{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:W5J7DGQPTP6QTP7HNY6PLYH3TC","short_pith_number":"pith:W5J7DGQP","canonical_record":{"source":{"id":"2207.13446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-27T10:54:05Z","cross_cats_sorted":["cs.FL"],"title_canon_sha256":"e7c5fedc13906fefb44b781f579bad68259a7b445bdb260eea381c9e55714097","abstract_canon_sha256":"948d85974bd595b58e66cc813badfdb6a783f49d68f3dbb2d953828b3b79f657"},"schema_version":"1.0"},"canonical_sha256":"b753f19a0f9bfd09bfe76e3cf5e0fb98ac0e105e657beab6056b65cfce558e01","source":{"kind":"arxiv","id":"2207.13446","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.13446","created_at":"2026-07-05T04:44:07Z"},{"alias_kind":"arxiv_version","alias_value":"2207.13446v1","created_at":"2026-07-05T04:44:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13446","created_at":"2026-07-05T04:44:07Z"},{"alias_kind":"pith_short_12","alias_value":"W5J7DGQPTP6Q","created_at":"2026-07-05T04:44:07Z"},{"alias_kind":"pith_short_16","alias_value":"W5J7DGQPTP6QTP7H","created_at":"2026-07-05T04:44:07Z"},{"alias_kind":"pith_short_8","alias_value":"W5J7DGQP","created_at":"2026-07-05T04:44:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:W5J7DGQPTP6QTP7HNY6PLYH3TC","target":"record","payload":{"canonical_record":{"source":{"id":"2207.13446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-27T10:54:05Z","cross_cats_sorted":["cs.FL"],"title_canon_sha256":"e7c5fedc13906fefb44b781f579bad68259a7b445bdb260eea381c9e55714097","abstract_canon_sha256":"948d85974bd595b58e66cc813badfdb6a783f49d68f3dbb2d953828b3b79f657"},"schema_version":"1.0"},"canonical_sha256":"b753f19a0f9bfd09bfe76e3cf5e0fb98ac0e105e657beab6056b65cfce558e01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:07.217032Z","signature_b64":"phqQs6BA5YWQPubx5RpSjrvhEcXn/Wxpolmt2bpt1z62LyTNmWFIy8q36VnHPX1V+UkZCQj7turwy91k9HxEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b753f19a0f9bfd09bfe76e3cf5e0fb98ac0e105e657beab6056b65cfce558e01","last_reissued_at":"2026-07-05T04:44:07.216637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:07.216637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.13446","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:44:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BJi6NSkzhQgaeTKyGfebDMBONbWa8JP7zhoMiUO14cJ0BW6asKN48If88GQbj0XNxZoogBCA3KVUlwz+/w+TDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:07:01.496500Z"},"content_sha256":"f82440b9733ebe55b41dfa3283914993dbad2f51dc67ba33003494dce8060883","schema_version":"1.0","event_id":"sha256:f82440b9733ebe55b41dfa3283914993dbad2f51dc67ba33003494dce8060883"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:W5J7DGQPTP6QTP7HNY6PLYH3TC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Shielding for Reinforcement Learning in Black-Box Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL"],"primary_cat":"cs.LG","authors_text":"Ezequiel Castellano, Ichiro Hasuo, Masaki Waga, Sasinee Pruekprasert, Stefan Klikovits, Toru Takisaka","submitted_at":"2022-07-27T10:54:05Z","abstract_excerpt":"It is challenging to use reinforcement learning (RL) in cyber-physical systems due to the lack of safety guarantees during learning. Although there have been various proposals to reduce undesired behaviors during learning, most of these techniques require prior system knowledge, and their applicability is limited. This paper aims to reduce undesired behaviors during learning without requiring any prior system knowledge. We propose dynamic shielding: an extension of a model-based safe RL technique called shielding using automata learning. The dynamic shielding technique constructs an approximat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13446","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/2207.13446/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:44:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"THuczeK1J+N1k4VmXJQzVUtT++iHDmSVdnpMzB7sfVQB8z7Ih3tq87k5/Cap71nJYylQbdeiEN4KkXo6AhAEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:07:01.497218Z"},"content_sha256":"024561309055186c8a9e0205da90b1ad46bb40b9e1945f1c5482411749b1caf4","schema_version":"1.0","event_id":"sha256:024561309055186c8a9e0205da90b1ad46bb40b9e1945f1c5482411749b1caf4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W5J7DGQPTP6QTP7HNY6PLYH3TC/bundle.json","state_url":"https://pith.science/pith/W5J7DGQPTP6QTP7HNY6PLYH3TC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W5J7DGQPTP6QTP7HNY6PLYH3TC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T14:07:01Z","links":{"resolver":"https://pith.science/pith/W5J7DGQPTP6QTP7HNY6PLYH3TC","bundle":"https://pith.science/pith/W5J7DGQPTP6QTP7HNY6PLYH3TC/bundle.json","state":"https://pith.science/pith/W5J7DGQPTP6QTP7HNY6PLYH3TC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W5J7DGQPTP6QTP7HNY6PLYH3TC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:W5J7DGQPTP6QTP7HNY6PLYH3TC","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":"948d85974bd595b58e66cc813badfdb6a783f49d68f3dbb2d953828b3b79f657","cross_cats_sorted":["cs.FL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-27T10:54:05Z","title_canon_sha256":"e7c5fedc13906fefb44b781f579bad68259a7b445bdb260eea381c9e55714097"},"schema_version":"1.0","source":{"id":"2207.13446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.13446","created_at":"2026-07-05T04:44:07Z"},{"alias_kind":"arxiv_version","alias_value":"2207.13446v1","created_at":"2026-07-05T04:44:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13446","created_at":"2026-07-05T04:44:07Z"},{"alias_kind":"pith_short_12","alias_value":"W5J7DGQPTP6Q","created_at":"2026-07-05T04:44:07Z"},{"alias_kind":"pith_short_16","alias_value":"W5J7DGQPTP6QTP7H","created_at":"2026-07-05T04:44:07Z"},{"alias_kind":"pith_short_8","alias_value":"W5J7DGQP","created_at":"2026-07-05T04:44:07Z"}],"graph_snapshots":[{"event_id":"sha256:024561309055186c8a9e0205da90b1ad46bb40b9e1945f1c5482411749b1caf4","target":"graph","created_at":"2026-07-05T04:44:07Z","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/2207.13446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is challenging to use reinforcement learning (RL) in cyber-physical systems due to the lack of safety guarantees during learning. Although there have been various proposals to reduce undesired behaviors during learning, most of these techniques require prior system knowledge, and their applicability is limited. This paper aims to reduce undesired behaviors during learning without requiring any prior system knowledge. We propose dynamic shielding: an extension of a model-based safe RL technique called shielding using automata learning. The dynamic shielding technique constructs an approximat","authors_text":"Ezequiel Castellano, Ichiro Hasuo, Masaki Waga, Sasinee Pruekprasert, Stefan Klikovits, Toru Takisaka","cross_cats":["cs.FL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-27T10:54:05Z","title":"Dynamic Shielding for Reinforcement Learning in Black-Box Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13446","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:f82440b9733ebe55b41dfa3283914993dbad2f51dc67ba33003494dce8060883","target":"record","created_at":"2026-07-05T04:44:07Z","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":"948d85974bd595b58e66cc813badfdb6a783f49d68f3dbb2d953828b3b79f657","cross_cats_sorted":["cs.FL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-27T10:54:05Z","title_canon_sha256":"e7c5fedc13906fefb44b781f579bad68259a7b445bdb260eea381c9e55714097"},"schema_version":"1.0","source":{"id":"2207.13446","kind":"arxiv","version":1}},"canonical_sha256":"b753f19a0f9bfd09bfe76e3cf5e0fb98ac0e105e657beab6056b65cfce558e01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b753f19a0f9bfd09bfe76e3cf5e0fb98ac0e105e657beab6056b65cfce558e01","first_computed_at":"2026-07-05T04:44:07.216637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:44:07.216637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"phqQs6BA5YWQPubx5RpSjrvhEcXn/Wxpolmt2bpt1z62LyTNmWFIy8q36VnHPX1V+UkZCQj7turwy91k9HxEDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:44:07.217032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.13446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f82440b9733ebe55b41dfa3283914993dbad2f51dc67ba33003494dce8060883","sha256:024561309055186c8a9e0205da90b1ad46bb40b9e1945f1c5482411749b1caf4"],"state_sha256":"d0a036246c1d3193e9ca6c0171e170d301d286213da368a8261b799cffdbc0e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tve/IwJN/vBisWYRgjX0aUryaeAPI0x3uJyNR0IpD3AToXmaDsqJ10FDHrUay+5FcfX4X2O9M/9HCoisWZmMBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T14:07:01.511004Z","bundle_sha256":"b61a62c422dc3943177102352a4205d671bad2de6747e207c76d6af7ffe12c44"}}