{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SRM34SDSOCISB4RTRT54C52GXS","short_pith_number":"pith:SRM34SDS","schema_version":"1.0","canonical_sha256":"9459be4872709120f2338cfbc17746bc8df9ec3284239bbc40282f5869860eca","source":{"kind":"arxiv","id":"1904.05873","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Study of Spatial Attention Mechanisms in Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dazhi Cheng, Jifeng Dai, Stephen Lin, Xizhou Zhu, Zheng Zhang","submitted_at":"2019-04-11T17:58:37Z","abstract_excerpt":"Attention mechanisms have become a popular component in deep neural networks, yet there has been little examination of how different influencing factors and methods for computing attention from these factors affect performance. Toward a better general understanding of attention mechanisms, we present an empirical study that ablates various spatial attention elements within a generalized attention formulation, encompassing the dominant Transformer attention as well as the prevalent deformable convolution and dynamic convolution modules. Conducted on a variety of applications, the study yields s"},"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":"1904.05873","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-11T17:58:37Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"333f7cc4b73ff5966b82aef2540ac04915c7c8e0e76cd7edc8cd7533fdca4eae","abstract_canon_sha256":"a7282524a3eeb2f6fd27e3940aa751aa92a641fa3f852e31a08bb4b7a1f39e62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:44.825607Z","signature_b64":"z/yIYYP4U9FQ6ycbDS4KSybuGeCBAADwryCDdSEtDKLRM7WJZ0PEZQgOjD8wiLD7aRXeJ4i+eei+xZ4yYf6UDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9459be4872709120f2338cfbc17746bc8df9ec3284239bbc40282f5869860eca","last_reissued_at":"2026-05-17T23:48:44.824980Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:44.824980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study of Spatial Attention Mechanisms in Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dazhi Cheng, Jifeng Dai, Stephen Lin, Xizhou Zhu, Zheng Zhang","submitted_at":"2019-04-11T17:58:37Z","abstract_excerpt":"Attention mechanisms have become a popular component in deep neural networks, yet there has been little examination of how different influencing factors and methods for computing attention from these factors affect performance. Toward a better general understanding of attention mechanisms, we present an empirical study that ablates various spatial attention elements within a generalized attention formulation, encompassing the dominant Transformer attention as well as the prevalent deformable convolution and dynamic convolution modules. Conducted on a variety of applications, the study yields s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.05873","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":""},"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":"1904.05873","created_at":"2026-05-17T23:48:44.825069+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.05873v1","created_at":"2026-05-17T23:48:44.825069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.05873","created_at":"2026-05-17T23:48:44.825069+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRM34SDSOCIS","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRM34SDSOCISB4RT","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRM34SDS","created_at":"2026-05-18T12:33:27.125529+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/SRM34SDSOCISB4RTRT54C52GXS","json":"https://pith.science/pith/SRM34SDSOCISB4RTRT54C52GXS.json","graph_json":"https://pith.science/api/pith-number/SRM34SDSOCISB4RTRT54C52GXS/graph.json","events_json":"https://pith.science/api/pith-number/SRM34SDSOCISB4RTRT54C52GXS/events.json","paper":"https://pith.science/paper/SRM34SDS"},"agent_actions":{"view_html":"https://pith.science/pith/SRM34SDSOCISB4RTRT54C52GXS","download_json":"https://pith.science/pith/SRM34SDSOCISB4RTRT54C52GXS.json","view_paper":"https://pith.science/paper/SRM34SDS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.05873&json=true","fetch_graph":"https://pith.science/api/pith-number/SRM34SDSOCISB4RTRT54C52GXS/graph.json","fetch_events":"https://pith.science/api/pith-number/SRM34SDSOCISB4RTRT54C52GXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRM34SDSOCISB4RTRT54C52GXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRM34SDSOCISB4RTRT54C52GXS/action/storage_attestation","attest_author":"https://pith.science/pith/SRM34SDSOCISB4RTRT54C52GXS/action/author_attestation","sign_citation":"https://pith.science/pith/SRM34SDSOCISB4RTRT54C52GXS/action/citation_signature","submit_replication":"https://pith.science/pith/SRM34SDSOCISB4RTRT54C52GXS/action/replication_record"}},"created_at":"2026-05-17T23:48:44.825069+00:00","updated_at":"2026-05-17T23:48:44.825069+00:00"}