{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NERJSJC42AGJ6NMHU5ITVE4MU2","short_pith_number":"pith:NERJSJC4","schema_version":"1.0","canonical_sha256":"692299245cd00c9f3587a7513a938ca69c8303f56f33af0fbb8ad816b246e8f6","source":{"kind":"arxiv","id":"2303.17803","version":5},"attestation_state":"computed","paper":{"title":"Rethinking Local Perception in Lightweight Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaibo Huang, Jiyang Guan, Qihang Fan, Ran He","submitted_at":"2023-03-31T05:25:32Z","abstract_excerpt":"Vision Transformers (ViTs) have been shown to be effective in various vision tasks. However, resizing them to a mobile-friendly size leads to significant performance degradation. Therefore, developing lightweight vision transformers has become a crucial area of research. This paper introduces CloFormer, a lightweight vision transformer that leverages context-aware local enhancement. CloFormer explores the relationship between globally shared weights often used in vanilla convolutional operators and token-specific context-aware weights appearing in attention, then proposes an effective and stra"},"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":"2303.17803","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-31T05:25:32Z","cross_cats_sorted":[],"title_canon_sha256":"ba73d78bcfafb93b9f50cd3d61cceab4d4042dcc8a5050fb71cf894a8bb52c8a","abstract_canon_sha256":"eb8bb2b593a2283fb8793d0893ceaabb1103daae74f986eb0d50f6bf71c913e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:17.478826Z","signature_b64":"H3iQ4yF7GbTeheaD7MgLVQLvWARuEXR5/Zi1dMkyOjumWIFLqJco9dAFKyxeh1g3W1mdqKLVigXete/ocUA/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"692299245cd00c9f3587a7513a938ca69c8303f56f33af0fbb8ad816b246e8f6","last_reissued_at":"2026-07-05T06:16:17.478278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:17.478278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Local Perception in Lightweight Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaibo Huang, Jiyang Guan, Qihang Fan, Ran He","submitted_at":"2023-03-31T05:25:32Z","abstract_excerpt":"Vision Transformers (ViTs) have been shown to be effective in various vision tasks. However, resizing them to a mobile-friendly size leads to significant performance degradation. Therefore, developing lightweight vision transformers has become a crucial area of research. This paper introduces CloFormer, a lightweight vision transformer that leverages context-aware local enhancement. CloFormer explores the relationship between globally shared weights often used in vanilla convolutional operators and token-specific context-aware weights appearing in attention, then proposes an effective and stra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17803","kind":"arxiv","version":5},"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/2303.17803/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":"2303.17803","created_at":"2026-07-05T06:16:17.478356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17803v5","created_at":"2026-07-05T06:16:17.478356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17803","created_at":"2026-07-05T06:16:17.478356+00:00"},{"alias_kind":"pith_short_12","alias_value":"NERJSJC42AGJ","created_at":"2026-07-05T06:16:17.478356+00:00"},{"alias_kind":"pith_short_16","alias_value":"NERJSJC42AGJ6NMH","created_at":"2026-07-05T06:16:17.478356+00:00"},{"alias_kind":"pith_short_8","alias_value":"NERJSJC4","created_at":"2026-07-05T06:16:17.478356+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18543","citing_title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18549","citing_title":"Advancing Vision Transformer with Enhanced Spatial Priors","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NERJSJC42AGJ6NMHU5ITVE4MU2","json":"https://pith.science/pith/NERJSJC42AGJ6NMHU5ITVE4MU2.json","graph_json":"https://pith.science/api/pith-number/NERJSJC42AGJ6NMHU5ITVE4MU2/graph.json","events_json":"https://pith.science/api/pith-number/NERJSJC42AGJ6NMHU5ITVE4MU2/events.json","paper":"https://pith.science/paper/NERJSJC4"},"agent_actions":{"view_html":"https://pith.science/pith/NERJSJC42AGJ6NMHU5ITVE4MU2","download_json":"https://pith.science/pith/NERJSJC42AGJ6NMHU5ITVE4MU2.json","view_paper":"https://pith.science/paper/NERJSJC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17803&json=true","fetch_graph":"https://pith.science/api/pith-number/NERJSJC42AGJ6NMHU5ITVE4MU2/graph.json","fetch_events":"https://pith.science/api/pith-number/NERJSJC42AGJ6NMHU5ITVE4MU2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NERJSJC42AGJ6NMHU5ITVE4MU2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NERJSJC42AGJ6NMHU5ITVE4MU2/action/storage_attestation","attest_author":"https://pith.science/pith/NERJSJC42AGJ6NMHU5ITVE4MU2/action/author_attestation","sign_citation":"https://pith.science/pith/NERJSJC42AGJ6NMHU5ITVE4MU2/action/citation_signature","submit_replication":"https://pith.science/pith/NERJSJC42AGJ6NMHU5ITVE4MU2/action/replication_record"}},"created_at":"2026-07-05T06:16:17.478356+00:00","updated_at":"2026-07-05T06:16:17.478356+00:00"}