{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BJ4Z5WGNRQFS3KFHVO37IDFRA4","short_pith_number":"pith:BJ4Z5WGN","schema_version":"1.0","canonical_sha256":"0a799ed8cd8c0b2da8a7abb7f40cb10725d16bddc20a1a96c649668aef1ef6fa","source":{"kind":"arxiv","id":"2007.14902","version":3},"attestation_state":"computed","paper":{"title":"Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxi Duan, Jianlin Su, Rui Li, Shunyi Zheng","submitted_at":"2020-07-29T15:18:46Z","abstract_excerpt":"In this paper, to remedy this deficiency, we propose a Linear Attention Mechanism which is approximate to dot-product attention with much less memory and computational costs. The efficient design makes the incorporation between attention mechanisms and neural networks more flexible and versatile. Experiments conducted on semantic segmentation demonstrated the effectiveness of linear attention mechanism. Code is available at https://github.com/lironui/Linear-Attention-Mechanism."},"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":"2007.14902","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-29T15:18:46Z","cross_cats_sorted":[],"title_canon_sha256":"3788eee84168b7e7e81cd15b4ab79918f0936931c0cd8f453f6f0b7095fc4c48","abstract_canon_sha256":"6303957f7492a6fd9e331031dbf9a47340f7f96091d33c46e285fb6701b8876b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:31.496108Z","signature_b64":"yW7jKuXgFofxK3O6JeAZKmauPNefhlqYgiAlSzpYNOMi7W6GVLW8IVZb4GF3inqFhA5SqgyLFbd1Z/JEgjbgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a799ed8cd8c0b2da8a7abb7f40cb10725d16bddc20a1a96c649668aef1ef6fa","last_reissued_at":"2026-07-05T01:28:31.495714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:31.495714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxi Duan, Jianlin Su, Rui Li, Shunyi Zheng","submitted_at":"2020-07-29T15:18:46Z","abstract_excerpt":"In this paper, to remedy this deficiency, we propose a Linear Attention Mechanism which is approximate to dot-product attention with much less memory and computational costs. The efficient design makes the incorporation between attention mechanisms and neural networks more flexible and versatile. Experiments conducted on semantic segmentation demonstrated the effectiveness of linear attention mechanism. Code is available at https://github.com/lironui/Linear-Attention-Mechanism."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14902","kind":"arxiv","version":3},"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/2007.14902/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":"2007.14902","created_at":"2026-07-05T01:28:31.495771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.14902v3","created_at":"2026-07-05T01:28:31.495771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14902","created_at":"2026-07-05T01:28:31.495771+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJ4Z5WGNRQFS","created_at":"2026-07-05T01:28:31.495771+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJ4Z5WGNRQFS3KFH","created_at":"2026-07-05T01:28:31.495771+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJ4Z5WGN","created_at":"2026-07-05T01:28:31.495771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08297","citing_title":"SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJ4Z5WGNRQFS3KFHVO37IDFRA4","json":"https://pith.science/pith/BJ4Z5WGNRQFS3KFHVO37IDFRA4.json","graph_json":"https://pith.science/api/pith-number/BJ4Z5WGNRQFS3KFHVO37IDFRA4/graph.json","events_json":"https://pith.science/api/pith-number/BJ4Z5WGNRQFS3KFHVO37IDFRA4/events.json","paper":"https://pith.science/paper/BJ4Z5WGN"},"agent_actions":{"view_html":"https://pith.science/pith/BJ4Z5WGNRQFS3KFHVO37IDFRA4","download_json":"https://pith.science/pith/BJ4Z5WGNRQFS3KFHVO37IDFRA4.json","view_paper":"https://pith.science/paper/BJ4Z5WGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.14902&json=true","fetch_graph":"https://pith.science/api/pith-number/BJ4Z5WGNRQFS3KFHVO37IDFRA4/graph.json","fetch_events":"https://pith.science/api/pith-number/BJ4Z5WGNRQFS3KFHVO37IDFRA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJ4Z5WGNRQFS3KFHVO37IDFRA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJ4Z5WGNRQFS3KFHVO37IDFRA4/action/storage_attestation","attest_author":"https://pith.science/pith/BJ4Z5WGNRQFS3KFHVO37IDFRA4/action/author_attestation","sign_citation":"https://pith.science/pith/BJ4Z5WGNRQFS3KFHVO37IDFRA4/action/citation_signature","submit_replication":"https://pith.science/pith/BJ4Z5WGNRQFS3KFHVO37IDFRA4/action/replication_record"}},"created_at":"2026-07-05T01:28:31.495771+00:00","updated_at":"2026-07-05T01:28:31.495771+00:00"}