{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FJUUVTYTJQ4BBMO7FJALOTR73X","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":"a4691ad411add1a554db61abf2a881386c8ae1db35d59d2435326b053ee190d5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T01:04:10Z","title_canon_sha256":"9133832bd7f2fccd94c626f6fe0ea007fd663cb8c5b68dc59fa61dc93e30b299"},"schema_version":"1.0","source":{"id":"2209.15159","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15159","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15159v2","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15159","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"FJUUVTYTJQ4B","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"pith_short_16","alias_value":"FJUUVTYTJQ4BBMO7","created_at":"2026-07-05T05:04:04Z"},{"alias_kind":"pith_short_8","alias_value":"FJUUVTYT","created_at":"2026-07-05T05:04:04Z"}],"graph_snapshots":[{"event_id":"sha256:877bc2df8faf199a3805dbd296fe6f4afdbbb5b7998b0acb2777974a556a9afc","target":"graph","created_at":"2026-07-05T05:04:04Z","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/2209.15159/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"MobileViT (MobileViTv1) combines convolutional neural networks (CNNs) and vision transformers (ViTs) to create light-weight models for mobile vision tasks. Though the main MobileViTv1-block helps to achieve competitive state-of-the-art results, the fusion block inside MobileViTv1-block, creates scaling challenges and has a complex learning task. We propose changes to the fusion block that are simple and effective to create MobileViTv3-block, which addresses the scaling and simplifies the learning task. Our proposed MobileViTv3-block used to create MobileViTv3-XXS, XS and S models outperform Mo","authors_text":"Abhishek Chaurasia, Shakti N. Wadekar","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T01:04:10Z","title":"MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15159","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:ab65b90fc7cf73e996b97888a5d8b963d0e426dd68459a2df3ca8e53fbc8fb1f","target":"record","created_at":"2026-07-05T05:04:04Z","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":"a4691ad411add1a554db61abf2a881386c8ae1db35d59d2435326b053ee190d5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T01:04:10Z","title_canon_sha256":"9133832bd7f2fccd94c626f6fe0ea007fd663cb8c5b68dc59fa61dc93e30b299"},"schema_version":"1.0","source":{"id":"2209.15159","kind":"arxiv","version":2}},"canonical_sha256":"2a694acf134c3810b1df2a40b74e3fdde6374382e441253b9e731fd920a5af5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a694acf134c3810b1df2a40b74e3fdde6374382e441253b9e731fd920a5af5f","first_computed_at":"2026-07-05T05:04:04.099391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:04.099391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iTwxvt5oOyI79tK+8/xgYSgmdkNTBTK56qBz9U09eJ16LfyAAkMpNTmwZ6nGpbk20+YVyO8E+o/l9MhVmkweBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:04.099814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15159","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab65b90fc7cf73e996b97888a5d8b963d0e426dd68459a2df3ca8e53fbc8fb1f","sha256:877bc2df8faf199a3805dbd296fe6f4afdbbb5b7998b0acb2777974a556a9afc"],"state_sha256":"867d3e7efded4525545fba3ae61d44bdb0fa6988c08724bf1086798652ffbd2b"}