{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CCQ4XKRDFGJVD25EEVK6ATB5KZ","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":"cb819f6dedd0e09e4b2608a76fa97ed0925fd6c1d9ac733ae95a396944880e73","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-05T00:39:05Z","title_canon_sha256":"aa558d68fe50e1494e588984af50d0bda04e8c4f5792a980360e7fb6a5ea3277"},"schema_version":"1.0","source":{"id":"2103.03404","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03404","created_at":"2026-07-05T06:36:19Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03404v2","created_at":"2026-07-05T06:36:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03404","created_at":"2026-07-05T06:36:19Z"},{"alias_kind":"pith_short_12","alias_value":"CCQ4XKRDFGJV","created_at":"2026-07-05T06:36:19Z"},{"alias_kind":"pith_short_16","alias_value":"CCQ4XKRDFGJVD25E","created_at":"2026-07-05T06:36:19Z"},{"alias_kind":"pith_short_8","alias_value":"CCQ4XKRD","created_at":"2026-07-05T06:36:19Z"}],"graph_snapshots":[{"event_id":"sha256:7dbcc34fb3e570f7a72f0e9fd9cfbd8ad2a9bc1a1e611e10264bd8be6fabddb2","target":"graph","created_at":"2026-07-05T06:36:19Z","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/2103.03404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their output can be decomposed into a sum of smaller terms, each involving the operation of a sequence of attention heads across layers. Using this decomposition, we prove that self-attention possesses a strong inductive bias towards \"token uniformity\". Specifically, without skip connections or multi-layer perceptrons (MLPs), the output converges doubly exponential","authors_text":"Andreas Loukas, Jean-Baptiste Cordonnier, Yihe Dong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-05T00:39:05Z","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03404","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":"sha256:4e33158bb1b85c86112882ced99f49971b3b20853c8aa2603b447abc240fe54f","target":"record","created_at":"2026-07-05T06:36:19Z","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":"cb819f6dedd0e09e4b2608a76fa97ed0925fd6c1d9ac733ae95a396944880e73","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-05T00:39:05Z","title_canon_sha256":"aa558d68fe50e1494e588984af50d0bda04e8c4f5792a980360e7fb6a5ea3277"},"schema_version":"1.0","source":{"id":"2103.03404","kind":"arxiv","version":2}},"canonical_sha256":"10a1cbaa23299351eba42555e04c3d567e64e2ee6b71a50ebb915167277a04c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10a1cbaa23299351eba42555e04c3d567e64e2ee6b71a50ebb915167277a04c7","first_computed_at":"2026-07-05T06:36:19.014621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:19.014621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j1jMhT++ZySlPZontFXzP4RJgQaKPjTr8W0CtFGZjQMg/jAajKjMyKY2gtf3jePL+YKsg/4D8yJdzddYNOjRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:19.015114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.03404","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e33158bb1b85c86112882ced99f49971b3b20853c8aa2603b447abc240fe54f","sha256:7dbcc34fb3e570f7a72f0e9fd9cfbd8ad2a9bc1a1e611e10264bd8be6fabddb2"],"state_sha256":"53fa5b1ccba5f14b7857b7f2cf0dfbdec970c086f3b42bfd3b9e1f9db0a62007"}