{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KCDG7YCROPQQBUOFEM5SLC43FX","short_pith_number":"pith:KCDG7YCR","canonical_record":{"source":{"id":"2312.11314","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T16:09:43Z","cross_cats_sorted":["cs.LO","cs.SY","eess.SY"],"title_canon_sha256":"8f9d72c6736c009f1ddbc682740d3dc3a3de59141e3c8929489d214b20565840","abstract_canon_sha256":"c671706c5c6ba2e17e24c1ba0ba00e6c54222822684794930544d442f5477811"},"schema_version":"1.0"},"canonical_sha256":"50866fe05173e100d1c5233b258b9b2dfab5d4ad547919fc8682d8739c51365e","source":{"kind":"arxiv","id":"2312.11314","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11314","created_at":"2026-07-05T07:25:31Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11314v1","created_at":"2026-07-05T07:25:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11314","created_at":"2026-07-05T07:25:31Z"},{"alias_kind":"pith_short_12","alias_value":"KCDG7YCROPQQ","created_at":"2026-07-05T07:25:31Z"},{"alias_kind":"pith_short_16","alias_value":"KCDG7YCROPQQBUOF","created_at":"2026-07-05T07:25:31Z"},{"alias_kind":"pith_short_8","alias_value":"KCDG7YCR","created_at":"2026-07-05T07:25:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KCDG7YCROPQQBUOFEM5SLC43FX","target":"record","payload":{"canonical_record":{"source":{"id":"2312.11314","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T16:09:43Z","cross_cats_sorted":["cs.LO","cs.SY","eess.SY"],"title_canon_sha256":"8f9d72c6736c009f1ddbc682740d3dc3a3de59141e3c8929489d214b20565840","abstract_canon_sha256":"c671706c5c6ba2e17e24c1ba0ba00e6c54222822684794930544d442f5477811"},"schema_version":"1.0"},"canonical_sha256":"50866fe05173e100d1c5233b258b9b2dfab5d4ad547919fc8682d8739c51365e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:31.543139Z","signature_b64":"Qux5fo8TaXezPpuF9ebDzZzaTx7IZ1bPUBxAh/qjEIugjScl0k7hXJkHDnFcE5cpsqxsLWpt4Ewi/QXXY2cZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50866fe05173e100d1c5233b258b9b2dfab5d4ad547919fc8682d8739c51365e","last_reissued_at":"2026-07-05T07:25:31.542683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:31.542683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.11314","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":"2026-07-05T07:25:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LAaM0Xc7OvxI2Mr8Igy44OKFndzYSmTPv7dF2YoEqoRxotBrVOivcYhnsI31ZoRw0BoymMimhjZIM2MhubGYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:45:23.363101Z"},"content_sha256":"e55e4dcbbf51bef798a7cf6d6242ab5ce49f75c5545a8349a295b71435779e19","schema_version":"1.0","event_id":"sha256:e55e4dcbbf51bef798a7cf6d6242ab5ce49f75c5545a8349a295b71435779e19"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KCDG7YCROPQQBUOFEM5SLC43FX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Alessandro Abate, Daniel Kroening, Hosein Hasanbeig, Jun Wang, Rohan Mitta, Yiannis Kantaros","submitted_at":"2023-12-18T16:09:43Z","abstract_excerpt":"This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL), such that the safety constraint violations are bounded at any point during learning. In a variety of RL applications the safety of the agent is particularly important, e.g. autonomous platforms or robots that work in proximity of humans. As enforcing safety during training might severely limit the agent's exploration, we propose here a new architecture that handles the trade-off between efficient progress and safety during exploration. As the exploration progresses, we update via Bayesian inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11314","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/2312.11314/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":"2026-07-05T07:25:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MAe3ftW7UBKvHA6KkFznlMndL6wOUmuztt0/x3RA/RoLBKo6j8ugB1h1heCgnN0d4a4ToW/HblJ8QM2gFaeUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:45:23.363494Z"},"content_sha256":"0aeb539c63fe1a9781e50a15fe8505486805afd4b390751c6c6ef8d5ab1096f6","schema_version":"1.0","event_id":"sha256:0aeb539c63fe1a9781e50a15fe8505486805afd4b390751c6c6ef8d5ab1096f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KCDG7YCROPQQBUOFEM5SLC43FX/bundle.json","state_url":"https://pith.science/pith/KCDG7YCROPQQBUOFEM5SLC43FX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KCDG7YCROPQQBUOFEM5SLC43FX/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":"2026-07-07T02:45:23Z","links":{"resolver":"https://pith.science/pith/KCDG7YCROPQQBUOFEM5SLC43FX","bundle":"https://pith.science/pith/KCDG7YCROPQQBUOFEM5SLC43FX/bundle.json","state":"https://pith.science/pith/KCDG7YCROPQQBUOFEM5SLC43FX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KCDG7YCROPQQBUOFEM5SLC43FX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KCDG7YCROPQQBUOFEM5SLC43FX","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":"c671706c5c6ba2e17e24c1ba0ba00e6c54222822684794930544d442f5477811","cross_cats_sorted":["cs.LO","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T16:09:43Z","title_canon_sha256":"8f9d72c6736c009f1ddbc682740d3dc3a3de59141e3c8929489d214b20565840"},"schema_version":"1.0","source":{"id":"2312.11314","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11314","created_at":"2026-07-05T07:25:31Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11314v1","created_at":"2026-07-05T07:25:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11314","created_at":"2026-07-05T07:25:31Z"},{"alias_kind":"pith_short_12","alias_value":"KCDG7YCROPQQ","created_at":"2026-07-05T07:25:31Z"},{"alias_kind":"pith_short_16","alias_value":"KCDG7YCROPQQBUOF","created_at":"2026-07-05T07:25:31Z"},{"alias_kind":"pith_short_8","alias_value":"KCDG7YCR","created_at":"2026-07-05T07:25:31Z"}],"graph_snapshots":[{"event_id":"sha256:0aeb539c63fe1a9781e50a15fe8505486805afd4b390751c6c6ef8d5ab1096f6","target":"graph","created_at":"2026-07-05T07:25:31Z","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/2312.11314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL), such that the safety constraint violations are bounded at any point during learning. In a variety of RL applications the safety of the agent is particularly important, e.g. autonomous platforms or robots that work in proximity of humans. As enforcing safety during training might severely limit the agent's exploration, we propose here a new architecture that handles the trade-off between efficient progress and safety during exploration. As the exploration progresses, we update via Bayesian inf","authors_text":"Alessandro Abate, Daniel Kroening, Hosein Hasanbeig, Jun Wang, Rohan Mitta, Yiannis Kantaros","cross_cats":["cs.LO","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T16:09:43Z","title":"Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11314","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:e55e4dcbbf51bef798a7cf6d6242ab5ce49f75c5545a8349a295b71435779e19","target":"record","created_at":"2026-07-05T07:25:31Z","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":"c671706c5c6ba2e17e24c1ba0ba00e6c54222822684794930544d442f5477811","cross_cats_sorted":["cs.LO","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T16:09:43Z","title_canon_sha256":"8f9d72c6736c009f1ddbc682740d3dc3a3de59141e3c8929489d214b20565840"},"schema_version":"1.0","source":{"id":"2312.11314","kind":"arxiv","version":1}},"canonical_sha256":"50866fe05173e100d1c5233b258b9b2dfab5d4ad547919fc8682d8739c51365e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50866fe05173e100d1c5233b258b9b2dfab5d4ad547919fc8682d8739c51365e","first_computed_at":"2026-07-05T07:25:31.542683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:31.542683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qux5fo8TaXezPpuF9ebDzZzaTx7IZ1bPUBxAh/qjEIugjScl0k7hXJkHDnFcE5cpsqxsLWpt4Ewi/QXXY2cZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:31.543139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.11314","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e55e4dcbbf51bef798a7cf6d6242ab5ce49f75c5545a8349a295b71435779e19","sha256:0aeb539c63fe1a9781e50a15fe8505486805afd4b390751c6c6ef8d5ab1096f6"],"state_sha256":"ea871e5400e4030e1ea74548c8a764f36e515473be0e152dd4248b3178ee8d2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PXbM7a5Z8LjGyJka+uXkrYfk9GK95mH20Dsz4AtYID/LUcXCMWVaKFiQJF8QAMFshIv15RAu6svOjYDqophQBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:45:23.365457Z","bundle_sha256":"d0ecf77e91dd7d5910b20f730b87baae2d1a3696cc74298da8f82fcf567e72e7"}}