{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X762V5T5FGJIXPMIX5G7HZUXAE","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":"ecc3a2140438e8aa2ae73754da46e102c4cb542198ee8b77f6403b0fd2fbd3f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T15:35:48Z","title_canon_sha256":"7201beff1382352907298597c499b60e91940b3f761ebec1bd1a6b2c35d6e824"},"schema_version":"1.0","source":{"id":"2501.09611","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09611","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09611v1","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09611","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"X762V5T5FGJI","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"pith_short_16","alias_value":"X762V5T5FGJIXPMI","created_at":"2026-07-05T10:01:49Z"},{"alias_kind":"pith_short_8","alias_value":"X762V5T5","created_at":"2026-07-05T10:01:49Z"}],"graph_snapshots":[{"event_id":"sha256:be7078ca57d7fd584b9662d655fcb506ecf00f2ff1d9ff2a34ca4eec65a6ede1","target":"graph","created_at":"2026-07-05T10:01:49Z","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/2501.09611/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Posterior Sampling for Reinforcement Learning (PSRL) is a well-known algorithm that augments model-based reinforcement learning (MBRL) algorithms with Thompson sampling. PSRL maintains posterior distributions of the environment transition dynamics and the reward function, which are intractable for tasks with high-dimensional state and action spaces. Recent works show that dropout, used in conjunction with neural networks, induces variational distributions that can approximate these posteriors. In this paper, we propose Event-based Variational Distributions for Exploration (EVaDE), which are va","authors_text":"Dixant Mittal, Siddharth Aravindan, Wee Sun Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T15:35:48Z","title":"EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09611","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":"sha256:4e973cf23da75f9ca8719ae6c6291e675ea1b8c1bcfa0b170f4db401d3627f92","target":"record","created_at":"2026-07-05T10:01:49Z","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":"ecc3a2140438e8aa2ae73754da46e102c4cb542198ee8b77f6403b0fd2fbd3f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T15:35:48Z","title_canon_sha256":"7201beff1382352907298597c499b60e91940b3f761ebec1bd1a6b2c35d6e824"},"schema_version":"1.0","source":{"id":"2501.09611","kind":"arxiv","version":1}},"canonical_sha256":"bffdaaf67d29928bbd88bf4df3e697010fc0cf0747d0a9b5ca6326d69b67f4ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bffdaaf67d29928bbd88bf4df3e697010fc0cf0747d0a9b5ca6326d69b67f4ad","first_computed_at":"2026-07-05T10:01:49.763954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:49.763954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jqmfz+iRcY7U1JMIj50fok8qW/Qtf55WJbwy7xle3NIj6VgestateTAn5xw2Wqwlr+oJwIo/LQ47e+VCOlZbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:49.764498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09611","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e973cf23da75f9ca8719ae6c6291e675ea1b8c1bcfa0b170f4db401d3627f92","sha256:be7078ca57d7fd584b9662d655fcb506ecf00f2ff1d9ff2a34ca4eec65a6ede1"],"state_sha256":"9ffef127575c7b6207e38a1647268442869c966a2005d071aabaca8e6d98ab39"}