{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QVH43KDVZK23AMNMTMM6HWDMQS","short_pith_number":"pith:QVH43KDV","canonical_record":{"source":{"id":"2307.14316","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T17:26:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43d08f2673aac69d2ae3ef17942ad929e89818f44c1c13dfc14e2cf8e39adf2a","abstract_canon_sha256":"8499d7e036792b588725c9c02045e83c6b49f9f11a96b47423d3a20e70ef27b5"},"schema_version":"1.0"},"canonical_sha256":"854fcda875cab5b031ac9b19e3d86c84a307decf4354799f0fabf96c51c2a1c6","source":{"kind":"arxiv","id":"2307.14316","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14316","created_at":"2026-07-05T07:59:03Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14316v1","created_at":"2026-07-05T07:59:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14316","created_at":"2026-07-05T07:59:03Z"},{"alias_kind":"pith_short_12","alias_value":"QVH43KDVZK23","created_at":"2026-07-05T07:59:03Z"},{"alias_kind":"pith_short_16","alias_value":"QVH43KDVZK23AMNM","created_at":"2026-07-05T07:59:03Z"},{"alias_kind":"pith_short_8","alias_value":"QVH43KDV","created_at":"2026-07-05T07:59:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QVH43KDVZK23AMNMTMM6HWDMQS","target":"record","payload":{"canonical_record":{"source":{"id":"2307.14316","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T17:26:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43d08f2673aac69d2ae3ef17942ad929e89818f44c1c13dfc14e2cf8e39adf2a","abstract_canon_sha256":"8499d7e036792b588725c9c02045e83c6b49f9f11a96b47423d3a20e70ef27b5"},"schema_version":"1.0"},"canonical_sha256":"854fcda875cab5b031ac9b19e3d86c84a307decf4354799f0fabf96c51c2a1c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:03.131509Z","signature_b64":"KMSyMzFVHWyw7ErcycrRBAzq8vk+U6mHLEsJjb69n5uM3TdAya8e4Cd2QpZdXvFFmodMKtt+hPJN9mT6UVZFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"854fcda875cab5b031ac9b19e3d86c84a307decf4354799f0fabf96c51c2a1c6","last_reissued_at":"2026-07-05T07:59:03.131008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:03.131008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.14316","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":"2026-07-05T07:59:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TiVQqxQ3LV6DD0+7il/rXI/FHQfJM4vnBmI5idsSoqffEkB6HDRjbpERPoKUTXV7oBN+ACJJmuL+moJ77KdQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:59:36.214871Z"},"content_sha256":"210f3f2557c0226ba28aaa4844086c1af0caef2d991a992d078ff86013cd9e8e","schema_version":"1.0","event_id":"sha256:210f3f2557c0226ba28aaa4844086c1af0caef2d991a992d078ff86013cd9e8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QVH43KDVZK23AMNMTMM6HWDMQS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning by Guided Safe Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Matthijs T. J. Spaan, Nils Jansen, Qisong Yang, Simon H. Tindemans, Thiago D. Sim\\~ao","submitted_at":"2023-07-26T17:26:21Z","abstract_excerpt":"Safety is critical to broadening the application of reinforcement learning (RL). Often, we train RL agents in a controlled environment, such as a laboratory, before deploying them in the real world. However, the real-world target task might be unknown prior to deployment. Reward-free RL trains an agent without the reward to adapt quickly once the reward is revealed. We consider the constrained reward-free setting, where an agent (the guide) learns to explore safely without the reward signal. This agent is trained in a controlled environment, which allows unsafe interactions and still provides "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14316","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/2307.14316/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":"2026-07-05T07:59:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OjLi1YQh1GjuA/EXDWk32oSETAG1rNB+V+Xdgdd3pCgRSHQEYK8FmH3w+MECIcEqb2dZVRb+9XT4MYcRRGgDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:59:36.215447Z"},"content_sha256":"ca23c073a2e0b1fabb1e91972edbf2471ae83dbb8b5dde1653a272b1e05bf538","schema_version":"1.0","event_id":"sha256:ca23c073a2e0b1fabb1e91972edbf2471ae83dbb8b5dde1653a272b1e05bf538"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS/bundle.json","state_url":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVH43KDVZK23AMNMTMM6HWDMQS/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":"2026-08-13T15:59:36Z","links":{"resolver":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS","bundle":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS/bundle.json","state":"https://pith.science/pith/QVH43KDVZK23AMNMTMM6HWDMQS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVH43KDVZK23AMNMTMM6HWDMQS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QVH43KDVZK23AMNMTMM6HWDMQS","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":"8499d7e036792b588725c9c02045e83c6b49f9f11a96b47423d3a20e70ef27b5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T17:26:21Z","title_canon_sha256":"43d08f2673aac69d2ae3ef17942ad929e89818f44c1c13dfc14e2cf8e39adf2a"},"schema_version":"1.0","source":{"id":"2307.14316","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14316","created_at":"2026-07-05T07:59:03Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14316v1","created_at":"2026-07-05T07:59:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14316","created_at":"2026-07-05T07:59:03Z"},{"alias_kind":"pith_short_12","alias_value":"QVH43KDVZK23","created_at":"2026-07-05T07:59:03Z"},{"alias_kind":"pith_short_16","alias_value":"QVH43KDVZK23AMNM","created_at":"2026-07-05T07:59:03Z"},{"alias_kind":"pith_short_8","alias_value":"QVH43KDV","created_at":"2026-07-05T07:59:03Z"}],"graph_snapshots":[{"event_id":"sha256:ca23c073a2e0b1fabb1e91972edbf2471ae83dbb8b5dde1653a272b1e05bf538","target":"graph","created_at":"2026-07-05T07:59:03Z","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/2307.14316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety is critical to broadening the application of reinforcement learning (RL). Often, we train RL agents in a controlled environment, such as a laboratory, before deploying them in the real world. However, the real-world target task might be unknown prior to deployment. Reward-free RL trains an agent without the reward to adapt quickly once the reward is revealed. We consider the constrained reward-free setting, where an agent (the guide) learns to explore safely without the reward signal. This agent is trained in a controlled environment, which allows unsafe interactions and still provides ","authors_text":"Matthijs T. J. Spaan, Nils Jansen, Qisong Yang, Simon H. Tindemans, Thiago D. Sim\\~ao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T17:26:21Z","title":"Reinforcement Learning by Guided Safe Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14316","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":"sha256:210f3f2557c0226ba28aaa4844086c1af0caef2d991a992d078ff86013cd9e8e","target":"record","created_at":"2026-07-05T07:59:03Z","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":"8499d7e036792b588725c9c02045e83c6b49f9f11a96b47423d3a20e70ef27b5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T17:26:21Z","title_canon_sha256":"43d08f2673aac69d2ae3ef17942ad929e89818f44c1c13dfc14e2cf8e39adf2a"},"schema_version":"1.0","source":{"id":"2307.14316","kind":"arxiv","version":1}},"canonical_sha256":"854fcda875cab5b031ac9b19e3d86c84a307decf4354799f0fabf96c51c2a1c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"854fcda875cab5b031ac9b19e3d86c84a307decf4354799f0fabf96c51c2a1c6","first_computed_at":"2026-07-05T07:59:03.131008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:03.131008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KMSyMzFVHWyw7ErcycrRBAzq8vk+U6mHLEsJjb69n5uM3TdAya8e4Cd2QpZdXvFFmodMKtt+hPJN9mT6UVZFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:03.131509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.14316","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:210f3f2557c0226ba28aaa4844086c1af0caef2d991a992d078ff86013cd9e8e","sha256:ca23c073a2e0b1fabb1e91972edbf2471ae83dbb8b5dde1653a272b1e05bf538"],"state_sha256":"d44106a54ad3fe15fdf2040c7a6171ee96cb3ee29de5a39c4dd8026c41c33f8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r6eE2EBpIbB6eY8v8D93KT2KjHw2vhyPEeL8dGTASbdZ7JdYgcQnqsNiEpUDlBSg+v7CdxNBXOlrWj7LR2svDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:59:36.219378Z","bundle_sha256":"1417a2b276bc18faf16005283868a5ab39afa1941abbe6954d250f1672b9e336"}}