{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IWV2N3436MOFCOTBJQUSIAGTZR","short_pith_number":"pith:IWV2N343","canonical_record":{"source":{"id":"2603.08287","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-03-09T12:03:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5a65a033180fef1d3a47461ee4d07f1a851b892733a540c482ad6a86d90aff0e","abstract_canon_sha256":"6be0e328e7bb3b821155f1b189cdf32a345c60d9edfbddc774e18ace0f81d9dd"},"schema_version":"1.0"},"canonical_sha256":"45aba6ef9bf31c513a614c292400d3cc6b472988892964e549c140e2c3045cbe","source":{"kind":"arxiv","id":"2603.08287","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.08287","created_at":"2026-06-24T01:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2603.08287v2","created_at":"2026-06-24T01:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.08287","created_at":"2026-06-24T01:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"IWV2N3436MOF","created_at":"2026-06-24T01:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"IWV2N3436MOFCOTB","created_at":"2026-06-24T01:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"IWV2N343","created_at":"2026-06-24T01:15:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IWV2N3436MOFCOTBJQUSIAGTZR","target":"record","payload":{"canonical_record":{"source":{"id":"2603.08287","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-03-09T12:03:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5a65a033180fef1d3a47461ee4d07f1a851b892733a540c482ad6a86d90aff0e","abstract_canon_sha256":"6be0e328e7bb3b821155f1b189cdf32a345c60d9edfbddc774e18ace0f81d9dd"},"schema_version":"1.0"},"canonical_sha256":"45aba6ef9bf31c513a614c292400d3cc6b472988892964e549c140e2c3045cbe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:01.651376Z","signature_b64":"zqh6Rh1XwaL4KFRLcYGBp5DwfWyejgXJ+Ooy5jHkqTW3ACkz+rA8ThLUPnL0ZGKje4sn6A4AS1+tHYpJajrpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45aba6ef9bf31c513a614c292400d3cc6b472988892964e549c140e2c3045cbe","last_reissued_at":"2026-06-24T01:15:01.650875Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:01.650875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.08287","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":"2026-06-24T01:15:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YEY9LhfmqTAhP5xG000tdlz5nEBJ4HUkDo7oX6DlQ5/yCcMZVd9cqaKnXAy4u6IoOvYzLCD1NR71Uz2JvO9nBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:51:18.323363Z"},"content_sha256":"8d00ba45f813eead71f1ef7b796cbcbe77a9ecb1aeda4a7c4fd930681535c738","schema_version":"1.0","event_id":"sha256:8d00ba45f813eead71f1ef7b796cbcbe77a9ecb1aeda4a7c4fd930681535c738"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IWV2N3436MOFCOTBJQUSIAGTZR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Hamish Flynn, Ingmar Posner, Jan Peters, Joe Watson","submitted_at":"2026-03-09T12:03:25Z","abstract_excerpt":"We analyze the Bayesian regret of the Gaussian process posterior sampling reinforcement learning (GP-PSRL) algorithm. Posterior sampling is a heuristic for decision-making under uncertainty that has been used to develop successful algorithms for a variety of continuous control problems. However, theoretical work on GP-PSRL is limited. All known regret bounds either have a sub-optimal growth rate, require strong smoothness assumptions, or fail to properly account for the fact that the set of possible system states is unbounded. Through a recursive application of the Borell-Tsirelson-Ibragimov-S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.08287","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/2603.08287/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":"2026-06-24T01:15:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ftHpi9rnmIaYctiHk1LoBDqCDpGj3+mPLZQPs4k1W+4NLHHWKw73UKpI7Fh5k9QAtKkT4fSoXBIFn71QRd4MBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:51:18.324314Z"},"content_sha256":"a4c749bd4a2617d40746aca7be4b58b1f265e36c7705feee475fc002bd1c9614","schema_version":"1.0","event_id":"sha256:a4c749bd4a2617d40746aca7be4b58b1f265e36c7705feee475fc002bd1c9614"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IWV2N3436MOFCOTBJQUSIAGTZR/bundle.json","state_url":"https://pith.science/pith/IWV2N3436MOFCOTBJQUSIAGTZR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IWV2N3436MOFCOTBJQUSIAGTZR/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":"2026-08-11T05:51:18Z","links":{"resolver":"https://pith.science/pith/IWV2N3436MOFCOTBJQUSIAGTZR","bundle":"https://pith.science/pith/IWV2N3436MOFCOTBJQUSIAGTZR/bundle.json","state":"https://pith.science/pith/IWV2N3436MOFCOTBJQUSIAGTZR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IWV2N3436MOFCOTBJQUSIAGTZR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IWV2N3436MOFCOTBJQUSIAGTZR","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":"6be0e328e7bb3b821155f1b189cdf32a345c60d9edfbddc774e18ace0f81d9dd","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-03-09T12:03:25Z","title_canon_sha256":"5a65a033180fef1d3a47461ee4d07f1a851b892733a540c482ad6a86d90aff0e"},"schema_version":"1.0","source":{"id":"2603.08287","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.08287","created_at":"2026-06-24T01:15:01Z"},{"alias_kind":"arxiv_version","alias_value":"2603.08287v2","created_at":"2026-06-24T01:15:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.08287","created_at":"2026-06-24T01:15:01Z"},{"alias_kind":"pith_short_12","alias_value":"IWV2N3436MOF","created_at":"2026-06-24T01:15:01Z"},{"alias_kind":"pith_short_16","alias_value":"IWV2N3436MOFCOTB","created_at":"2026-06-24T01:15:01Z"},{"alias_kind":"pith_short_8","alias_value":"IWV2N343","created_at":"2026-06-24T01:15:01Z"}],"graph_snapshots":[{"event_id":"sha256:a4c749bd4a2617d40746aca7be4b58b1f265e36c7705feee475fc002bd1c9614","target":"graph","created_at":"2026-06-24T01:15:01Z","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/2603.08287/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We analyze the Bayesian regret of the Gaussian process posterior sampling reinforcement learning (GP-PSRL) algorithm. Posterior sampling is a heuristic for decision-making under uncertainty that has been used to develop successful algorithms for a variety of continuous control problems. However, theoretical work on GP-PSRL is limited. All known regret bounds either have a sub-optimal growth rate, require strong smoothness assumptions, or fail to properly account for the fact that the set of possible system states is unbounded. Through a recursive application of the Borell-Tsirelson-Ibragimov-S","authors_text":"Hamish Flynn, Ingmar Posner, Jan Peters, Joe Watson","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-03-09T12:03:25Z","title":"Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.08287","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":"sha256:8d00ba45f813eead71f1ef7b796cbcbe77a9ecb1aeda4a7c4fd930681535c738","target":"record","created_at":"2026-06-24T01:15:01Z","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":"6be0e328e7bb3b821155f1b189cdf32a345c60d9edfbddc774e18ace0f81d9dd","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-03-09T12:03:25Z","title_canon_sha256":"5a65a033180fef1d3a47461ee4d07f1a851b892733a540c482ad6a86d90aff0e"},"schema_version":"1.0","source":{"id":"2603.08287","kind":"arxiv","version":2}},"canonical_sha256":"45aba6ef9bf31c513a614c292400d3cc6b472988892964e549c140e2c3045cbe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45aba6ef9bf31c513a614c292400d3cc6b472988892964e549c140e2c3045cbe","first_computed_at":"2026-06-24T01:15:01.650875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:01.650875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zqh6Rh1XwaL4KFRLcYGBp5DwfWyejgXJ+Ooy5jHkqTW3ACkz+rA8ThLUPnL0ZGKje4sn6A4AS1+tHYpJajrpDw==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:01.651376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.08287","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d00ba45f813eead71f1ef7b796cbcbe77a9ecb1aeda4a7c4fd930681535c738","sha256:a4c749bd4a2617d40746aca7be4b58b1f265e36c7705feee475fc002bd1c9614"],"state_sha256":"54478ee5bca7e2b65b2832f5d2f28e14a5e9aa3d8c299f166579db794033dad8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qf0GhEFWZBniz8br08RoL+tg8tL/zPkbeCoHz5ECp0AROxGsUK/aXJ24GJSM1DkfX1hT0uvzr1WaMD5p4lWqAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T05:51:18.332276Z","bundle_sha256":"f3546a9d35a11293acdb67ac05a3bf81656151fcf5452540c44bac989dddbbfb"}}