{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KPN5DMMKPND6NQTO6LNUZAD4VF","short_pith_number":"pith:KPN5DMMK","schema_version":"1.0","canonical_sha256":"53dbd1b18a7b47e6c26ef2db4c807ca971f20a8ee0226e65492af5ab89e6ed43","source":{"kind":"arxiv","id":"2310.17683","version":1},"attestation_state":"computed","paper":{"title":"Sliceformer: Make Multi-head Attention as Simple as Sorting in Discriminative Tasks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongteng Xu, Shen Yuan","submitted_at":"2023-10-26T14:43:07Z","abstract_excerpt":"As one of the most popular neural network modules, Transformer plays a central role in many fundamental deep learning models, e.g., the ViT in computer vision and the BERT and GPT in natural language processing. The effectiveness of the Transformer is often attributed to its multi-head attention (MHA) mechanism. In this study, we discuss the limitations of MHA, including the high computational complexity due to its ``query-key-value'' architecture and the numerical issue caused by its softmax operation. Considering the above problems and the recent development tendency of the attention layer, "},"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":"2310.17683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T14:43:07Z","cross_cats_sorted":[],"title_canon_sha256":"de77a7a0323bd4ba1d112e7172df4efceb3321ff16fe3de2354793d8f6c149af","abstract_canon_sha256":"f49e134c6dfe95890b22b637c95f9eb4adb8b4e2a7a534f33bb120e52a71595c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:50.779143Z","signature_b64":"V+hHahm2hvFzNZNO1JIGnixv6vQvbqS4RCrMbI/8szgVusB/US3qgN5Tzv+DR5ZcRojEBt/iEkDk0OUXvZaBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53dbd1b18a7b47e6c26ef2db4c807ca971f20a8ee0226e65492af5ab89e6ed43","last_reissued_at":"2026-07-05T07:05:50.778683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:50.778683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sliceformer: Make Multi-head Attention as Simple as Sorting in Discriminative Tasks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongteng Xu, Shen Yuan","submitted_at":"2023-10-26T14:43:07Z","abstract_excerpt":"As one of the most popular neural network modules, Transformer plays a central role in many fundamental deep learning models, e.g., the ViT in computer vision and the BERT and GPT in natural language processing. The effectiveness of the Transformer is often attributed to its multi-head attention (MHA) mechanism. In this study, we discuss the limitations of MHA, including the high computational complexity due to its ``query-key-value'' architecture and the numerical issue caused by its softmax operation. Considering the above problems and the recent development tendency of the attention layer, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17683","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/2310.17683/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":"2310.17683","created_at":"2026-07-05T07:05:50.778743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17683v1","created_at":"2026-07-05T07:05:50.778743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17683","created_at":"2026-07-05T07:05:50.778743+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPN5DMMKPND6","created_at":"2026-07-05T07:05:50.778743+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPN5DMMKPND6NQTO","created_at":"2026-07-05T07:05:50.778743+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPN5DMMK","created_at":"2026-07-05T07:05:50.778743+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/KPN5DMMKPND6NQTO6LNUZAD4VF","json":"https://pith.science/pith/KPN5DMMKPND6NQTO6LNUZAD4VF.json","graph_json":"https://pith.science/api/pith-number/KPN5DMMKPND6NQTO6LNUZAD4VF/graph.json","events_json":"https://pith.science/api/pith-number/KPN5DMMKPND6NQTO6LNUZAD4VF/events.json","paper":"https://pith.science/paper/KPN5DMMK"},"agent_actions":{"view_html":"https://pith.science/pith/KPN5DMMKPND6NQTO6LNUZAD4VF","download_json":"https://pith.science/pith/KPN5DMMKPND6NQTO6LNUZAD4VF.json","view_paper":"https://pith.science/paper/KPN5DMMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17683&json=true","fetch_graph":"https://pith.science/api/pith-number/KPN5DMMKPND6NQTO6LNUZAD4VF/graph.json","fetch_events":"https://pith.science/api/pith-number/KPN5DMMKPND6NQTO6LNUZAD4VF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPN5DMMKPND6NQTO6LNUZAD4VF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPN5DMMKPND6NQTO6LNUZAD4VF/action/storage_attestation","attest_author":"https://pith.science/pith/KPN5DMMKPND6NQTO6LNUZAD4VF/action/author_attestation","sign_citation":"https://pith.science/pith/KPN5DMMKPND6NQTO6LNUZAD4VF/action/citation_signature","submit_replication":"https://pith.science/pith/KPN5DMMKPND6NQTO6LNUZAD4VF/action/replication_record"}},"created_at":"2026-07-05T07:05:50.778743+00:00","updated_at":"2026-07-05T07:05:50.778743+00:00"}