{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LXQHPQVTONXUJRYOFOOTHD3X2W","short_pith_number":"pith:LXQHPQVT","schema_version":"1.0","canonical_sha256":"5de077c2b3736f44c70e2b9d338f77d5a005e6879b02c68339cf77399b607a8a","source":{"kind":"arxiv","id":"2301.01146","version":4},"attestation_state":"computed","paper":{"title":"Rethinking Mobile Block for Efficient Attention-based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boshen Zhang, Chengjie Wang, Jiangning Zhang, Jian Li, Liang Liu, Tianxin Huang, Xiangtai Li, Yabiao Wang, Zhengkai Jiang, Zhucun Xue","submitted_at":"2023-01-03T15:11:41Z","abstract_excerpt":"This paper focuses on developing modern, efficient, lightweight models for dense predictions while trading off parameters, FLOPs, and performance. Inverted Residual Block (IRB) serves as the infrastructure for lightweight CNNs, but no counterpart has been recognized by attention-based studies. This work rethinks lightweight infrastructure from efficient IRB and effective components of Transformer from a unified perspective, extending CNN-based IRB to attention-based models and abstracting a one-residual Meta Mobile Block (MMB) for lightweight model design. Following simple but effective design"},"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":"2301.01146","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-03T15:11:41Z","cross_cats_sorted":[],"title_canon_sha256":"e3785686bc6380e3a1cfc3d5d351a04915afbdae13926b0faf9a8941a5ab7565","abstract_canon_sha256":"643e35c2ef3ff830677cae79a82c266f4b081e5d1aa7fac7261edcc8c6f3f740"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:50.813193Z","signature_b64":"bOpwTh+tNSf7G8iPaqiFIeFN6PHrKQkK4RUESyS4vD2t23nSCUzbu+LhrFJVKBOcavoqxPydrrdoVWZNyDjwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5de077c2b3736f44c70e2b9d338f77d5a005e6879b02c68339cf77399b607a8a","last_reissued_at":"2026-07-05T06:40:50.812701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:50.812701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Mobile Block for Efficient Attention-based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boshen Zhang, Chengjie Wang, Jiangning Zhang, Jian Li, Liang Liu, Tianxin Huang, Xiangtai Li, Yabiao Wang, Zhengkai Jiang, Zhucun Xue","submitted_at":"2023-01-03T15:11:41Z","abstract_excerpt":"This paper focuses on developing modern, efficient, lightweight models for dense predictions while trading off parameters, FLOPs, and performance. Inverted Residual Block (IRB) serves as the infrastructure for lightweight CNNs, but no counterpart has been recognized by attention-based studies. This work rethinks lightweight infrastructure from efficient IRB and effective components of Transformer from a unified perspective, extending CNN-based IRB to attention-based models and abstracting a one-residual Meta Mobile Block (MMB) for lightweight model design. Following simple but effective design"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01146","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/2301.01146/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":"2301.01146","created_at":"2026-07-05T06:40:50.812764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.01146v4","created_at":"2026-07-05T06:40:50.812764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01146","created_at":"2026-07-05T06:40:50.812764+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXQHPQVTONXU","created_at":"2026-07-05T06:40:50.812764+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXQHPQVTONXUJRYO","created_at":"2026-07-05T06:40:50.812764+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXQHPQVT","created_at":"2026-07-05T06:40:50.812764+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/LXQHPQVTONXUJRYOFOOTHD3X2W","json":"https://pith.science/pith/LXQHPQVTONXUJRYOFOOTHD3X2W.json","graph_json":"https://pith.science/api/pith-number/LXQHPQVTONXUJRYOFOOTHD3X2W/graph.json","events_json":"https://pith.science/api/pith-number/LXQHPQVTONXUJRYOFOOTHD3X2W/events.json","paper":"https://pith.science/paper/LXQHPQVT"},"agent_actions":{"view_html":"https://pith.science/pith/LXQHPQVTONXUJRYOFOOTHD3X2W","download_json":"https://pith.science/pith/LXQHPQVTONXUJRYOFOOTHD3X2W.json","view_paper":"https://pith.science/paper/LXQHPQVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.01146&json=true","fetch_graph":"https://pith.science/api/pith-number/LXQHPQVTONXUJRYOFOOTHD3X2W/graph.json","fetch_events":"https://pith.science/api/pith-number/LXQHPQVTONXUJRYOFOOTHD3X2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXQHPQVTONXUJRYOFOOTHD3X2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXQHPQVTONXUJRYOFOOTHD3X2W/action/storage_attestation","attest_author":"https://pith.science/pith/LXQHPQVTONXUJRYOFOOTHD3X2W/action/author_attestation","sign_citation":"https://pith.science/pith/LXQHPQVTONXUJRYOFOOTHD3X2W/action/citation_signature","submit_replication":"https://pith.science/pith/LXQHPQVTONXUJRYOFOOTHD3X2W/action/replication_record"}},"created_at":"2026-07-05T06:40:50.812764+00:00","updated_at":"2026-07-05T06:40:50.812764+00:00"}