{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:R4MVEJNUWTAUIZ6WMFODF3BMY3","short_pith_number":"pith:R4MVEJNU","canonical_record":{"source":{"id":"2306.12371","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T16:26:59Z","cross_cats_sorted":["cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"8c411269a6162703baa122102e03f4ed13f439e7111cd54df9feb7e3dbd47bb3","abstract_canon_sha256":"6f306413fdc98cad945ae63bd2b7e530a6ca5151fc0fc89a1cf28f80c1def0a5"},"schema_version":"1.0"},"canonical_sha256":"8f195225b4b4c14467d6615c32ec2cc6ea2a37d31fcdb66263f77cb1852134c2","source":{"kind":"arxiv","id":"2306.12371","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.12371","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.12371v2","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12371","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_12","alias_value":"R4MVEJNUWTAU","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_16","alias_value":"R4MVEJNUWTAUIZ6W","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_8","alias_value":"R4MVEJNU","created_at":"2026-07-05T07:06:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:R4MVEJNUWTAUIZ6WMFODF3BMY3","target":"record","payload":{"canonical_record":{"source":{"id":"2306.12371","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T16:26:59Z","cross_cats_sorted":["cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"8c411269a6162703baa122102e03f4ed13f439e7111cd54df9feb7e3dbd47bb3","abstract_canon_sha256":"6f306413fdc98cad945ae63bd2b7e530a6ca5151fc0fc89a1cf28f80c1def0a5"},"schema_version":"1.0"},"canonical_sha256":"8f195225b4b4c14467d6615c32ec2cc6ea2a37d31fcdb66263f77cb1852134c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:30.520062Z","signature_b64":"Si5oUKokaEflGJwV4D7HPJ3Xl0eqTCt2r69TkrX49nvS3vB61i6KUxHAThsW+eq3OFF8qjAuhgfIO75Q963CCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f195225b4b4c14467d6615c32ec2cc6ea2a37d31fcdb66263f77cb1852134c2","last_reissued_at":"2026-07-05T07:06:30.519469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:30.519469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.12371","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:06:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I+v99W/NexoKcK7w9EFCNvpFPDNf5lDfC0U2zR9BJjwBbbKU9ajyiqG6jem1Xfh8LcaCKMU6iQFO3flh57L9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:14:52.193384Z"},"content_sha256":"51e78dc6a4cccc34ea7b65d2abc2cf080b1621959dfa45a41ce113af994481ef","schema_version":"1.0","event_id":"sha256:51e78dc6a4cccc34ea7b65d2abc2cf080b1621959dfa45a41ce113af994481ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:R4MVEJNUWTAUIZ6WMFODF3BMY3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimistic Active Exploration of Dynamical Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Bhavya Sukhija, Cansu Sancaktar, Lenart Treven, Sebastian Blaes, Stelian Coros","submitted_at":"2023-06-21T16:26:59Z","abstract_excerpt":"Reinforcement learning algorithms commonly seek to optimize policies for solving one particular task. How should we explore an unknown dynamical system such that the estimated model globally approximates the dynamics and allows us to solve multiple downstream tasks in a zero-shot manner? In this paper, we address this challenge, by developing an algorithm -- OPAX -- for active exploration. OPAX uses well-calibrated probabilistic models to quantify the epistemic uncertainty about the unknown dynamics. It optimistically -- w.r.t. to plausible dynamics -- maximizes the information gain between th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12371","kind":"arxiv","version":2},"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/2306.12371/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":"2026-07-05T07:06:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NUHaL95G3NY/TT8p6w+zICRN40Y8kntoo0NPdTA0QvHK9qegiAsMYF1QI94B8WKhhaZo4Ung2roEB3peXa8iDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:14:52.193756Z"},"content_sha256":"f6e7c2aa60095fa9462f17b1a437c523f580b9780827694ce7db94fe4caa6437","schema_version":"1.0","event_id":"sha256:f6e7c2aa60095fa9462f17b1a437c523f580b9780827694ce7db94fe4caa6437"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R4MVEJNUWTAUIZ6WMFODF3BMY3/bundle.json","state_url":"https://pith.science/pith/R4MVEJNUWTAUIZ6WMFODF3BMY3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R4MVEJNUWTAUIZ6WMFODF3BMY3/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":"2026-07-06T08:14:52Z","links":{"resolver":"https://pith.science/pith/R4MVEJNUWTAUIZ6WMFODF3BMY3","bundle":"https://pith.science/pith/R4MVEJNUWTAUIZ6WMFODF3BMY3/bundle.json","state":"https://pith.science/pith/R4MVEJNUWTAUIZ6WMFODF3BMY3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R4MVEJNUWTAUIZ6WMFODF3BMY3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:R4MVEJNUWTAUIZ6WMFODF3BMY3","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":"6f306413fdc98cad945ae63bd2b7e530a6ca5151fc0fc89a1cf28f80c1def0a5","cross_cats_sorted":["cs.RO","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T16:26:59Z","title_canon_sha256":"8c411269a6162703baa122102e03f4ed13f439e7111cd54df9feb7e3dbd47bb3"},"schema_version":"1.0","source":{"id":"2306.12371","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.12371","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.12371v2","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12371","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_12","alias_value":"R4MVEJNUWTAU","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_16","alias_value":"R4MVEJNUWTAUIZ6W","created_at":"2026-07-05T07:06:30Z"},{"alias_kind":"pith_short_8","alias_value":"R4MVEJNU","created_at":"2026-07-05T07:06:30Z"}],"graph_snapshots":[{"event_id":"sha256:f6e7c2aa60095fa9462f17b1a437c523f580b9780827694ce7db94fe4caa6437","target":"graph","created_at":"2026-07-05T07:06:30Z","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/2306.12371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning algorithms commonly seek to optimize policies for solving one particular task. How should we explore an unknown dynamical system such that the estimated model globally approximates the dynamics and allows us to solve multiple downstream tasks in a zero-shot manner? In this paper, we address this challenge, by developing an algorithm -- OPAX -- for active exploration. OPAX uses well-calibrated probabilistic models to quantify the epistemic uncertainty about the unknown dynamics. It optimistically -- w.r.t. to plausible dynamics -- maximizes the information gain between th","authors_text":"Andreas Krause, Bhavya Sukhija, Cansu Sancaktar, Lenart Treven, Sebastian Blaes, Stelian Coros","cross_cats":["cs.RO","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T16:26:59Z","title":"Optimistic Active Exploration of Dynamical Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12371","kind":"arxiv","version":2},"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":"sha256:51e78dc6a4cccc34ea7b65d2abc2cf080b1621959dfa45a41ce113af994481ef","target":"record","created_at":"2026-07-05T07:06:30Z","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":"6f306413fdc98cad945ae63bd2b7e530a6ca5151fc0fc89a1cf28f80c1def0a5","cross_cats_sorted":["cs.RO","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T16:26:59Z","title_canon_sha256":"8c411269a6162703baa122102e03f4ed13f439e7111cd54df9feb7e3dbd47bb3"},"schema_version":"1.0","source":{"id":"2306.12371","kind":"arxiv","version":2}},"canonical_sha256":"8f195225b4b4c14467d6615c32ec2cc6ea2a37d31fcdb66263f77cb1852134c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f195225b4b4c14467d6615c32ec2cc6ea2a37d31fcdb66263f77cb1852134c2","first_computed_at":"2026-07-05T07:06:30.519469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:30.519469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Si5oUKokaEflGJwV4D7HPJ3Xl0eqTCt2r69TkrX49nvS3vB61i6KUxHAThsW+eq3OFF8qjAuhgfIO75Q963CCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:30.520062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.12371","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51e78dc6a4cccc34ea7b65d2abc2cf080b1621959dfa45a41ce113af994481ef","sha256:f6e7c2aa60095fa9462f17b1a437c523f580b9780827694ce7db94fe4caa6437"],"state_sha256":"acca07475ea21038a860103879f1f389d83fd79e9ccc815970083f85220e25ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MDOq4QjW9kzefhLgNyhYN4q5Wfke1eI2WB1f7Y22gcaxxBEqoJZ+iBnaEOsOhH1s7xLKim5f86hqZLTVyEQEAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:14:52.195734Z","bundle_sha256":"918df25ddbbc94d20c0e4a16e8641f35dfd7efd892c80ef7543cf0170d3c04f2"}}