{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HNTBZRPXWNMARHT4YP6QNJIEYV","short_pith_number":"pith:HNTBZRPX","canonical_record":{"source":{"id":"2406.01175","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T10:14:32Z","cross_cats_sorted":[],"title_canon_sha256":"29cdf0e578976b0268da2a4e0821236ec1fdec95e186bc66ce25d84b85e88767","abstract_canon_sha256":"5de475d003bb9bf8b97a5d61bb48d8c475796abe84cdddcb02941f4ff435a027"},"schema_version":"1.0"},"canonical_sha256":"3b661cc5f7b358089e7cc3fd06a504c5446e635eee422c5caba6e17e652e0bc3","source":{"kind":"arxiv","id":"2406.01175","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01175","created_at":"2026-07-05T10:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01175v4","created_at":"2026-07-05T10:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01175","created_at":"2026-07-05T10:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"HNTBZRPXWNMA","created_at":"2026-07-05T10:12:16Z"},{"alias_kind":"pith_short_16","alias_value":"HNTBZRPXWNMARHT4","created_at":"2026-07-05T10:12:16Z"},{"alias_kind":"pith_short_8","alias_value":"HNTBZRPX","created_at":"2026-07-05T10:12:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HNTBZRPXWNMARHT4YP6QNJIEYV","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01175","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T10:14:32Z","cross_cats_sorted":[],"title_canon_sha256":"29cdf0e578976b0268da2a4e0821236ec1fdec95e186bc66ce25d84b85e88767","abstract_canon_sha256":"5de475d003bb9bf8b97a5d61bb48d8c475796abe84cdddcb02941f4ff435a027"},"schema_version":"1.0"},"canonical_sha256":"3b661cc5f7b358089e7cc3fd06a504c5446e635eee422c5caba6e17e652e0bc3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:16.734013Z","signature_b64":"JocbLcXaP5+VvuRIx7KCg5BYWu5/brVmB5ET9QNrQldqiTabQryWh9jHQO4786jljFyiINcjQAvjlZzgHWt4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b661cc5f7b358089e7cc3fd06a504c5446e635eee422c5caba6e17e652e0bc3","last_reissued_at":"2026-07-05T10:12:16.733520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:16.733520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01175","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qSw/VEIKVI7SJlYQAC37ISHg4M3a8z8UWJ33ANr7A0PshKGq96vzZWssVIseGsiXkdDhbJC2/EnRvA6ohOYYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:48:30.133070Z"},"content_sha256":"ad07193b3bb11d980fb0d8bdf4e038bef1adba36309028eebd00ff253a31e56f","schema_version":"1.0","event_id":"sha256:ad07193b3bb11d980fb0d8bdf4e038bef1adba36309028eebd00ff253a31e56f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HNTBZRPXWNMARHT4YP6QNJIEYV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NeoRL: Efficient Exploration for Nonepisodic RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Bhavya Sukhija, Florian D\\\"orfler, Lenart Treven, Stelian Coros","submitted_at":"2024-06-03T10:14:32Z","abstract_excerpt":"We study the problem of nonepisodic reinforcement learning (RL) for nonlinear dynamical systems, where the system dynamics are unknown and the RL agent has to learn from a single trajectory, i.e., without resets. We propose Nonepisodic Optimistic RL (NeoRL), an approach based on the principle of optimism in the face of uncertainty. NeoRL uses well-calibrated probabilistic models and plans optimistically w.r.t. the epistemic uncertainty about the unknown dynamics. Under continuity and bounded energy assumptions on the system, we provide a first-of-its-kind regret bound of $O(\\Gamma_T \\sqrt{T})$"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01175","kind":"arxiv","version":4},"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/2406.01175/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":"2026-07-05T10:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nvDAk3jhcmFeRhcoTst4+jckOHyfTnTy+OYtHjCUQAkzJL7Xq/s3YCBe2avoU5WCcb1J3zTGTwdima/wM0aFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:48:30.133455Z"},"content_sha256":"7108fe19366b51ca4dbbead75ae50256818952fd2664d8046f08566a494c95b6","schema_version":"1.0","event_id":"sha256:7108fe19366b51ca4dbbead75ae50256818952fd2664d8046f08566a494c95b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV/bundle.json","state_url":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HNTBZRPXWNMARHT4YP6QNJIEYV/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":"2026-07-06T13:48:30Z","links":{"resolver":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV","bundle":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV/bundle.json","state":"https://pith.science/pith/HNTBZRPXWNMARHT4YP6QNJIEYV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HNTBZRPXWNMARHT4YP6QNJIEYV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HNTBZRPXWNMARHT4YP6QNJIEYV","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":"5de475d003bb9bf8b97a5d61bb48d8c475796abe84cdddcb02941f4ff435a027","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T10:14:32Z","title_canon_sha256":"29cdf0e578976b0268da2a4e0821236ec1fdec95e186bc66ce25d84b85e88767"},"schema_version":"1.0","source":{"id":"2406.01175","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01175","created_at":"2026-07-05T10:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01175v4","created_at":"2026-07-05T10:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01175","created_at":"2026-07-05T10:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"HNTBZRPXWNMA","created_at":"2026-07-05T10:12:16Z"},{"alias_kind":"pith_short_16","alias_value":"HNTBZRPXWNMARHT4","created_at":"2026-07-05T10:12:16Z"},{"alias_kind":"pith_short_8","alias_value":"HNTBZRPX","created_at":"2026-07-05T10:12:16Z"}],"graph_snapshots":[{"event_id":"sha256:7108fe19366b51ca4dbbead75ae50256818952fd2664d8046f08566a494c95b6","target":"graph","created_at":"2026-07-05T10:12:16Z","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/2406.01175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of nonepisodic reinforcement learning (RL) for nonlinear dynamical systems, where the system dynamics are unknown and the RL agent has to learn from a single trajectory, i.e., without resets. We propose Nonepisodic Optimistic RL (NeoRL), an approach based on the principle of optimism in the face of uncertainty. NeoRL uses well-calibrated probabilistic models and plans optimistically w.r.t. the epistemic uncertainty about the unknown dynamics. Under continuity and bounded energy assumptions on the system, we provide a first-of-its-kind regret bound of $O(\\Gamma_T \\sqrt{T})$","authors_text":"Andreas Krause, Bhavya Sukhija, Florian D\\\"orfler, Lenart Treven, Stelian Coros","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T10:14:32Z","title":"NeoRL: Efficient Exploration for Nonepisodic RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01175","kind":"arxiv","version":4},"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:ad07193b3bb11d980fb0d8bdf4e038bef1adba36309028eebd00ff253a31e56f","target":"record","created_at":"2026-07-05T10:12:16Z","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":"5de475d003bb9bf8b97a5d61bb48d8c475796abe84cdddcb02941f4ff435a027","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T10:14:32Z","title_canon_sha256":"29cdf0e578976b0268da2a4e0821236ec1fdec95e186bc66ce25d84b85e88767"},"schema_version":"1.0","source":{"id":"2406.01175","kind":"arxiv","version":4}},"canonical_sha256":"3b661cc5f7b358089e7cc3fd06a504c5446e635eee422c5caba6e17e652e0bc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b661cc5f7b358089e7cc3fd06a504c5446e635eee422c5caba6e17e652e0bc3","first_computed_at":"2026-07-05T10:12:16.733520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:16.733520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JocbLcXaP5+VvuRIx7KCg5BYWu5/brVmB5ET9QNrQldqiTabQryWh9jHQO4786jljFyiINcjQAvjlZzgHWt4CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:16.734013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01175","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad07193b3bb11d980fb0d8bdf4e038bef1adba36309028eebd00ff253a31e56f","sha256:7108fe19366b51ca4dbbead75ae50256818952fd2664d8046f08566a494c95b6"],"state_sha256":"3e3b7cfef5127f68cecec9c39a8e9492999a47c70f7d7d07f890042c214fbafd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WNX/BzNMoh9PCu9Vcl7/mAnbkOGis/nNQbXo3UAgX14E+HDMdzEnyp1wUG9xkF/9nQ6vAkiPWhqOtnTRBLKFAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:48:30.135467Z","bundle_sha256":"f1c31cd1231e9a6610b89973f9538c727dba5a53d16c36ec22bf963b54a3ba21"}}