{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VRN65EDECTKWGE7Z7EVNBDNJDG","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":"92370d7a6bd8cbba3723efe6e40eb33e395d09345e0c857798335cf91d39206f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-30T09:35:45Z","title_canon_sha256":"4588c15144c555396512791aba373b80f868f2c93732e5748f0269e7051da47b"},"schema_version":"1.0","source":{"id":"2412.20824","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20824","created_at":"2026-07-05T10:09:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20824v2","created_at":"2026-07-05T10:09:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20824","created_at":"2026-07-05T10:09:50Z"},{"alias_kind":"pith_short_12","alias_value":"VRN65EDECTKW","created_at":"2026-07-05T10:09:50Z"},{"alias_kind":"pith_short_16","alias_value":"VRN65EDECTKWGE7Z","created_at":"2026-07-05T10:09:50Z"},{"alias_kind":"pith_short_8","alias_value":"VRN65EDE","created_at":"2026-07-05T10:09:50Z"}],"graph_snapshots":[{"event_id":"sha256:a8c411622dc51c976c9ac4d17ef0a5e0cc5d79ec551432b3c5f3b74133a83175","target":"graph","created_at":"2026-07-05T10:09:50Z","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/2412.20824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Common assumptions, like linear or RKHS models, and Gaussian or log-concave posteriors over the models, do not explain practical success of RL across a wider range of distributions and models. Thus, we study how to design RL algorithms with sublinear regret for isoperimetric distributions, specifically the ones satisfying the Log-Sobolev Inequality (LSI). LSI distributions include the standard setups of RL theory, and others, such as many non-log-concave and perturbed distributions. First, we show that the Posterior Sampling-based RL (PSRL) algorithm yields sublinear regret if the data distrib","authors_text":"Christos Dimitrakakis, Debabrota Basu, Emilio Jorge","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-30T09:35:45Z","title":"Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20824","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":"sha256:5992066e6ca588904f40e1d456ba86be84a66b5633e6a2af5f4c733d40c65fa0","target":"record","created_at":"2026-07-05T10:09:50Z","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":"92370d7a6bd8cbba3723efe6e40eb33e395d09345e0c857798335cf91d39206f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-30T09:35:45Z","title_canon_sha256":"4588c15144c555396512791aba373b80f868f2c93732e5748f0269e7051da47b"},"schema_version":"1.0","source":{"id":"2412.20824","kind":"arxiv","version":2}},"canonical_sha256":"ac5bee906414d56313f9f92ad08da91984a6e89b91b05bd9ff2a9c9f27c76723","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac5bee906414d56313f9f92ad08da91984a6e89b91b05bd9ff2a9c9f27c76723","first_computed_at":"2026-07-05T10:09:50.899808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:50.899808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y7ui/c0F/Y0vqN2y9fIhv2i/bn+k1wInMfMCNhBvweb1lvzhsk4bhlUaxVuBm2PkDt1L0CyM4Le6W/Y2pxAaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:50.900278Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20824","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5992066e6ca588904f40e1d456ba86be84a66b5633e6a2af5f4c733d40c65fa0","sha256:a8c411622dc51c976c9ac4d17ef0a5e0cc5d79ec551432b3c5f3b74133a83175"],"state_sha256":"1b634376f01b4da104b666cdb1d34917f2c6f8a6267450c28ca2fafb93f0bdb0"}