{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YZQLU3K4VXFUGGOQSXPE5HSF2J","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":"df15d7376751ecf37115e9a9ec9f0ed77a5fafba6943b330a1f91db935de4209","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-27T02:53:44Z","title_canon_sha256":"857fac3f3b6206f95976c335f1545046b325559dd1de04b88c57e6d358ded31a"},"schema_version":"1.0","source":{"id":"2112.13487","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13487","created_at":"2026-07-05T06:29:29Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13487v3","created_at":"2026-07-05T06:29:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13487","created_at":"2026-07-05T06:29:29Z"},{"alias_kind":"pith_short_12","alias_value":"YZQLU3K4VXFU","created_at":"2026-07-05T06:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"YZQLU3K4VXFUGGOQ","created_at":"2026-07-05T06:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"YZQLU3K4","created_at":"2026-07-05T06:29:29Z"}],"graph_snapshots":[{"event_id":"sha256:d28418089344c85d0490f653ef686b7c0d561b10161f80747a9bee2a42f5e796","target":"graph","created_at":"2026-07-05T06:29:29Z","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/2112.13487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A fundamental challenge in interactive learning and decision making, ranging from bandit problems to reinforcement learning, is to provide sample-efficient, adaptive learning algorithms that achieve near-optimal regret. This question is analogous to the classical problem of optimal (supervised) statistical learning, where there are well-known complexity measures (e.g., VC dimension and Rademacher complexity) that govern the statistical complexity of learning. However, characterizing the statistical complexity of interactive learning is substantially more challenging due to the adaptive nature ","authors_text":"Alexander Rakhlin, Dylan J. Foster, Jian Qian, Sham M. Kakade","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-27T02:53:44Z","title":"The Statistical Complexity of Interactive Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13487","kind":"arxiv","version":3},"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":"sha256:68e7620ef3acc7d4e76e18a0ef5161cd8ea3d65bb4de0ba6bb93cc4a11a5c2f0","target":"record","created_at":"2026-07-05T06:29:29Z","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":"df15d7376751ecf37115e9a9ec9f0ed77a5fafba6943b330a1f91db935de4209","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-27T02:53:44Z","title_canon_sha256":"857fac3f3b6206f95976c335f1545046b325559dd1de04b88c57e6d358ded31a"},"schema_version":"1.0","source":{"id":"2112.13487","kind":"arxiv","version":3}},"canonical_sha256":"c660ba6d5cadcb4319d095de4e9e45d2544c150a7035fb9190670a5af154cdc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c660ba6d5cadcb4319d095de4e9e45d2544c150a7035fb9190670a5af154cdc1","first_computed_at":"2026-07-05T06:29:29.290100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:29:29.290100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PvGuYMK1FntOJzn2MMonanwvsCa7rpUt/lka/zs7vSNfPVzwvEOdjUeHKI3IbkJcysFebcFbR+8ILkbkj69aBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:29:29.290533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.13487","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68e7620ef3acc7d4e76e18a0ef5161cd8ea3d65bb4de0ba6bb93cc4a11a5c2f0","sha256:d28418089344c85d0490f653ef686b7c0d561b10161f80747a9bee2a42f5e796"],"state_sha256":"e997d366b776ee43bf845fc136dd1d7972b9fc0f52cd2ae07cb56f9d8683918c"}