{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5HJQJBTSCX2KUZ54EUCFJARFM4","short_pith_number":"pith:5HJQJBTS","schema_version":"1.0","canonical_sha256":"e9d304867215f4aa67bc250454822567085f73bf969145d6c667ebe1b268c53b","source":{"kind":"arxiv","id":"2306.06189","version":2},"attestation_state":"computed","paper":{"title":"FasterViT: Fast Vision Transformers with Hierarchical Attention","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Hatamizadeh, Andrew Tao, Greg Heinrich, Hongxu Yin, Jan Kautz, Jose M. Alvarez, Pavlo Molchanov","submitted_at":"2023-06-09T18:41:37Z","abstract_excerpt":"We design a new family of hybrid CNN-ViT neural networks, named FasterViT, with a focus on high image throughput for computer vision (CV) applications. FasterViT combines the benefits of fast local representation learning in CNNs and global modeling properties in ViT. Our newly introduced Hierarchical Attention (HAT) approach decomposes global self-attention with quadratic complexity into a multi-level attention with reduced computational costs. We benefit from efficient window-based self-attention. Each window has access to dedicated carrier tokens that participate in local and global represe"},"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":"2306.06189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-09T18:41:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c2aa42533863a7801ddac988f333efbceba0edd499e17c07d96c6eae9c230869","abstract_canon_sha256":"6b78d8af8f40b656bbb15abd5939ae1886e46b97ca3fbf52108d7aca05ab16b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:06.321981Z","signature_b64":"gGjGws+yTmWbOpHZHA9icDmsX3jJxysx4OZ8Tl6SdaPHxC2ZeN+A7CNtqVTmkKj+Q/QiwaFJBA8zDo+CNdwqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9d304867215f4aa67bc250454822567085f73bf969145d6c667ebe1b268c53b","last_reissued_at":"2026-07-05T08:03:06.321493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:06.321493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FasterViT: Fast Vision Transformers with Hierarchical Attention","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Hatamizadeh, Andrew Tao, Greg Heinrich, Hongxu Yin, Jan Kautz, Jose M. Alvarez, Pavlo Molchanov","submitted_at":"2023-06-09T18:41:37Z","abstract_excerpt":"We design a new family of hybrid CNN-ViT neural networks, named FasterViT, with a focus on high image throughput for computer vision (CV) applications. FasterViT combines the benefits of fast local representation learning in CNNs and global modeling properties in ViT. Our newly introduced Hierarchical Attention (HAT) approach decomposes global self-attention with quadratic complexity into a multi-level attention with reduced computational costs. We benefit from efficient window-based self-attention. Each window has access to dedicated carrier tokens that participate in local and global represe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06189","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/2306.06189/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":"2306.06189","created_at":"2026-07-05T08:03:06.321547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06189v2","created_at":"2026-07-05T08:03:06.321547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06189","created_at":"2026-07-05T08:03:06.321547+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HJQJBTSCX2K","created_at":"2026-07-05T08:03:06.321547+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HJQJBTSCX2KUZ54","created_at":"2026-07-05T08:03:06.321547+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HJQJBTS","created_at":"2026-07-05T08:03:06.321547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29063","citing_title":"Accelerating HEVC Intra Partitioning via a CNN-Hierarchical Attention Transformer Hybrid","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11563","citing_title":"TCP-SSM: Efficient Vision State Space Models with Token-Conditioned Poles","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12798","citing_title":"VFA: Relieving Vector Operations in Flash Attention with Global Maximum Pre-computation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08333","citing_title":"Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HJQJBTSCX2KUZ54EUCFJARFM4","json":"https://pith.science/pith/5HJQJBTSCX2KUZ54EUCFJARFM4.json","graph_json":"https://pith.science/api/pith-number/5HJQJBTSCX2KUZ54EUCFJARFM4/graph.json","events_json":"https://pith.science/api/pith-number/5HJQJBTSCX2KUZ54EUCFJARFM4/events.json","paper":"https://pith.science/paper/5HJQJBTS"},"agent_actions":{"view_html":"https://pith.science/pith/5HJQJBTSCX2KUZ54EUCFJARFM4","download_json":"https://pith.science/pith/5HJQJBTSCX2KUZ54EUCFJARFM4.json","view_paper":"https://pith.science/paper/5HJQJBTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06189&json=true","fetch_graph":"https://pith.science/api/pith-number/5HJQJBTSCX2KUZ54EUCFJARFM4/graph.json","fetch_events":"https://pith.science/api/pith-number/5HJQJBTSCX2KUZ54EUCFJARFM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HJQJBTSCX2KUZ54EUCFJARFM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HJQJBTSCX2KUZ54EUCFJARFM4/action/storage_attestation","attest_author":"https://pith.science/pith/5HJQJBTSCX2KUZ54EUCFJARFM4/action/author_attestation","sign_citation":"https://pith.science/pith/5HJQJBTSCX2KUZ54EUCFJARFM4/action/citation_signature","submit_replication":"https://pith.science/pith/5HJQJBTSCX2KUZ54EUCFJARFM4/action/replication_record"}},"created_at":"2026-07-05T08:03:06.321547+00:00","updated_at":"2026-07-05T08:03:06.321547+00:00"}