{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TNZPBX65RGFBHGKQGIWPYLNBMU","short_pith_number":"pith:TNZPBX65","canonical_record":{"source":{"id":"2606.03804","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:50:34Z","cross_cats_sorted":[],"title_canon_sha256":"c34e644706d27c3b8764647be8a2ad3f6e51b7de860caac2f652070b4ab86171","abstract_canon_sha256":"8a2ff875035e6abd49dbd48cdc2ed4f726673e9a0ba2ae3f08f560b89761d5d6"},"schema_version":"1.0"},"canonical_sha256":"9b72f0dfdd898a139950322cfc2da165139d87b3d6b749355e22be3c3f7de431","source":{"kind":"arxiv","id":"2606.03804","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03804","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03804v1","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03804","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_12","alias_value":"TNZPBX65RGFB","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_16","alias_value":"TNZPBX65RGFBHGKQ","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_8","alias_value":"TNZPBX65","created_at":"2026-06-03T02:06:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TNZPBX65RGFBHGKQGIWPYLNBMU","target":"record","payload":{"canonical_record":{"source":{"id":"2606.03804","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:50:34Z","cross_cats_sorted":[],"title_canon_sha256":"c34e644706d27c3b8764647be8a2ad3f6e51b7de860caac2f652070b4ab86171","abstract_canon_sha256":"8a2ff875035e6abd49dbd48cdc2ed4f726673e9a0ba2ae3f08f560b89761d5d6"},"schema_version":"1.0"},"canonical_sha256":"9b72f0dfdd898a139950322cfc2da165139d87b3d6b749355e22be3c3f7de431","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:02.852492Z","signature_b64":"0BQ2KDTaAgKa0JIB9NcKGupCxoCLy49UJwjRdX9jtuAB4wERgo8gYBkhpdMi3ztBmBPq5PhGyXAYSLb4f72pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b72f0dfdd898a139950322cfc2da165139d87b3d6b749355e22be3c3f7de431","last_reissued_at":"2026-06-03T02:06:02.852058Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:02.852058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.03804","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":"2026-06-03T02:06:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BySmgc0FplBK2/TiOQi6/Hgq8Dg4H6oyj0N93ruNi0IAQ0x06pZqjRdEFA8iNVhYCVfRmHvC4gnQgluz9wT+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T21:35:48.682029Z"},"content_sha256":"9f4a308a8866af55c775223677f4b1afada0c1cc2ed76fde5b274110f58b0623","schema_version":"1.0","event_id":"sha256:9f4a308a8866af55c775223677f4b1afada0c1cc2ed76fde5b274110f58b0623"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TNZPBX65RGFBHGKQGIWPYLNBMU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Easy-to-Use Shielding for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bettina K\\\"onighofer, Stefan Pranger","submitted_at":"2026-06-02T15:50:34Z","abstract_excerpt":"Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their environment. Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their environment. Shielding is one such technique that assumes domain knowledge in the form of an environment model to decide upon action safety. Although well-established, shielding has seen limited adoption in RL due to the lack of accessible end-to-end infrastructure connecting formal shield sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03804","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/2606.03804/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":"2026-06-03T02:06:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iERa7iAfdXiMjB2Cj25qsDg8c2E8uoh7DdQDn4wk/PSuV2QL8RbVcs5QLievylFNF4/h2/U+WkZ0nsI9jFsXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T21:35:48.682747Z"},"content_sha256":"25c935be1a6618e7d460ca8eeccb982425a66d9f20e55de7b21d1b078a9003d9","schema_version":"1.0","event_id":"sha256:25c935be1a6618e7d460ca8eeccb982425a66d9f20e55de7b21d1b078a9003d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TNZPBX65RGFBHGKQGIWPYLNBMU/bundle.json","state_url":"https://pith.science/pith/TNZPBX65RGFBHGKQGIWPYLNBMU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TNZPBX65RGFBHGKQGIWPYLNBMU/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":"2026-06-11T21:35:48Z","links":{"resolver":"https://pith.science/pith/TNZPBX65RGFBHGKQGIWPYLNBMU","bundle":"https://pith.science/pith/TNZPBX65RGFBHGKQGIWPYLNBMU/bundle.json","state":"https://pith.science/pith/TNZPBX65RGFBHGKQGIWPYLNBMU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TNZPBX65RGFBHGKQGIWPYLNBMU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TNZPBX65RGFBHGKQGIWPYLNBMU","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":"8a2ff875035e6abd49dbd48cdc2ed4f726673e9a0ba2ae3f08f560b89761d5d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:50:34Z","title_canon_sha256":"c34e644706d27c3b8764647be8a2ad3f6e51b7de860caac2f652070b4ab86171"},"schema_version":"1.0","source":{"id":"2606.03804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03804","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03804v1","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03804","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_12","alias_value":"TNZPBX65RGFB","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_16","alias_value":"TNZPBX65RGFBHGKQ","created_at":"2026-06-03T02:06:02Z"},{"alias_kind":"pith_short_8","alias_value":"TNZPBX65","created_at":"2026-06-03T02:06:02Z"}],"graph_snapshots":[{"event_id":"sha256:25c935be1a6618e7d460ca8eeccb982425a66d9f20e55de7b21d1b078a9003d9","target":"graph","created_at":"2026-06-03T02:06:02Z","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/2606.03804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their environment. Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their environment. Shielding is one such technique that assumes domain knowledge in the form of an environment model to decide upon action safety. Although well-established, shielding has seen limited adoption in RL due to the lack of accessible end-to-end infrastructure connecting formal shield sy","authors_text":"Bettina K\\\"onighofer, Stefan Pranger","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:50:34Z","title":"Easy-to-Use Shielding for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03804","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":"sha256:9f4a308a8866af55c775223677f4b1afada0c1cc2ed76fde5b274110f58b0623","target":"record","created_at":"2026-06-03T02:06:02Z","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":"8a2ff875035e6abd49dbd48cdc2ed4f726673e9a0ba2ae3f08f560b89761d5d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T15:50:34Z","title_canon_sha256":"c34e644706d27c3b8764647be8a2ad3f6e51b7de860caac2f652070b4ab86171"},"schema_version":"1.0","source":{"id":"2606.03804","kind":"arxiv","version":1}},"canonical_sha256":"9b72f0dfdd898a139950322cfc2da165139d87b3d6b749355e22be3c3f7de431","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b72f0dfdd898a139950322cfc2da165139d87b3d6b749355e22be3c3f7de431","first_computed_at":"2026-06-03T02:06:02.852058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:02.852058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0BQ2KDTaAgKa0JIB9NcKGupCxoCLy49UJwjRdX9jtuAB4wERgo8gYBkhpdMi3ztBmBPq5PhGyXAYSLb4f72pAw==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:02.852492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f4a308a8866af55c775223677f4b1afada0c1cc2ed76fde5b274110f58b0623","sha256:25c935be1a6618e7d460ca8eeccb982425a66d9f20e55de7b21d1b078a9003d9"],"state_sha256":"1d829287dd29c1bf072f408774f4d6124ed545e6daec6f1a9eb7ef8e34b756f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MBFlvdMTLs1G/izNe5M9l61J/NbzJsbmpjgTlwCUa+zmdAFGIjpyDb+X/kQDkICesfOyItkvbhQ8z3+CFQFMBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T21:35:48.687125Z","bundle_sha256":"c46f1b766b0120fa8f711faac33f8147e559adb3e9344df02594b705d8dc63b3"}}