{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KAA6WJPCPG7LTMFU52JARVQCLM","short_pith_number":"pith:KAA6WJPC","schema_version":"1.0","canonical_sha256":"5001eb25e279beb9b0b4ee9208d6025b0a8f7dd90e8d06f47910b8391d8a9276","source":{"kind":"arxiv","id":"2501.15369","version":2},"attestation_state":"computed","paper":{"title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chuanyang Zheng","submitted_at":"2025-01-26T02:34:58Z","abstract_excerpt":"We present a new family of mobile hybrid vision networks, called iFormer, with a focus on optimizing latency and accuracy on mobile applications. iFormer effectively integrates the fast local representation capacity of convolution with the efficient global modeling ability of self-attention. The local interactions are derived from transforming a standard convolutional network, \\textit{i.e.}, ConvNeXt, to design a more lightweight mobile network. Our newly introduced mobile modulation attention removes memory-intensive operations in MHA and employs an efficient modulation mechanism to boost dyn"},"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":"2501.15369","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T02:34:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"296b5c87bea5ae768e26128e6417822466a942a6577501d0050b111b8847373c","abstract_canon_sha256":"156642e1422856d942ece58505a4e6c00d2f1efc9d1ee7f8e56e2603cf324e6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:25.018281Z","signature_b64":"CHPE0ZRCGsTgaT1C58JtsCfMxZunDTfKOcw+mwo3SvwEWCjINMY7FVK67V4Nz2FcbBm54nXU2IHFEg7zhNHWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5001eb25e279beb9b0b4ee9208d6025b0a8f7dd90e8d06f47910b8391d8a9276","last_reissued_at":"2026-07-05T10:15:25.017743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:25.017743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chuanyang Zheng","submitted_at":"2025-01-26T02:34:58Z","abstract_excerpt":"We present a new family of mobile hybrid vision networks, called iFormer, with a focus on optimizing latency and accuracy on mobile applications. iFormer effectively integrates the fast local representation capacity of convolution with the efficient global modeling ability of self-attention. The local interactions are derived from transforming a standard convolutional network, \\textit{i.e.}, ConvNeXt, to design a more lightweight mobile network. Our newly introduced mobile modulation attention removes memory-intensive operations in MHA and employs an efficient modulation mechanism to boost dyn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15369","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/2501.15369/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":"2501.15369","created_at":"2026-07-05T10:15:25.017810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15369v2","created_at":"2026-07-05T10:15:25.017810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15369","created_at":"2026-07-05T10:15:25.017810+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAA6WJPCPG7L","created_at":"2026-07-05T10:15:25.017810+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAA6WJPCPG7LTMFU","created_at":"2026-07-05T10:15:25.017810+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAA6WJPC","created_at":"2026-07-05T10:15:25.017810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09648","citing_title":"TRACE: Thermal Recognition Attentive-Framework for CO2 Emissions from Livestock","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAA6WJPCPG7LTMFU52JARVQCLM","json":"https://pith.science/pith/KAA6WJPCPG7LTMFU52JARVQCLM.json","graph_json":"https://pith.science/api/pith-number/KAA6WJPCPG7LTMFU52JARVQCLM/graph.json","events_json":"https://pith.science/api/pith-number/KAA6WJPCPG7LTMFU52JARVQCLM/events.json","paper":"https://pith.science/paper/KAA6WJPC"},"agent_actions":{"view_html":"https://pith.science/pith/KAA6WJPCPG7LTMFU52JARVQCLM","download_json":"https://pith.science/pith/KAA6WJPCPG7LTMFU52JARVQCLM.json","view_paper":"https://pith.science/paper/KAA6WJPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15369&json=true","fetch_graph":"https://pith.science/api/pith-number/KAA6WJPCPG7LTMFU52JARVQCLM/graph.json","fetch_events":"https://pith.science/api/pith-number/KAA6WJPCPG7LTMFU52JARVQCLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAA6WJPCPG7LTMFU52JARVQCLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAA6WJPCPG7LTMFU52JARVQCLM/action/storage_attestation","attest_author":"https://pith.science/pith/KAA6WJPCPG7LTMFU52JARVQCLM/action/author_attestation","sign_citation":"https://pith.science/pith/KAA6WJPCPG7LTMFU52JARVQCLM/action/citation_signature","submit_replication":"https://pith.science/pith/KAA6WJPCPG7LTMFU52JARVQCLM/action/replication_record"}},"created_at":"2026-07-05T10:15:25.017810+00:00","updated_at":"2026-07-05T10:15:25.017810+00:00"}