{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7D72SUPNIATXHXIRMH4CBS4IE5","short_pith_number":"pith:7D72SUPN","schema_version":"1.0","canonical_sha256":"f8ffa951ed402773dd1161f820cb88275c68e684487a8fcee6a0b45c0f9ecf22","source":{"kind":"arxiv","id":"2309.02031","version":2},"attestation_state":"computed","paper":{"title":"A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Irene Amerini, Lorenzo Papa, Luping Zhou, Paolo Russo","submitted_at":"2023-09-05T08:21:16Z","abstract_excerpt":"Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism, outperforming earlier convolutional neural networks. However, ViT deployment and performance have grown steadily with their size, number of trainable parameters, and operations. Furthermore, self-attention's computational and memory cost quadratically increases with the image resolution. Generally speaking, it is challenging to employ these architectures in real"},"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":"2309.02031","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T08:21:16Z","cross_cats_sorted":[],"title_canon_sha256":"d0336ca496d807331cb9b0ef974b223a4422047e19a92d278d02a1ea55fadc5b","abstract_canon_sha256":"fac452038f1d76e4cba845d498f4af4f6dd56fa5f57cfbd7b34ea37c23cd54f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:50.354195Z","signature_b64":"nSBX2RLObb5aW00iFsrTdRWlEzTBoPX6rmElySUACwRWCC5shRJ6AbYOjcs8APayXfmv1YUGoQN2jnEbvmM7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8ffa951ed402773dd1161f820cb88275c68e684487a8fcee6a0b45c0f9ecf22","last_reissued_at":"2026-07-05T08:14:50.353802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:50.353802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Irene Amerini, Lorenzo Papa, Luping Zhou, Paolo Russo","submitted_at":"2023-09-05T08:21:16Z","abstract_excerpt":"Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism, outperforming earlier convolutional neural networks. However, ViT deployment and performance have grown steadily with their size, number of trainable parameters, and operations. Furthermore, self-attention's computational and memory cost quadratically increases with the image resolution. Generally speaking, it is challenging to employ these architectures in real"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02031","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/2309.02031/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":"2309.02031","created_at":"2026-07-05T08:14:50.353861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02031v2","created_at":"2026-07-05T08:14:50.353861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02031","created_at":"2026-07-05T08:14:50.353861+00:00"},{"alias_kind":"pith_short_12","alias_value":"7D72SUPNIATX","created_at":"2026-07-05T08:14:50.353861+00:00"},{"alias_kind":"pith_short_16","alias_value":"7D72SUPNIATXHXIR","created_at":"2026-07-05T08:14:50.353861+00:00"},{"alias_kind":"pith_short_8","alias_value":"7D72SUPN","created_at":"2026-07-05T08:14:50.353861+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/7D72SUPNIATXHXIRMH4CBS4IE5","json":"https://pith.science/pith/7D72SUPNIATXHXIRMH4CBS4IE5.json","graph_json":"https://pith.science/api/pith-number/7D72SUPNIATXHXIRMH4CBS4IE5/graph.json","events_json":"https://pith.science/api/pith-number/7D72SUPNIATXHXIRMH4CBS4IE5/events.json","paper":"https://pith.science/paper/7D72SUPN"},"agent_actions":{"view_html":"https://pith.science/pith/7D72SUPNIATXHXIRMH4CBS4IE5","download_json":"https://pith.science/pith/7D72SUPNIATXHXIRMH4CBS4IE5.json","view_paper":"https://pith.science/paper/7D72SUPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02031&json=true","fetch_graph":"https://pith.science/api/pith-number/7D72SUPNIATXHXIRMH4CBS4IE5/graph.json","fetch_events":"https://pith.science/api/pith-number/7D72SUPNIATXHXIRMH4CBS4IE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7D72SUPNIATXHXIRMH4CBS4IE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7D72SUPNIATXHXIRMH4CBS4IE5/action/storage_attestation","attest_author":"https://pith.science/pith/7D72SUPNIATXHXIRMH4CBS4IE5/action/author_attestation","sign_citation":"https://pith.science/pith/7D72SUPNIATXHXIRMH4CBS4IE5/action/citation_signature","submit_replication":"https://pith.science/pith/7D72SUPNIATXHXIRMH4CBS4IE5/action/replication_record"}},"created_at":"2026-07-05T08:14:50.353861+00:00","updated_at":"2026-07-05T08:14:50.353861+00:00"}