{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:535W2DWHRBBH77SNIEDOOXKW5B","short_pith_number":"pith:535W2DWH","schema_version":"1.0","canonical_sha256":"eefb6d0ec788427ffe4d4106e75d56e85d5a94eaf49ee5b86445d7bc449d890a","source":{"kind":"arxiv","id":"2401.12849","version":1},"attestation_state":"computed","paper":{"title":"Learning safety critics via a non-contractive binary bellman operator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Agustin Castellano, Enrique Mallada, Hancheng Min, Juan Andr\\'es Bazerque","submitted_at":"2024-01-23T15:33:30Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.12849","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T15:33:30Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"6e30a9e8875be2f1b022c2a067e11ff71fbb3357c80d800ef85db9e58cb564e2","abstract_canon_sha256":"43927a273293f7d5116b0c04a956b5a204a83a9f261228c84d79c50b882d8cbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:37.001044Z","signature_b64":"0FHxIaOlEKUwXkQOWnV1da8Swiy8UQ63fFDvUxvv2+0TF6b/ZDY/e3K/0pqBnnd/uqkHF6ovTG28H++/WYlsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eefb6d0ec788427ffe4d4106e75d56e85d5a94eaf49ee5b86445d7bc449d890a","last_reissued_at":"2026-07-05T07:36:37.000654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:37.000654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning safety critics via a non-contractive binary bellman operator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Agustin Castellano, Enrique Mallada, Hancheng Min, Juan Andr\\'es Bazerque","submitted_at":"2024-01-23T15:33:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12849","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.12849/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.12849","created_at":"2026-07-05T07:36:37.000708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12849v1","created_at":"2026-07-05T07:36:37.000708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12849","created_at":"2026-07-05T07:36:37.000708+00:00"},{"alias_kind":"pith_short_12","alias_value":"535W2DWHRBBH","created_at":"2026-07-05T07:36:37.000708+00:00"},{"alias_kind":"pith_short_16","alias_value":"535W2DWHRBBH77SN","created_at":"2026-07-05T07:36:37.000708+00:00"},{"alias_kind":"pith_short_8","alias_value":"535W2DWH","created_at":"2026-07-05T07:36:37.000708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.19809","citing_title":"Q-learning-based Model-free Safety Filter","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/535W2DWHRBBH77SNIEDOOXKW5B","json":"https://pith.science/pith/535W2DWHRBBH77SNIEDOOXKW5B.json","graph_json":"https://pith.science/api/pith-number/535W2DWHRBBH77SNIEDOOXKW5B/graph.json","events_json":"https://pith.science/api/pith-number/535W2DWHRBBH77SNIEDOOXKW5B/events.json","paper":"https://pith.science/paper/535W2DWH"},"agent_actions":{"view_html":"https://pith.science/pith/535W2DWHRBBH77SNIEDOOXKW5B","download_json":"https://pith.science/pith/535W2DWHRBBH77SNIEDOOXKW5B.json","view_paper":"https://pith.science/paper/535W2DWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12849&json=true","fetch_graph":"https://pith.science/api/pith-number/535W2DWHRBBH77SNIEDOOXKW5B/graph.json","fetch_events":"https://pith.science/api/pith-number/535W2DWHRBBH77SNIEDOOXKW5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/535W2DWHRBBH77SNIEDOOXKW5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/535W2DWHRBBH77SNIEDOOXKW5B/action/storage_attestation","attest_author":"https://pith.science/pith/535W2DWHRBBH77SNIEDOOXKW5B/action/author_attestation","sign_citation":"https://pith.science/pith/535W2DWHRBBH77SNIEDOOXKW5B/action/citation_signature","submit_replication":"https://pith.science/pith/535W2DWHRBBH77SNIEDOOXKW5B/action/replication_record"}},"created_at":"2026-07-05T07:36:37.000708+00:00","updated_at":"2026-07-05T07:36:37.000708+00:00"}