72a9e6cc42302c98899ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2556c6d7526eb56bce6c7e4f2c44495c5d82baebb9b72a9e6cc42302c98899ed","first_computed_at":"2026-05-26T02:04:26.335715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:26.335715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1fvfxHIQocU9MChCRvbK71+uNnPr8+SXdpznoMiReWusFXxTon2BTf3ngq+OgQM7sx+y+zZaLvbkhT/SjTZ4Bw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:26.336536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25267","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b2c3485616be73c2f0c4b75326dc2b277af17e23d9bb6e9330f35ed787624e1","sha256:f547efa9c81c4829dd0c9d06c1325f6a2b05ead4ca96639172f6b9f5b2d4bb26"],"state_sha256":"ad5fa16a81745ee0d56810f500feaf31c0d4383ddebf51fa56c164ba56570b49"}