{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TEBF7JPAIYBD5SIZIGFC2J5Z2G","short_pith_number":"pith:TEBF7JPA","schema_version":"1.0","canonical_sha256":"99025fa5e046023ec919418a2d27b9d1a86dbd8c40322f42f04eb8b653009ea7","source":{"kind":"arxiv","id":"2107.02960","version":3},"attestation_state":"computed","paper":{"title":"GLiT: Neural Architecture Search for Global and Local Image Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baopu Li, Boyu Chen, Chen Lin, Chuming Li, Junjie Yan, Lei Bai, Ming Sun, Peixia Li, Wanli Ouyang","submitted_at":"2021-07-07T00:48:09Z","abstract_excerpt":"We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones are found to achieve impressive performance for image recognition. However, the transformer is designed for NLP tasks and thus could be sub-optimal when directly used for image recognition. In order to improve the visual representation ability for transformers, we propose a new search space and searching algorithm. Specifically, we introduce a locality module that models the local correlations in images explicitly wit"},"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":"2107.02960","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-07T00:48:09Z","cross_cats_sorted":[],"title_canon_sha256":"88cd4490e629670d838e2e60e3acd01f9d8863115540765ad61116da4226753e","abstract_canon_sha256":"a0bf8cd874a902a01b66a07741e3ed106aa181677f913d5ae370c57549d55811"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:31.045587Z","signature_b64":"0Pu9eLTsqBHYw5QCOPnrlL49+j7y2ZyxzdHFsaU8V5D5JtTJFE3Usy3fYY7KwM03m7yRL+1Hp/Esk/bA2uhyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99025fa5e046023ec919418a2d27b9d1a86dbd8c40322f42f04eb8b653009ea7","last_reissued_at":"2026-07-05T03:06:31.045181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:31.045181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLiT: Neural Architecture Search for Global and Local Image Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baopu Li, Boyu Chen, Chen Lin, Chuming Li, Junjie Yan, Lei Bai, Ming Sun, Peixia Li, Wanli Ouyang","submitted_at":"2021-07-07T00:48:09Z","abstract_excerpt":"We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones are found to achieve impressive performance for image recognition. However, the transformer is designed for NLP tasks and thus could be sub-optimal when directly used for image recognition. In order to improve the visual representation ability for transformers, we propose a new search space and searching algorithm. Specifically, we introduce a locality module that models the local correlations in images explicitly wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02960","kind":"arxiv","version":3},"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/2107.02960/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":"2107.02960","created_at":"2026-07-05T03:06:31.045235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.02960v3","created_at":"2026-07-05T03:06:31.045235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02960","created_at":"2026-07-05T03:06:31.045235+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEBF7JPAIYBD","created_at":"2026-07-05T03:06:31.045235+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEBF7JPAIYBD5SIZ","created_at":"2026-07-05T03:06:31.045235+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEBF7JPA","created_at":"2026-07-05T03:06:31.045235+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/TEBF7JPAIYBD5SIZIGFC2J5Z2G","json":"https://pith.science/pith/TEBF7JPAIYBD5SIZIGFC2J5Z2G.json","graph_json":"https://pith.science/api/pith-number/TEBF7JPAIYBD5SIZIGFC2J5Z2G/graph.json","events_json":"https://pith.science/api/pith-number/TEBF7JPAIYBD5SIZIGFC2J5Z2G/events.json","paper":"https://pith.science/paper/TEBF7JPA"},"agent_actions":{"view_html":"https://pith.science/pith/TEBF7JPAIYBD5SIZIGFC2J5Z2G","download_json":"https://pith.science/pith/TEBF7JPAIYBD5SIZIGFC2J5Z2G.json","view_paper":"https://pith.science/paper/TEBF7JPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.02960&json=true","fetch_graph":"https://pith.science/api/pith-number/TEBF7JPAIYBD5SIZIGFC2J5Z2G/graph.json","fetch_events":"https://pith.science/api/pith-number/TEBF7JPAIYBD5SIZIGFC2J5Z2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEBF7JPAIYBD5SIZIGFC2J5Z2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEBF7JPAIYBD5SIZIGFC2J5Z2G/action/storage_attestation","attest_author":"https://pith.science/pith/TEBF7JPAIYBD5SIZIGFC2J5Z2G/action/author_attestation","sign_citation":"https://pith.science/pith/TEBF7JPAIYBD5SIZIGFC2J5Z2G/action/citation_signature","submit_replication":"https://pith.science/pith/TEBF7JPAIYBD5SIZIGFC2J5Z2G/action/replication_record"}},"created_at":"2026-07-05T03:06:31.045235+00:00","updated_at":"2026-07-05T03:06:31.045235+00:00"}