{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q3SBFNVOTGPK2FZSXKCSQMZYSC","short_pith_number":"pith:Q3SBFNVO","schema_version":"1.0","canonical_sha256":"86e412b6ae999ead1732ba8528333890b0acedee0b701db674fd2f5a65a1a782","source":{"kind":"arxiv","id":"2405.02754","version":2},"attestation_state":"computed","paper":{"title":"Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Changliu Liu, Feihan Li, Weiye Zhao","submitted_at":"2024-05-04T20:59:06Z","abstract_excerpt":"Deep reinforcement learning (DRL) has demonstrated remarkable performance in many continuous control tasks. However, a significant obstacle to the real-world application of DRL is the lack of safety guarantees. Although DRL agents can satisfy system safety in expectation through reward shaping, designing agents to consistently meet hard constraints (e.g., safety specifications) at every time step remains a formidable challenge. In contrast, existing work in the field of safe control provides guarantees on persistent satisfaction of hard safety constraints. However, these methods require explic"},"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":"2405.02754","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-04T20:59:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"015843ce54b107c4e6f8fc5edf06e29fca505b759f988dbe64bc3120167aa378","abstract_canon_sha256":"db17fdbb40ebd5c63fea6ddea23b89c13864442646dafbb2efb3588d2eef214b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:26.741704Z","signature_b64":"0nRywI190m8QmLdKwcmMDoTK2OhtXuOBeNWgaSdvGS4vBxnObpZ+EBGJf+0IVKrf1gKU3+7tnD/cy5+TKIRsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86e412b6ae999ead1732ba8528333890b0acedee0b701db674fd2f5a65a1a782","last_reissued_at":"2026-07-05T11:53:26.741229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:26.741229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Changliu Liu, Feihan Li, Weiye Zhao","submitted_at":"2024-05-04T20:59:06Z","abstract_excerpt":"Deep reinforcement learning (DRL) has demonstrated remarkable performance in many continuous control tasks. However, a significant obstacle to the real-world application of DRL is the lack of safety guarantees. Although DRL agents can satisfy system safety in expectation through reward shaping, designing agents to consistently meet hard constraints (e.g., safety specifications) at every time step remains a formidable challenge. In contrast, existing work in the field of safe control provides guarantees on persistent satisfaction of hard safety constraints. However, these methods require explic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02754","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/2405.02754/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":"2405.02754","created_at":"2026-07-05T11:53:26.741289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02754v2","created_at":"2026-07-05T11:53:26.741289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02754","created_at":"2026-07-05T11:53:26.741289+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3SBFNVOTGPK","created_at":"2026-07-05T11:53:26.741289+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3SBFNVOTGPK2FZS","created_at":"2026-07-05T11:53:26.741289+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3SBFNVO","created_at":"2026-07-05T11:53:26.741289+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/Q3SBFNVOTGPK2FZSXKCSQMZYSC","json":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC.json","graph_json":"https://pith.science/api/pith-number/Q3SBFNVOTGPK2FZSXKCSQMZYSC/graph.json","events_json":"https://pith.science/api/pith-number/Q3SBFNVOTGPK2FZSXKCSQMZYSC/events.json","paper":"https://pith.science/paper/Q3SBFNVO"},"agent_actions":{"view_html":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC","download_json":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC.json","view_paper":"https://pith.science/paper/Q3SBFNVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02754&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3SBFNVOTGPK2FZSXKCSQMZYSC/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3SBFNVOTGPK2FZSXKCSQMZYSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC/action/storage_attestation","attest_author":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC/action/author_attestation","sign_citation":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC/action/citation_signature","submit_replication":"https://pith.science/pith/Q3SBFNVOTGPK2FZSXKCSQMZYSC/action/replication_record"}},"created_at":"2026-07-05T11:53:26.741289+00:00","updated_at":"2026-07-05T11:53:26.741289+00:00"}