{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LLNI43T2Z4PCJC5GLT4V3BOQ5S","short_pith_number":"pith:LLNI43T2","schema_version":"1.0","canonical_sha256":"5ada8e6e7acf1e248ba65cf95d85d0ecaa944ba815d6753855d2bc54976133f8","source":{"kind":"arxiv","id":"2211.03295","version":4},"attestation_state":"computed","paper":{"title":"MogaNet: Multi-order Gated Aggregation Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng Tan, Di Wu, Haitao Lin, Jiangbin Zheng, Siyuan Li, Stan Z. Li, Zedong Wang, Zhiyuan Chen, Zicheng Liu","submitted_at":"2022-11-07T04:31:17Z","abstract_excerpt":"By contextualizing the kernel as global as possible, Modern ConvNets have shown great potential in computer vision tasks. However, recent progress on multi-order game-theoretic interaction within deep neural networks (DNNs) reveals the representation bottleneck of modern ConvNets, where the expressive interactions have not been effectively encoded with the increased kernel size. To tackle this challenge, we propose a new family of modern ConvNets, dubbed MogaNet, for discriminative visual representation learning in pure ConvNet-based models with favorable complexity-performance trade-offs. Mog"},"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":"2211.03295","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-07T04:31:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f62d5bf55be8764738ba98aa75327581ad62a5bafad7573413cdcb83c978b25b","abstract_canon_sha256":"7bfc60c39d68e4098813e96e560831bf9ce0bb839cadf5a021097bcf4e6da62e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:14.859486Z","signature_b64":"px6DrHZyrq4Oa730HTpfJH/VOso2+Lh9iiQ5OVUVP7sBLJlwa6X4ocWACGTkBsAR16hsNMBAqHhoDFqFXQDnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ada8e6e7acf1e248ba65cf95d85d0ecaa944ba815d6753855d2bc54976133f8","last_reissued_at":"2026-07-05T11:22:14.858986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:14.858986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MogaNet: Multi-order Gated Aggregation Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng Tan, Di Wu, Haitao Lin, Jiangbin Zheng, Siyuan Li, Stan Z. Li, Zedong Wang, Zhiyuan Chen, Zicheng Liu","submitted_at":"2022-11-07T04:31:17Z","abstract_excerpt":"By contextualizing the kernel as global as possible, Modern ConvNets have shown great potential in computer vision tasks. However, recent progress on multi-order game-theoretic interaction within deep neural networks (DNNs) reveals the representation bottleneck of modern ConvNets, where the expressive interactions have not been effectively encoded with the increased kernel size. To tackle this challenge, we propose a new family of modern ConvNets, dubbed MogaNet, for discriminative visual representation learning in pure ConvNet-based models with favorable complexity-performance trade-offs. Mog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03295","kind":"arxiv","version":4},"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/2211.03295/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":"2211.03295","created_at":"2026-07-05T11:22:14.859043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.03295v4","created_at":"2026-07-05T11:22:14.859043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03295","created_at":"2026-07-05T11:22:14.859043+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLNI43T2Z4PC","created_at":"2026-07-05T11:22:14.859043+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLNI43T2Z4PCJC5G","created_at":"2026-07-05T11:22:14.859043+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLNI43T2","created_at":"2026-07-05T11:22:14.859043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.02727","citing_title":"Gated Differential Linear Attention: A Linear-Time Decoder for High-Fidelity Medical Segmentation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01667","citing_title":"Deep neural networks with Fisher vector encoding for medical image classification","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLNI43T2Z4PCJC5GLT4V3BOQ5S","json":"https://pith.science/pith/LLNI43T2Z4PCJC5GLT4V3BOQ5S.json","graph_json":"https://pith.science/api/pith-number/LLNI43T2Z4PCJC5GLT4V3BOQ5S/graph.json","events_json":"https://pith.science/api/pith-number/LLNI43T2Z4PCJC5GLT4V3BOQ5S/events.json","paper":"https://pith.science/paper/LLNI43T2"},"agent_actions":{"view_html":"https://pith.science/pith/LLNI43T2Z4PCJC5GLT4V3BOQ5S","download_json":"https://pith.science/pith/LLNI43T2Z4PCJC5GLT4V3BOQ5S.json","view_paper":"https://pith.science/paper/LLNI43T2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.03295&json=true","fetch_graph":"https://pith.science/api/pith-number/LLNI43T2Z4PCJC5GLT4V3BOQ5S/graph.json","fetch_events":"https://pith.science/api/pith-number/LLNI43T2Z4PCJC5GLT4V3BOQ5S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLNI43T2Z4PCJC5GLT4V3BOQ5S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLNI43T2Z4PCJC5GLT4V3BOQ5S/action/storage_attestation","attest_author":"https://pith.science/pith/LLNI43T2Z4PCJC5GLT4V3BOQ5S/action/author_attestation","sign_citation":"https://pith.science/pith/LLNI43T2Z4PCJC5GLT4V3BOQ5S/action/citation_signature","submit_replication":"https://pith.science/pith/LLNI43T2Z4PCJC5GLT4V3BOQ5S/action/replication_record"}},"created_at":"2026-07-05T11:22:14.859043+00:00","updated_at":"2026-07-05T11:22:14.859043+00:00"}