{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7E2Q2DDO6DY7K2C7CM5RBA3V23","short_pith_number":"pith:7E2Q2DDO","schema_version":"1.0","canonical_sha256":"f9350d0c6ef0f1f5685f133b108375d6fe456bd6532003e3cfba89ad12f0ac10","source":{"kind":"arxiv","id":"2207.05557","version":1},"attestation_state":"computed","paper":{"title":"LightViT: Towards Light-Weight Convolution-Free Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chen Qian, Fei Wang, Lang Huang, Shan You, Tao Huang","submitted_at":"2022-07-12T14:27:57Z","abstract_excerpt":"Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias. Recent works thus resort to convolutions as a plug-and-play module and embed them in various ViT counterparts. In this paper, we argue that the convolutional kernels perform information aggregation to connect all tokens; however, they would be actually unnecessary for light-weight ViTs if this explicit aggregation could function in a more homogeneous way. Inspired by this, we present LightViT as a new family of light-weight ViTs to achieve bette"},"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":"2207.05557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-12T14:27:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6e404f9cce19c1c0b15dc4def74b9c51ce481011f7aa25e390d5de84b3dac99b","abstract_canon_sha256":"3c9e0797e25fecfb6579e58be3ef1bfbfc7f3f6f792fdc3b9e30ed7db8ce06a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:43.982440Z","signature_b64":"A21Z8VGno6+CHYZl5L0X4cT/bhbc7uoG0oHibyK3CCQ6GHZpuJYPjhXrkzRrcsnPdL4T04iGRQ+0eJQcigwuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9350d0c6ef0f1f5685f133b108375d6fe456bd6532003e3cfba89ad12f0ac10","last_reissued_at":"2026-07-05T04:39:43.981906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:43.981906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LightViT: Towards Light-Weight Convolution-Free Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chen Qian, Fei Wang, Lang Huang, Shan You, Tao Huang","submitted_at":"2022-07-12T14:27:57Z","abstract_excerpt":"Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias. Recent works thus resort to convolutions as a plug-and-play module and embed them in various ViT counterparts. In this paper, we argue that the convolutional kernels perform information aggregation to connect all tokens; however, they would be actually unnecessary for light-weight ViTs if this explicit aggregation could function in a more homogeneous way. Inspired by this, we present LightViT as a new family of light-weight ViTs to achieve bette"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05557","kind":"arxiv","version":1},"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/2207.05557/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":"2207.05557","created_at":"2026-07-05T04:39:43.981987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.05557v1","created_at":"2026-07-05T04:39:43.981987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05557","created_at":"2026-07-05T04:39:43.981987+00:00"},{"alias_kind":"pith_short_12","alias_value":"7E2Q2DDO6DY7","created_at":"2026-07-05T04:39:43.981987+00:00"},{"alias_kind":"pith_short_16","alias_value":"7E2Q2DDO6DY7K2C7","created_at":"2026-07-05T04:39:43.981987+00:00"},{"alias_kind":"pith_short_8","alias_value":"7E2Q2DDO","created_at":"2026-07-05T04:39:43.981987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04118","citing_title":"PromptSR: Cascade Prompting for Lightweight Image Super-Resolution","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7E2Q2DDO6DY7K2C7CM5RBA3V23","json":"https://pith.science/pith/7E2Q2DDO6DY7K2C7CM5RBA3V23.json","graph_json":"https://pith.science/api/pith-number/7E2Q2DDO6DY7K2C7CM5RBA3V23/graph.json","events_json":"https://pith.science/api/pith-number/7E2Q2DDO6DY7K2C7CM5RBA3V23/events.json","paper":"https://pith.science/paper/7E2Q2DDO"},"agent_actions":{"view_html":"https://pith.science/pith/7E2Q2DDO6DY7K2C7CM5RBA3V23","download_json":"https://pith.science/pith/7E2Q2DDO6DY7K2C7CM5RBA3V23.json","view_paper":"https://pith.science/paper/7E2Q2DDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.05557&json=true","fetch_graph":"https://pith.science/api/pith-number/7E2Q2DDO6DY7K2C7CM5RBA3V23/graph.json","fetch_events":"https://pith.science/api/pith-number/7E2Q2DDO6DY7K2C7CM5RBA3V23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7E2Q2DDO6DY7K2C7CM5RBA3V23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7E2Q2DDO6DY7K2C7CM5RBA3V23/action/storage_attestation","attest_author":"https://pith.science/pith/7E2Q2DDO6DY7K2C7CM5RBA3V23/action/author_attestation","sign_citation":"https://pith.science/pith/7E2Q2DDO6DY7K2C7CM5RBA3V23/action/citation_signature","submit_replication":"https://pith.science/pith/7E2Q2DDO6DY7K2C7CM5RBA3V23/action/replication_record"}},"created_at":"2026-07-05T04:39:43.981987+00:00","updated_at":"2026-07-05T04:39:43.981987+00:00"}