{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D7LZDI7BN6UUOND4M6JGTYU263","short_pith_number":"pith:D7LZDI7B","schema_version":"1.0","canonical_sha256":"1fd791a3e16fa947347c679269e29af6f606ad677a56d19521468c456dfa2c0e","source":{"kind":"arxiv","id":"2306.00603","version":2},"attestation_state":"computed","paper":{"title":"Safe Offline Reinforcement Learning with Real-Time Budget Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bo Tang, Chao Yu, Dong Wang, Qian Lin, Qianlong Xie, Shangqin Mao, Xingxing Wang, Zifan Wu","submitted_at":"2023-06-01T12:19:32Z","abstract_excerpt":"Aiming at promoting the safe real-world deployment of Reinforcement Learning (RL), research on safe RL has made significant progress in recent years. However, most existing works in the literature still focus on the online setting where risky violations of the safety budget are likely to be incurred during training. Besides, in many real-world applications, the learned policy is required to respond to dynamically determined safety budgets (i.e., constraint threshold) in real time. In this paper, we target at the above real-time budget constraint problem under the offline setting, and propose T"},"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":"2306.00603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T12:19:32Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"d80aa258d74cd57e84142d743c5b805950496592bd8a99b98b19364af4f30fdd","abstract_canon_sha256":"1b0e4f02edd5e76e12f3e7d41e7a7376ecf2e7f7816b5438b7e2ca086c44371e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:28.920403Z","signature_b64":"NATFTdV6bhBMxvoPQpSBmx5NG96z8/Ad/ZN7Tf0IJXFg9eOOL0BMPx/JbgQiVGd4k86OV5dbFuJudbbo1JZCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fd791a3e16fa947347c679269e29af6f606ad677a56d19521468c456dfa2c0e","last_reissued_at":"2026-07-05T07:51:28.919902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:28.919902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Offline Reinforcement Learning with Real-Time Budget Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bo Tang, Chao Yu, Dong Wang, Qian Lin, Qianlong Xie, Shangqin Mao, Xingxing Wang, Zifan Wu","submitted_at":"2023-06-01T12:19:32Z","abstract_excerpt":"Aiming at promoting the safe real-world deployment of Reinforcement Learning (RL), research on safe RL has made significant progress in recent years. However, most existing works in the literature still focus on the online setting where risky violations of the safety budget are likely to be incurred during training. Besides, in many real-world applications, the learned policy is required to respond to dynamically determined safety budgets (i.e., constraint threshold) in real time. In this paper, we target at the above real-time budget constraint problem under the offline setting, and propose T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00603","kind":"arxiv","version":2},"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/2306.00603/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":"2306.00603","created_at":"2026-07-05T07:51:28.919963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00603v2","created_at":"2026-07-05T07:51:28.919963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00603","created_at":"2026-07-05T07:51:28.919963+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7LZDI7BN6UU","created_at":"2026-07-05T07:51:28.919963+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7LZDI7BN6UUOND4","created_at":"2026-07-05T07:51:28.919963+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7LZDI7B","created_at":"2026-07-05T07:51:28.919963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D7LZDI7BN6UUOND4M6JGTYU263","json":"https://pith.science/pith/D7LZDI7BN6UUOND4M6JGTYU263.json","graph_json":"https://pith.science/api/pith-number/D7LZDI7BN6UUOND4M6JGTYU263/graph.json","events_json":"https://pith.science/api/pith-number/D7LZDI7BN6UUOND4M6JGTYU263/events.json","paper":"https://pith.science/paper/D7LZDI7B"},"agent_actions":{"view_html":"https://pith.science/pith/D7LZDI7BN6UUOND4M6JGTYU263","download_json":"https://pith.science/pith/D7LZDI7BN6UUOND4M6JGTYU263.json","view_paper":"https://pith.science/paper/D7LZDI7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00603&json=true","fetch_graph":"https://pith.science/api/pith-number/D7LZDI7BN6UUOND4M6JGTYU263/graph.json","fetch_events":"https://pith.science/api/pith-number/D7LZDI7BN6UUOND4M6JGTYU263/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7LZDI7BN6UUOND4M6JGTYU263/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7LZDI7BN6UUOND4M6JGTYU263/action/storage_attestation","attest_author":"https://pith.science/pith/D7LZDI7BN6UUOND4M6JGTYU263/action/author_attestation","sign_citation":"https://pith.science/pith/D7LZDI7BN6UUOND4M6JGTYU263/action/citation_signature","submit_replication":"https://pith.science/pith/D7LZDI7BN6UUOND4M6JGTYU263/action/replication_record"}},"created_at":"2026-07-05T07:51:28.919963+00:00","updated_at":"2026-07-05T07:51:28.919963+00:00"}