{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CSSWLRCSIY2DIYL3QSPRFS6EKP","short_pith_number":"pith:CSSWLRCS","schema_version":"1.0","canonical_sha256":"14a565c452463434617b849f12cbc453f0a0cc2f2feab09fb28dead183e2b59a","source":{"kind":"arxiv","id":"1805.00912","version":4},"attestation_state":"computed","paper":{"title":"Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Tao Shen, Tianyi Zhou","submitted_at":"2018-05-02T17:16:48Z","abstract_excerpt":"Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies. Further, their expressive power and performance can be boosted by using a vector to measure pairwise dependency, but this requires to expand the alignment matrix to a tensor, which results in memory and computation bottlenecks. In this paper, we propose a novel attention mechanism called \"Multi-mask Tensorized Self-Attention\" (MTSA), which is as fast and as memory-efficient as a CNN, but significantly outperforms previous CNN-/"},"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":"1805.00912","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-02T17:16:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e3bea6193be9132766075147e742845e9802104f734acfd3bd51e93fac06593","abstract_canon_sha256":"6aba1bb09521265d00af3debd5720328fb3b84e0a6c1ab135c9544c17515a948"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:28.063864Z","signature_b64":"WBhCYXXTUz3shE9ms9+vUsEQQA4bd2TAIANvuUoHT11TjgwOI7/ZZ09jLvCoecGp+5PP7rt6pi76CFKFXV2pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14a565c452463434617b849f12cbc453f0a0cc2f2feab09fb28dead183e2b59a","last_reissued_at":"2026-05-17T23:50:28.063340Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:28.063340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Tao Shen, Tianyi Zhou","submitted_at":"2018-05-02T17:16:48Z","abstract_excerpt":"Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies. Further, their expressive power and performance can be boosted by using a vector to measure pairwise dependency, but this requires to expand the alignment matrix to a tensor, which results in memory and computation bottlenecks. In this paper, we propose a novel attention mechanism called \"Multi-mask Tensorized Self-Attention\" (MTSA), which is as fast and as memory-efficient as a CNN, but significantly outperforms previous CNN-/"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00912","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1805.00912","created_at":"2026-05-17T23:50:28.063411+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.00912v4","created_at":"2026-05-17T23:50:28.063411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00912","created_at":"2026-05-17T23:50:28.063411+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSSWLRCSIY2D","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSSWLRCSIY2DIYL3","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSSWLRCS","created_at":"2026-05-18T12:32:19.392346+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/CSSWLRCSIY2DIYL3QSPRFS6EKP","json":"https://pith.science/pith/CSSWLRCSIY2DIYL3QSPRFS6EKP.json","graph_json":"https://pith.science/api/pith-number/CSSWLRCSIY2DIYL3QSPRFS6EKP/graph.json","events_json":"https://pith.science/api/pith-number/CSSWLRCSIY2DIYL3QSPRFS6EKP/events.json","paper":"https://pith.science/paper/CSSWLRCS"},"agent_actions":{"view_html":"https://pith.science/pith/CSSWLRCSIY2DIYL3QSPRFS6EKP","download_json":"https://pith.science/pith/CSSWLRCSIY2DIYL3QSPRFS6EKP.json","view_paper":"https://pith.science/paper/CSSWLRCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.00912&json=true","fetch_graph":"https://pith.science/api/pith-number/CSSWLRCSIY2DIYL3QSPRFS6EKP/graph.json","fetch_events":"https://pith.science/api/pith-number/CSSWLRCSIY2DIYL3QSPRFS6EKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSSWLRCSIY2DIYL3QSPRFS6EKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSSWLRCSIY2DIYL3QSPRFS6EKP/action/storage_attestation","attest_author":"https://pith.science/pith/CSSWLRCSIY2DIYL3QSPRFS6EKP/action/author_attestation","sign_citation":"https://pith.science/pith/CSSWLRCSIY2DIYL3QSPRFS6EKP/action/citation_signature","submit_replication":"https://pith.science/pith/CSSWLRCSIY2DIYL3QSPRFS6EKP/action/replication_record"}},"created_at":"2026-05-17T23:50:28.063411+00:00","updated_at":"2026-05-17T23:50:28.063411+00:00"}