{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6Y2K6T2GG7UNX2WPNIURXEHKME","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":"1433f670b5f9dd997bd6074186dce61d240e4bae8dcad4911a8cd19c4bbb2a30","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T23:43:53Z","title_canon_sha256":"2646223115b2d96ac7aa89aed52ad45b7d40f353c8a725aca2a896de7abdae79"},"schema_version":"1.0","source":{"id":"2605.20271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20271","created_at":"2026-05-21T00:04:23Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20271v1","created_at":"2026-05-21T00:04:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20271","created_at":"2026-05-21T00:04:23Z"},{"alias_kind":"pith_short_12","alias_value":"6Y2K6T2GG7UN","created_at":"2026-05-21T00:04:23Z"},{"alias_kind":"pith_short_16","alias_value":"6Y2K6T2GG7UNX2WP","created_at":"2026-05-21T00:04:23Z"},{"alias_kind":"pith_short_8","alias_value":"6Y2K6T2G","created_at":"2026-05-21T00:04:23Z"}],"graph_snapshots":[{"event_id":"sha256:64fac2344d147925b6c9009fdd6835d7a0c6c7d6037f874d0784053af6665f3e","target":"graph","created_at":"2026-05-21T00:04:23Z","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/2605.20271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We develop a rigorous statistical theory of multi-head attention (MHA) as an ensemble of Nadaraya-Watson (NW) kernel regression estimators. Building on the algebraic identity between single-head softmax attention and the NW estimator, we prove that MHA is a structured ensemble of H NW estimators, each operating in a distinct learned projection subspace of the key space. We derive an explicit Bias-Variance-Covariance decomposition of the MHA mean squared error, showing that variance reduction depends not merely on the number of heads H but fundamentally on the decorrelation of head outputs. Dec","authors_text":"Ernest Fokou\\'e","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T23:43:53Z","title":"Multi-Head Attention as Ensemble Nadaraya-Watson Estimation: Variance Reduction, Decorrelation, and Optimal Head Diversity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20271","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":"sha256:5bc5fe852eaaa42125aa05f9373c11f42bdb718be02411e74422cc44422873d8","target":"record","created_at":"2026-05-21T00:04:23Z","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":"1433f670b5f9dd997bd6074186dce61d240e4bae8dcad4911a8cd19c4bbb2a30","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T23:43:53Z","title_canon_sha256":"2646223115b2d96ac7aa89aed52ad45b7d40f353c8a725aca2a896de7abdae79"},"schema_version":"1.0","source":{"id":"2605.20271","kind":"arxiv","version":1}},"canonical_sha256":"f634af4f4637e8dbeacf6a291b90ea6115b50f43012b49cefdb8bbe39197592f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f634af4f4637e8dbeacf6a291b90ea6115b50f43012b49cefdb8bbe39197592f","first_computed_at":"2026-05-21T00:04:23.492719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T00:04:23.492719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bW2lOL3L9rFf9Abc5NmtRMfue/MWywrQEvrXnWofZXfGq+O52ssoqcDrDOXbB47WTCCT+ZNBQg2gB8j4nYr3DQ==","signature_status":"signed_v1","signed_at":"2026-05-21T00:04:23.493325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bc5fe852eaaa42125aa05f9373c11f42bdb718be02411e74422cc44422873d8","sha256:64fac2344d147925b6c9009fdd6835d7a0c6c7d6037f874d0784053af6665f3e"],"state_sha256":"c32fc419fae3244b5b60d65d4fd68be77d2f339f510cb20f72314b3ef8ebebd1"}