{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:X3LAZX6CGB6L6GYSEQC5PCD4GS","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":"b5f474aa68163c218fd68ea32d206f50cfa98b1ccd712a062de01ccb09ac39fc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T16:36:19Z","title_canon_sha256":"ed267dc6cca81eaceca6d8db617c300a73f5d2b3803b62461afd5223508e2e86"},"schema_version":"1.0","source":{"id":"2110.10090","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10090","created_at":"2026-07-05T04:34:26Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10090v2","created_at":"2026-07-05T04:34:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10090","created_at":"2026-07-05T04:34:26Z"},{"alias_kind":"pith_short_12","alias_value":"X3LAZX6CGB6L","created_at":"2026-07-05T04:34:26Z"},{"alias_kind":"pith_short_16","alias_value":"X3LAZX6CGB6L6GYS","created_at":"2026-07-05T04:34:26Z"},{"alias_kind":"pith_short_8","alias_value":"X3LAZX6C","created_at":"2026-07-05T04:34:26Z"}],"graph_snapshots":[{"event_id":"sha256:f55df314d92b9538f0ec5baecd5d8de6aa0458ec625e607083ce1eba5164e7f9","target":"graph","created_at":"2026-07-05T04:34:26Z","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/2110.10090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-attention, an architectural motif designed to model long-range interactions in sequential data, has driven numerous recent breakthroughs in natural language processing and beyond. This work provides a theoretical analysis of the inductive biases of self-attention modules. Our focus is to rigorously establish which functions and long-range dependencies self-attention blocks prefer to represent. Our main result shows that bounded-norm Transformer networks \"create sparse variables\": a single self-attention head can represent a sparse function of the input sequence, with sample complexity sca","authors_text":"Benjamin L. Edelman, Cyril Zhang, Sham Kakade, Surbhi Goel","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T16:36:19Z","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10090","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":"sha256:9bab1c5770d35940baa41942802044063aad3fc42910022f812b155f37163f46","target":"record","created_at":"2026-07-05T04:34:26Z","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":"b5f474aa68163c218fd68ea32d206f50cfa98b1ccd712a062de01ccb09ac39fc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T16:36:19Z","title_canon_sha256":"ed267dc6cca81eaceca6d8db617c300a73f5d2b3803b62461afd5223508e2e86"},"schema_version":"1.0","source":{"id":"2110.10090","kind":"arxiv","version":2}},"canonical_sha256":"bed60cdfc2307cbf1b122405d7887c3491a20ad93557d1cf8706700b258b3499","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bed60cdfc2307cbf1b122405d7887c3491a20ad93557d1cf8706700b258b3499","first_computed_at":"2026-07-05T04:34:26.800219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:34:26.800219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cDwzFjlsKIM1Ig/Sk7AlcEs9Dvd0WcQ5d36hNFJX57tx6QXMGtzcnMwlqJenRiC7+1eFvMW2tmHq4ic2c5oSAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:34:26.800741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.10090","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bab1c5770d35940baa41942802044063aad3fc42910022f812b155f37163f46","sha256:f55df314d92b9538f0ec5baecd5d8de6aa0458ec625e607083ce1eba5164e7f9"],"state_sha256":"ec45d4fe77f3bd5258bb79f39ba2fad6ab44c678e3ebb6328e45808c91241955"}