{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OQ2EC7FA2EHTO235HQVUQQECV3","short_pith_number":"pith:OQ2EC7FA","schema_version":"1.0","canonical_sha256":"7434417ca0d10f376b7d3c2b484082aef133fed344442a6bbb37568fa914fb59","source":{"kind":"arxiv","id":"2408.15178","version":1},"attestation_state":"computed","paper":{"title":"A Review of Transformer-Based Models for Computer Vision Tasks: Capturing Global Context and Spatial Relationships","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gracile Astlin Pereira, Muhammad Hussain","submitted_at":"2024-08-27T16:22:18Z","abstract_excerpt":"Transformer-based models have transformed the landscape of natural language processing (NLP) and are increasingly applied to computer vision tasks with remarkable success. These models, renowned for their ability to capture long-range dependencies and contextual information, offer a promising alternative to traditional convolutional neural networks (CNNs) in computer vision. In this review paper, we provide an extensive overview of various transformer architectures adapted for computer vision tasks. We delve into how these models capture global context and spatial relationships in images, empo"},"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":"2408.15178","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-27T16:22:18Z","cross_cats_sorted":[],"title_canon_sha256":"cdc677480882c1e53c095b5f810209d35f629348fb157e4e9ed0f92605725376","abstract_canon_sha256":"1400a9ed49c12d9b615ff16acc3eb4c87b7b1a066de47d6d91d29adb8ce7a76b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:55.487445Z","signature_b64":"iVL9AhWb6sP5RvNxiPoc4F+6KTNfVG8FtnMA5EI7JJ3JxJ7EkMmhtPnrKrBdulhBy1KqMLrGiD7L49s4jwHZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7434417ca0d10f376b7d3c2b484082aef133fed344442a6bbb37568fa914fb59","last_reissued_at":"2026-07-05T08:59:55.487063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:55.487063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Review of Transformer-Based Models for Computer Vision Tasks: Capturing Global Context and Spatial Relationships","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gracile Astlin Pereira, Muhammad Hussain","submitted_at":"2024-08-27T16:22:18Z","abstract_excerpt":"Transformer-based models have transformed the landscape of natural language processing (NLP) and are increasingly applied to computer vision tasks with remarkable success. These models, renowned for their ability to capture long-range dependencies and contextual information, offer a promising alternative to traditional convolutional neural networks (CNNs) in computer vision. In this review paper, we provide an extensive overview of various transformer architectures adapted for computer vision tasks. We delve into how these models capture global context and spatial relationships in images, empo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15178","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/2408.15178/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":"2408.15178","created_at":"2026-07-05T08:59:55.487119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.15178v1","created_at":"2026-07-05T08:59:55.487119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15178","created_at":"2026-07-05T08:59:55.487119+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQ2EC7FA2EHT","created_at":"2026-07-05T08:59:55.487119+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQ2EC7FA2EHTO235","created_at":"2026-07-05T08:59:55.487119+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQ2EC7FA","created_at":"2026-07-05T08:59:55.487119+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04020","citing_title":"Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learning","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQ2EC7FA2EHTO235HQVUQQECV3","json":"https://pith.science/pith/OQ2EC7FA2EHTO235HQVUQQECV3.json","graph_json":"https://pith.science/api/pith-number/OQ2EC7FA2EHTO235HQVUQQECV3/graph.json","events_json":"https://pith.science/api/pith-number/OQ2EC7FA2EHTO235HQVUQQECV3/events.json","paper":"https://pith.science/paper/OQ2EC7FA"},"agent_actions":{"view_html":"https://pith.science/pith/OQ2EC7FA2EHTO235HQVUQQECV3","download_json":"https://pith.science/pith/OQ2EC7FA2EHTO235HQVUQQECV3.json","view_paper":"https://pith.science/paper/OQ2EC7FA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.15178&json=true","fetch_graph":"https://pith.science/api/pith-number/OQ2EC7FA2EHTO235HQVUQQECV3/graph.json","fetch_events":"https://pith.science/api/pith-number/OQ2EC7FA2EHTO235HQVUQQECV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQ2EC7FA2EHTO235HQVUQQECV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQ2EC7FA2EHTO235HQVUQQECV3/action/storage_attestation","attest_author":"https://pith.science/pith/OQ2EC7FA2EHTO235HQVUQQECV3/action/author_attestation","sign_citation":"https://pith.science/pith/OQ2EC7FA2EHTO235HQVUQQECV3/action/citation_signature","submit_replication":"https://pith.science/pith/OQ2EC7FA2EHTO235HQVUQQECV3/action/replication_record"}},"created_at":"2026-07-05T08:59:55.487119+00:00","updated_at":"2026-07-05T08:59:55.487119+00:00"}