{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:535W2DWHRBBH77SNIEDOOXKW5B","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":"43927a273293f7d5116b0c04a956b5a204a83a9f261228c84d79c50b882d8cbe","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T15:33:30Z","title_canon_sha256":"6e30a9e8875be2f1b022c2a067e11ff71fbb3357c80d800ef85db9e58cb564e2"},"schema_version":"1.0","source":{"id":"2401.12849","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12849","created_at":"2026-07-05T07:36:37Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12849v1","created_at":"2026-07-05T07:36:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12849","created_at":"2026-07-05T07:36:37Z"},{"alias_kind":"pith_short_12","alias_value":"535W2DWHRBBH","created_at":"2026-07-05T07:36:37Z"},{"alias_kind":"pith_short_16","alias_value":"535W2DWHRBBH77SN","created_at":"2026-07-05T07:36:37Z"},{"alias_kind":"pith_short_8","alias_value":"535W2DWH","created_at":"2026-07-05T07:36:37Z"}],"graph_snapshots":[{"event_id":"sha256:ba4a1e8887fd2441a2f59d1bfe851ca7a48462ccacf3f43e4b6595da8c998e12","target":"graph","created_at":"2026-07-05T07:36:37Z","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/2401.12849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The inability to naturally enforce safety in Reinforcement Learning (RL), with limited failures, is a core challenge impeding its use in real-world applications. One notion of safety of vast practical relevance is the ability to avoid (unsafe) regions of the state space. Though such a safety goal can be captured by an action-value-like function, a.k.a. safety critics, the associated operator lacks the desired contraction and uniqueness properties that the classical Bellman operator enjoys. In this work, we overcome the non-contractiveness of safety critic operators by leveraging that safety is","authors_text":"Agustin Castellano, Enrique Mallada, Hancheng Min, Juan Andr\\'es Bazerque","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T15:33:30Z","title":"Learning safety critics via a non-contractive binary bellman operator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12849","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":"sha256:19546041bb137bfec07b6d74758dcabf047c31420f94e27f8f66f4448f674a0e","target":"record","created_at":"2026-07-05T07:36:37Z","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":"43927a273293f7d5116b0c04a956b5a204a83a9f261228c84d79c50b882d8cbe","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T15:33:30Z","title_canon_sha256":"6e30a9e8875be2f1b022c2a067e11ff71fbb3357c80d800ef85db9e58cb564e2"},"schema_version":"1.0","source":{"id":"2401.12849","kind":"arxiv","version":1}},"canonical_sha256":"eefb6d0ec788427ffe4d4106e75d56e85d5a94eaf49ee5b86445d7bc449d890a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eefb6d0ec788427ffe4d4106e75d56e85d5a94eaf49ee5b86445d7bc449d890a","first_computed_at":"2026-07-05T07:36:37.000654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:37.000654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0FHxIaOlEKUwXkQOWnV1da8Swiy8UQ63fFDvUxvv2+0TF6b/ZDY/e3K/0pqBnnd/uqkHF6ovTG28H++/WYlsAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:37.001044Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12849","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19546041bb137bfec07b6d74758dcabf047c31420f94e27f8f66f4448f674a0e","sha256:ba4a1e8887fd2441a2f59d1bfe851ca7a48462ccacf3f43e4b6595da8c998e12"],"state_sha256":"d1ba6f2f63d3cba8c0e877df6dcee7fff8558f74bd27343d16f2ce2955925b73"}