{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ELRZAFKNEJAHGXLGVCE5VFMBZI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d29ca47d3f6899be06c684b7be7b8546ec412de603ddadd370a9bb2617ec876e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-05T17:07:53Z","title_canon_sha256":"5dbc9e592e87be75d16342427694e7798726460eb9c431dbea41aa4ceecea0d4"},"schema_version":"1.0","source":{"id":"2110.02178","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02178","created_at":"2026-05-20T20:40:06Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02178v2","created_at":"2026-05-20T20:40:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02178","created_at":"2026-05-20T20:40:06Z"},{"alias_kind":"pith_short_12","alias_value":"ELRZAFKNEJAH","created_at":"2026-05-20T20:40:06Z"},{"alias_kind":"pith_short_16","alias_value":"ELRZAFKNEJAHGXLG","created_at":"2026-05-20T20:40:06Z"},{"alias_kind":"pith_short_8","alias_value":"ELRZAFKN","created_at":"2026-05-20T20:40:06Z"}],"graph_snapshots":[{"event_id":"sha256:1f9ecc6318ca58267978d150a88249d7c1bdde0af38148d997dea1fb6b9b4ebb","target":"graph","created_at":"2026-05-20T20:40:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.02178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters across different vision tasks. However, these networks are spatially local. To learn global representations, self-attention-based vision trans-formers (ViTs) have been adopted. Unlike CNNs, ViTs are heavy-weight. In this paper, we ask the following question: is it possible to combine the strengths of CNNs and ViTs to build a light-weight and low latency network for mobile vision tasks? Towards this end, we introduce","authors_text":"Mohammad Rastegari, Sachin Mehta","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-05T17:07:53Z","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02178","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:49d206ca4afa3a673a0f409ceec3d819f1539f1249224a697cd9b5d66048f0e3","target":"record","created_at":"2026-05-20T20:40:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d29ca47d3f6899be06c684b7be7b8546ec412de603ddadd370a9bb2617ec876e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-05T17:07:53Z","title_canon_sha256":"5dbc9e592e87be75d16342427694e7798726460eb9c431dbea41aa4ceecea0d4"},"schema_version":"1.0","source":{"id":"2110.02178","kind":"arxiv","version":2}},"canonical_sha256":"22e390154d2240735d66a889da9581ca0deab5a146b70db15af1f7f11686887c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22e390154d2240735d66a889da9581ca0deab5a146b70db15af1f7f11686887c","first_computed_at":"2026-05-20T20:40:06.250278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T20:40:06.250278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZFtK37LkpGWlJMLKBdXFIKl97DaYp6Bl2a3aww8cdhmdLWWeYwCmrCnQqJuZmTNbzuzkHPEBICqRTobDaWUKBg==","signature_status":"signed_v1","signed_at":"2026-05-20T20:40:06.252260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02178","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49d206ca4afa3a673a0f409ceec3d819f1539f1249224a697cd9b5d66048f0e3","sha256:1f9ecc6318ca58267978d150a88249d7c1bdde0af38148d997dea1fb6b9b4ebb"],"state_sha256":"672bfbff8ed57982e9c16488554bfa5f4d4c3b07a0fdbded77c317a698fb510e"}