{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IQKTB46QPA2JA26TISTZQH6C6X","short_pith_number":"pith:IQKTB46Q","canonical_record":{"source":{"id":"2411.10906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T22:51:52Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"f07d3c8ed21e20c93e6a10bbf6485d6de804f1f65d7644d92ba13aa974433847","abstract_canon_sha256":"6d9543e1cc0982a03fc37be2f2bc11285ef1a4e155689afc25df02268a09494b"},"schema_version":"1.0"},"canonical_sha256":"441530f3d07834906bd344a7981fc2f5cd88aa0f441558cef9d9b99004dbf81b","source":{"kind":"arxiv","id":"2411.10906","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10906","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10906v1","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10906","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"pith_short_12","alias_value":"IQKTB46QPA2J","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"pith_short_16","alias_value":"IQKTB46QPA2JA26T","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"pith_short_8","alias_value":"IQKTB46Q","created_at":"2026-07-05T09:36:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IQKTB46QPA2JA26TISTZQH6C6X","target":"record","payload":{"canonical_record":{"source":{"id":"2411.10906","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T22:51:52Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"f07d3c8ed21e20c93e6a10bbf6485d6de804f1f65d7644d92ba13aa974433847","abstract_canon_sha256":"6d9543e1cc0982a03fc37be2f2bc11285ef1a4e155689afc25df02268a09494b"},"schema_version":"1.0"},"canonical_sha256":"441530f3d07834906bd344a7981fc2f5cd88aa0f441558cef9d9b99004dbf81b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:24.525546Z","signature_b64":"D9Usebkb4y9uOx+BWQ2iYDgcZal/+qj2Nt0xkNR0MMoxtbe68WPjIwhWCUFMe5Ki6jVS+6RJCz7Ju1fkGThgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"441530f3d07834906bd344a7981fc2f5cd88aa0f441558cef9d9b99004dbf81b","last_reissued_at":"2026-07-05T09:36:24.525112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:24.525112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.10906","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":"2026-07-05T09:36:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r0vyUKsyWuDe1DYZk1aZ9WuTZ+1LH3ejY2wSHzYRY63kIjst+nIDeATW8NR09a1EpKHyp7Hj5/CRSDdDi9ncDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:20:02.834894Z"},"content_sha256":"aee35570a9749cba928ac1461464027c90b65a79bf5815b5e98c856fa2d616a6","schema_version":"1.0","event_id":"sha256:aee35570a9749cba928ac1461464027c90b65a79bf5815b5e98c856fa2d616a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IQKTB46QPA2JA26TISTZQH6C6X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient, Low-Regret, Online Reinforcement Learning for Linear MDPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Arnab Bhattacharyya, Dimitrios Myrisiotis, Philips George John, Silviu Maniu, Zhenan Wu","submitted_at":"2024-11-16T22:51:52Z","abstract_excerpt":"Reinforcement learning algorithms are usually stated without theoretical guarantees regarding their performance. Recently, Jin, Yang, Wang, and Jordan (COLT 2020) showed a polynomial-time reinforcement learning algorithm (namely, LSVI-UCB) for the setting of linear Markov decision processes, and provided theoretical guarantees regarding its running time and regret. In real-world scenarios, however, the space usage of this algorithm can be prohibitive due to a utilized linear regression step. We propose and analyze two modifications of LSVI-UCB, which alternate periods of learning and not-learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10906","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/2411.10906/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":"2026-07-05T09:36:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iXCgnx0QARgDbmg4q1Sr4hekoF5wl3YQAeqdw3ESA6YkCMWwZrtwQpwMV99jFLeAV8YVhqDn9r6q2Snza1LpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T08:20:02.835310Z"},"content_sha256":"3d488235832941e65f4885d733f3bbf4661627d3599eee4a7b81f3d116559e7d","schema_version":"1.0","event_id":"sha256:3d488235832941e65f4885d733f3bbf4661627d3599eee4a7b81f3d116559e7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQKTB46QPA2JA26TISTZQH6C6X/bundle.json","state_url":"https://pith.science/pith/IQKTB46QPA2JA26TISTZQH6C6X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQKTB46QPA2JA26TISTZQH6C6X/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":"2026-08-21T08:20:02Z","links":{"resolver":"https://pith.science/pith/IQKTB46QPA2JA26TISTZQH6C6X","bundle":"https://pith.science/pith/IQKTB46QPA2JA26TISTZQH6C6X/bundle.json","state":"https://pith.science/pith/IQKTB46QPA2JA26TISTZQH6C6X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQKTB46QPA2JA26TISTZQH6C6X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IQKTB46QPA2JA26TISTZQH6C6X","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":"6d9543e1cc0982a03fc37be2f2bc11285ef1a4e155689afc25df02268a09494b","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T22:51:52Z","title_canon_sha256":"f07d3c8ed21e20c93e6a10bbf6485d6de804f1f65d7644d92ba13aa974433847"},"schema_version":"1.0","source":{"id":"2411.10906","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10906","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10906v1","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10906","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"pith_short_12","alias_value":"IQKTB46QPA2J","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"pith_short_16","alias_value":"IQKTB46QPA2JA26T","created_at":"2026-07-05T09:36:24Z"},{"alias_kind":"pith_short_8","alias_value":"IQKTB46Q","created_at":"2026-07-05T09:36:24Z"}],"graph_snapshots":[{"event_id":"sha256:3d488235832941e65f4885d733f3bbf4661627d3599eee4a7b81f3d116559e7d","target":"graph","created_at":"2026-07-05T09:36:24Z","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/2411.10906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning algorithms are usually stated without theoretical guarantees regarding their performance. Recently, Jin, Yang, Wang, and Jordan (COLT 2020) showed a polynomial-time reinforcement learning algorithm (namely, LSVI-UCB) for the setting of linear Markov decision processes, and provided theoretical guarantees regarding its running time and regret. In real-world scenarios, however, the space usage of this algorithm can be prohibitive due to a utilized linear regression step. We propose and analyze two modifications of LSVI-UCB, which alternate periods of learning and not-learn","authors_text":"Arnab Bhattacharyya, Dimitrios Myrisiotis, Philips George John, Silviu Maniu, Zhenan Wu","cross_cats":["cs.DS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T22:51:52Z","title":"Efficient, Low-Regret, Online Reinforcement Learning for Linear MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10906","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:aee35570a9749cba928ac1461464027c90b65a79bf5815b5e98c856fa2d616a6","target":"record","created_at":"2026-07-05T09:36:24Z","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":"6d9543e1cc0982a03fc37be2f2bc11285ef1a4e155689afc25df02268a09494b","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T22:51:52Z","title_canon_sha256":"f07d3c8ed21e20c93e6a10bbf6485d6de804f1f65d7644d92ba13aa974433847"},"schema_version":"1.0","source":{"id":"2411.10906","kind":"arxiv","version":1}},"canonical_sha256":"441530f3d07834906bd344a7981fc2f5cd88aa0f441558cef9d9b99004dbf81b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"441530f3d07834906bd344a7981fc2f5cd88aa0f441558cef9d9b99004dbf81b","first_computed_at":"2026-07-05T09:36:24.525112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:24.525112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D9Usebkb4y9uOx+BWQ2iYDgcZal/+qj2Nt0xkNR0MMoxtbe68WPjIwhWCUFMe5Ki6jVS+6RJCz7Ju1fkGThgDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:24.525546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10906","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aee35570a9749cba928ac1461464027c90b65a79bf5815b5e98c856fa2d616a6","sha256:3d488235832941e65f4885d733f3bbf4661627d3599eee4a7b81f3d116559e7d"],"state_sha256":"0aad33f765aa484d88565fcf5ddeb70ecebbc4845c60d6aa452a2bbd5d55501d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0QNS13o6Z+rq4X4ZKLPLXkePQGpTQL0epIHEHLCWCsBUPzzTMTHYwR6d6abvd6UPjPaC1sOelvvvkbNBYFpPAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T08:20:02.839570Z","bundle_sha256":"746ae3f29c56b15502ee1b177e6bae97cc7401e66ec97518d517e097df67b096"}}