{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AFVQSLSPXFNWOS5SUVHU4V2H76","short_pith_number":"pith:AFVQSLSP","schema_version":"1.0","canonical_sha256":"016b092e4fb95b674bb2a54f4e5747ff8be62537ad09eb3173a1b88921121d9c","source":{"kind":"arxiv","id":"2106.02253","version":2},"attestation_state":"computed","paper":{"title":"X-volution: On the unification of convolution and self-attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Ni, Hang Wang, Xuanhong Chen","submitted_at":"2021-06-04T04:32:02Z","abstract_excerpt":"Convolution and self-attention are acting as two fundamental building blocks in deep neural networks, where the former extracts local image features in a linear way while the latter non-locally encodes high-order contextual relationships. Though essentially complementary to each other, i.e., first-/high-order, stat-of-the-art architectures, i.e., CNNs or transformers lack a principled way to simultaneously apply both operations in a single computational module, due to their heterogeneous computing pattern and excessive burden of global dot-product for visual tasks. In this work, we theoretical"},"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":"2106.02253","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-04T04:32:02Z","cross_cats_sorted":[],"title_canon_sha256":"1f82dce6b89261db53ed80bc10295aae7a35f81c695f2d54ca162d397423b6ed","abstract_canon_sha256":"2eec53def411330b9f939341a9469714962f80d8c5fe61679b429b1ef24d85a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:46.753497Z","signature_b64":"exHT4OGvh3NCYXu6y3n6A8oxjsqV7KdRhZdUpnHOekZU4NyDUVmbldPA7hZ1q+QVW6K5uxMGawfv4WCLqkTxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"016b092e4fb95b674bb2a54f4e5747ff8be62537ad09eb3173a1b88921121d9c","last_reissued_at":"2026-07-05T02:46:46.753074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:46.753074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-volution: On the unification of convolution and self-attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Ni, Hang Wang, Xuanhong Chen","submitted_at":"2021-06-04T04:32:02Z","abstract_excerpt":"Convolution and self-attention are acting as two fundamental building blocks in deep neural networks, where the former extracts local image features in a linear way while the latter non-locally encodes high-order contextual relationships. Though essentially complementary to each other, i.e., first-/high-order, stat-of-the-art architectures, i.e., CNNs or transformers lack a principled way to simultaneously apply both operations in a single computational module, due to their heterogeneous computing pattern and excessive burden of global dot-product for visual tasks. In this work, we theoretical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02253","kind":"arxiv","version":2},"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/2106.02253/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":"2106.02253","created_at":"2026-07-05T02:46:46.753135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.02253v2","created_at":"2026-07-05T02:46:46.753135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02253","created_at":"2026-07-05T02:46:46.753135+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFVQSLSPXFNW","created_at":"2026-07-05T02:46:46.753135+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFVQSLSPXFNWOS5S","created_at":"2026-07-05T02:46:46.753135+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFVQSLSP","created_at":"2026-07-05T02:46:46.753135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11216","citing_title":"GeoMM: On Geodesic Perspective for Multi-modal Learning","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AFVQSLSPXFNWOS5SUVHU4V2H76","json":"https://pith.science/pith/AFVQSLSPXFNWOS5SUVHU4V2H76.json","graph_json":"https://pith.science/api/pith-number/AFVQSLSPXFNWOS5SUVHU4V2H76/graph.json","events_json":"https://pith.science/api/pith-number/AFVQSLSPXFNWOS5SUVHU4V2H76/events.json","paper":"https://pith.science/paper/AFVQSLSP"},"agent_actions":{"view_html":"https://pith.science/pith/AFVQSLSPXFNWOS5SUVHU4V2H76","download_json":"https://pith.science/pith/AFVQSLSPXFNWOS5SUVHU4V2H76.json","view_paper":"https://pith.science/paper/AFVQSLSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.02253&json=true","fetch_graph":"https://pith.science/api/pith-number/AFVQSLSPXFNWOS5SUVHU4V2H76/graph.json","fetch_events":"https://pith.science/api/pith-number/AFVQSLSPXFNWOS5SUVHU4V2H76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFVQSLSPXFNWOS5SUVHU4V2H76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFVQSLSPXFNWOS5SUVHU4V2H76/action/storage_attestation","attest_author":"https://pith.science/pith/AFVQSLSPXFNWOS5SUVHU4V2H76/action/author_attestation","sign_citation":"https://pith.science/pith/AFVQSLSPXFNWOS5SUVHU4V2H76/action/citation_signature","submit_replication":"https://pith.science/pith/AFVQSLSPXFNWOS5SUVHU4V2H76/action/replication_record"}},"created_at":"2026-07-05T02:46:46.753135+00:00","updated_at":"2026-07-05T02:46:46.753135+00:00"}