{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OV2CHQL6DDPIO7LWRQIYNG3LDN","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":"287b4301e761ce2ec49d1b15a5f2a34a6675062bdf27bd0d4a5b62089c44c7e4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-27T11:59:26Z","title_canon_sha256":"87c3a71495184d0cd886f9918546912c5e5c242035c2cd2b16f4edce688ced1f"},"schema_version":"1.0","source":{"id":"2605.28364","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28364","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28364v1","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28364","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"OV2CHQL6DDPI","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"OV2CHQL6DDPIO7LW","created_at":"2026-05-28T01:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"OV2CHQL6","created_at":"2026-05-28T01:05:16Z"}],"graph_snapshots":[{"event_id":"sha256:4609e34df510125c7868b61d6b6ec4d6b85c51d3602792885a01058429a617c0","target":"graph","created_at":"2026-05-28T01:05:16Z","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/2605.28364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with multinomial logistic (MNL) function approximation has become an important framework due to its flexibility and broad applicability. While existing studies have established regret guarantees under worst-case analysis, they do not capture how performance depends on the variability of the interaction between the learner and the environment. In this paper, we develop a new theoretical analysis for MNL-based Markov decision processes that yields explicit variance-adaptive regret bounds. Our algorithm is computationally efficient and achieves the instance-wise optimal rat","authors_text":"Assaf Zeevi, Garud Iyengar, Min-hwan Oh, Wonyoung Kim","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-27T11:59:26Z","title":"Variance-Adaptive Optimal Algorithm for Reinforcement Learning with Multinomial Logit Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28364","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":"sha256:08f2059aaa4386e3861dff6a7fd0c2bba495d13186f38f0941d79e8a13519790","target":"record","created_at":"2026-05-28T01:05:16Z","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":"287b4301e761ce2ec49d1b15a5f2a34a6675062bdf27bd0d4a5b62089c44c7e4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-27T11:59:26Z","title_canon_sha256":"87c3a71495184d0cd886f9918546912c5e5c242035c2cd2b16f4edce688ced1f"},"schema_version":"1.0","source":{"id":"2605.28364","kind":"arxiv","version":1}},"canonical_sha256":"757423c17e18de877d768c11869b6b1b7edb758b72a669de2a7391613aa1689c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"757423c17e18de877d768c11869b6b1b7edb758b72a669de2a7391613aa1689c","first_computed_at":"2026-05-28T01:05:16.019049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:16.019049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"odaRGDvogIBJ67djcHnDP/jTKBpBJSbAnNQTeotsFVMLIZDnb1L5mXGNwoebzilNo4/GbxQlda4/hIl82rNKAQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:16.019519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28364","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08f2059aaa4386e3861dff6a7fd0c2bba495d13186f38f0941d79e8a13519790","sha256:4609e34df510125c7868b61d6b6ec4d6b85c51d3602792885a01058429a617c0"],"state_sha256":"4f83a2c46b1599a5e62626a3929db2bc69f38a18692ce6bb6da0e31bddb04c20"}