{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XWWC6R6I66HODMGDU7QE3A5IBH","short_pith_number":"pith:XWWC6R6I","schema_version":"1.0","canonical_sha256":"bdac2f47c8f78ee1b0c3a7e04d83a809c0d001bab3791035f92e33d003f5ef8b","source":{"kind":"arxiv","id":"2506.08297","version":1},"attestation_state":"computed","paper":{"title":"SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fanghui Xue, Jack Xin, Jiancheng Lyu, Nhat Thanh Tran, Shuai Zhang, Yingyong Qi, Yunling Zheng","submitted_at":"2025-06-10T00:03:19Z","abstract_excerpt":"Attention is the critical component of a transformer. Yet the quadratic computational complexity of vanilla full attention in the input size and the inability of its linear attention variant to focus have been challenges for computer vision tasks. We provide a mathematical definition of generalized attention and formulate both vanilla softmax attention and linear attention within the general framework. We prove that generalized attention disperses, that is, as the number of keys tends to infinity, the query assigns equal weights to all keys. Motivated by the dispersion property and recent deve"},"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":"2506.08297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T00:03:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6cafcd668cd1f093ccd73205c67df9ea6106056ff3fa793126855a50b890e28d","abstract_canon_sha256":"dbee07e9ee71e21919302d8f61f2acf2731aaeb979b7de37cb63feeea9b54469"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:47.718475Z","signature_b64":"fYhVpZngcc2AWUtb70lWiJPNccu1eWAUYfVkBySk7EuG2Y67Ev0Bd0jW37tiKzk2BPJxGfB+BmbjZzEzw9m1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdac2f47c8f78ee1b0c3a7e04d83a809c0d001bab3791035f92e33d003f5ef8b","last_reissued_at":"2026-07-05T11:18:47.717989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:47.717989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fanghui Xue, Jack Xin, Jiancheng Lyu, Nhat Thanh Tran, Shuai Zhang, Yingyong Qi, Yunling Zheng","submitted_at":"2025-06-10T00:03:19Z","abstract_excerpt":"Attention is the critical component of a transformer. Yet the quadratic computational complexity of vanilla full attention in the input size and the inability of its linear attention variant to focus have been challenges for computer vision tasks. We provide a mathematical definition of generalized attention and formulate both vanilla softmax attention and linear attention within the general framework. We prove that generalized attention disperses, that is, as the number of keys tends to infinity, the query assigns equal weights to all keys. Motivated by the dispersion property and recent deve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08297","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/2506.08297/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":"2506.08297","created_at":"2026-07-05T11:18:47.718047+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08297v1","created_at":"2026-07-05T11:18:47.718047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08297","created_at":"2026-07-05T11:18:47.718047+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWWC6R6I66HO","created_at":"2026-07-05T11:18:47.718047+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWWC6R6I66HODMGD","created_at":"2026-07-05T11:18:47.718047+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWWC6R6I","created_at":"2026-07-05T11:18:47.718047+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.11131","citing_title":"USEMA: a Scalable Efficient Mamba Like Attention for Medical Image Segmentation","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XWWC6R6I66HODMGDU7QE3A5IBH","json":"https://pith.science/pith/XWWC6R6I66HODMGDU7QE3A5IBH.json","graph_json":"https://pith.science/api/pith-number/XWWC6R6I66HODMGDU7QE3A5IBH/graph.json","events_json":"https://pith.science/api/pith-number/XWWC6R6I66HODMGDU7QE3A5IBH/events.json","paper":"https://pith.science/paper/XWWC6R6I"},"agent_actions":{"view_html":"https://pith.science/pith/XWWC6R6I66HODMGDU7QE3A5IBH","download_json":"https://pith.science/pith/XWWC6R6I66HODMGDU7QE3A5IBH.json","view_paper":"https://pith.science/paper/XWWC6R6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08297&json=true","fetch_graph":"https://pith.science/api/pith-number/XWWC6R6I66HODMGDU7QE3A5IBH/graph.json","fetch_events":"https://pith.science/api/pith-number/XWWC6R6I66HODMGDU7QE3A5IBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWWC6R6I66HODMGDU7QE3A5IBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWWC6R6I66HODMGDU7QE3A5IBH/action/storage_attestation","attest_author":"https://pith.science/pith/XWWC6R6I66HODMGDU7QE3A5IBH/action/author_attestation","sign_citation":"https://pith.science/pith/XWWC6R6I66HODMGDU7QE3A5IBH/action/citation_signature","submit_replication":"https://pith.science/pith/XWWC6R6I66HODMGDU7QE3A5IBH/action/replication_record"}},"created_at":"2026-07-05T11:18:47.718047+00:00","updated_at":"2026-07-05T11:18:47.718047+00:00"}