{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KLWDZLIYKIG6PQV4GGPU63C2AD","short_pith_number":"pith:KLWDZLIY","schema_version":"1.0","canonical_sha256":"52ec3cad18520de7c2bc319f4f6c5a00fb9eef437fb5a15ec61787b7af5ebb8c","source":{"kind":"arxiv","id":"2202.12166","version":1},"attestation_state":"computed","paper":{"title":"Attention Enables Zero Approximation Error","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ding-Xuan Zhou, Guang Cheng, Yidong Ouyang, Zhiying Fang","submitted_at":"2022-02-24T16:06:01Z","abstract_excerpt":"Deep learning models have been widely applied in various aspects of daily life. Many variant models based on deep learning structures have achieved even better performances. Attention-based architectures have become almost ubiquitous in deep learning structures. Especially, the transformer model has now defeated the convolutional neural network in image classification tasks to become the most widely used tool. However, the theoretical properties of attention-based models are seldom considered. In this work, we show that with suitable adaptations, the single-head self-attention transformer with"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2202.12166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-24T16:06:01Z","cross_cats_sorted":[],"title_canon_sha256":"68ef352744fb1847bca21691301ae35b737ffa9dda32acc180e6369e0e189012","abstract_canon_sha256":"81b2ef6ea5a2ee008e08d156d230cda71ce163fbdd2b36cd454d59e612adbee5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:50.645631Z","signature_b64":"nsw8sIKJw60fJ3CTJd4rzMSTc0Ok0kUsLF4amSAxQdRm2JAPl0F+RXf7tzkHSlQ30itzVZ1QYIqDqReI3TuqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52ec3cad18520de7c2bc319f4f6c5a00fb9eef437fb5a15ec61787b7af5ebb8c","last_reissued_at":"2026-07-05T03:59:50.645214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:50.645214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention Enables Zero Approximation Error","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ding-Xuan Zhou, Guang Cheng, Yidong Ouyang, Zhiying Fang","submitted_at":"2022-02-24T16:06:01Z","abstract_excerpt":"Deep learning models have been widely applied in various aspects of daily life. Many variant models based on deep learning structures have achieved even better performances. Attention-based architectures have become almost ubiquitous in deep learning structures. Especially, the transformer model has now defeated the convolutional neural network in image classification tasks to become the most widely used tool. However, the theoretical properties of attention-based models are seldom considered. In this work, we show that with suitable adaptations, the single-head self-attention transformer with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12166","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.12166/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.12166","created_at":"2026-07-05T03:59:50.645269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.12166v1","created_at":"2026-07-05T03:59:50.645269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12166","created_at":"2026-07-05T03:59:50.645269+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLWDZLIYKIG6","created_at":"2026-07-05T03:59:50.645269+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLWDZLIYKIG6PQV4","created_at":"2026-07-05T03:59:50.645269+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLWDZLIY","created_at":"2026-07-05T03:59:50.645269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLWDZLIYKIG6PQV4GGPU63C2AD","json":"https://pith.science/pith/KLWDZLIYKIG6PQV4GGPU63C2AD.json","graph_json":"https://pith.science/api/pith-number/KLWDZLIYKIG6PQV4GGPU63C2AD/graph.json","events_json":"https://pith.science/api/pith-number/KLWDZLIYKIG6PQV4GGPU63C2AD/events.json","paper":"https://pith.science/paper/KLWDZLIY"},"agent_actions":{"view_html":"https://pith.science/pith/KLWDZLIYKIG6PQV4GGPU63C2AD","download_json":"https://pith.science/pith/KLWDZLIYKIG6PQV4GGPU63C2AD.json","view_paper":"https://pith.science/paper/KLWDZLIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.12166&json=true","fetch_graph":"https://pith.science/api/pith-number/KLWDZLIYKIG6PQV4GGPU63C2AD/graph.json","fetch_events":"https://pith.science/api/pith-number/KLWDZLIYKIG6PQV4GGPU63C2AD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLWDZLIYKIG6PQV4GGPU63C2AD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLWDZLIYKIG6PQV4GGPU63C2AD/action/storage_attestation","attest_author":"https://pith.science/pith/KLWDZLIYKIG6PQV4GGPU63C2AD/action/author_attestation","sign_citation":"https://pith.science/pith/KLWDZLIYKIG6PQV4GGPU63C2AD/action/citation_signature","submit_replication":"https://pith.science/pith/KLWDZLIYKIG6PQV4GGPU63C2AD/action/replication_record"}},"created_at":"2026-07-05T03:59:50.645269+00:00","updated_at":"2026-07-05T03:59:50.645269+00:00"}