{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GR7Z6F6IVUFJLAO3K7MEF4DZN5","short_pith_number":"pith:GR7Z6F6I","schema_version":"1.0","canonical_sha256":"347f9f17c8ad0a9581db57d842f0796f7a0b0b7e2b9cd742addb35b562c795d7","source":{"kind":"arxiv","id":"2307.03254","version":1},"attestation_state":"computed","paper":{"title":"Vision Language Transformers: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Casey Kennington, Clayton Fields","submitted_at":"2023-07-06T19:08:56Z","abstract_excerpt":"Vision language tasks, such as answering questions about or generating captions that describe an image, are difficult tasks for computers to perform. A relatively recent body of research has adapted the pretrained transformer architecture introduced in \\citet{vaswani2017attention} to vision language modeling. Transformer models have greatly improved performance and versatility over previous vision language models. They do so by pretraining models on a large generic datasets and transferring their learning to new tasks with minor changes in architecture and parameter values. This type of transf"},"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":"2307.03254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-06T19:08:56Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"504df1b350ee4f4dec3268f88a0fdd69a489c81f99e9ced52fa2931aac0ffb02","abstract_canon_sha256":"53bfbd379bfee7245fe18eebd9531748c7be1009072812cb719bdbf3001177d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:39.915408Z","signature_b64":"nxcdT9CW3QlGsFU0HwjKtdqvxTD6L/C8qya4OOnc2eXk2thYGUzqvHEQa3qOmxyayDA0s0znYJBLoNwQmJPECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"347f9f17c8ad0a9581db57d842f0796f7a0b0b7e2b9cd742addb35b562c795d7","last_reissued_at":"2026-07-05T06:28:39.914850Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:39.914850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Language Transformers: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Casey Kennington, Clayton Fields","submitted_at":"2023-07-06T19:08:56Z","abstract_excerpt":"Vision language tasks, such as answering questions about or generating captions that describe an image, are difficult tasks for computers to perform. A relatively recent body of research has adapted the pretrained transformer architecture introduced in \\citet{vaswani2017attention} to vision language modeling. Transformer models have greatly improved performance and versatility over previous vision language models. They do so by pretraining models on a large generic datasets and transferring their learning to new tasks with minor changes in architecture and parameter values. This type of transf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03254","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/2307.03254/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":"2307.03254","created_at":"2026-07-05T06:28:39.914911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03254v1","created_at":"2026-07-05T06:28:39.914911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03254","created_at":"2026-07-05T06:28:39.914911+00:00"},{"alias_kind":"pith_short_12","alias_value":"GR7Z6F6IVUFJ","created_at":"2026-07-05T06:28:39.914911+00:00"},{"alias_kind":"pith_short_16","alias_value":"GR7Z6F6IVUFJLAO3","created_at":"2026-07-05T06:28:39.914911+00:00"},{"alias_kind":"pith_short_8","alias_value":"GR7Z6F6I","created_at":"2026-07-05T06:28:39.914911+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.22123","citing_title":"Multilingual Vision-Language Models, A Survey","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18452","citing_title":"ESsEN: Training Compact Discriminative Vision-Language Transformers in a Low-Resource Setting","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06714","citing_title":"Edge Deep Learning in Computer Vision and Medical Diagnostics: A Comprehensive Survey","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02035","citing_title":"VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation","ref_index":95,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GR7Z6F6IVUFJLAO3K7MEF4DZN5","json":"https://pith.science/pith/GR7Z6F6IVUFJLAO3K7MEF4DZN5.json","graph_json":"https://pith.science/api/pith-number/GR7Z6F6IVUFJLAO3K7MEF4DZN5/graph.json","events_json":"https://pith.science/api/pith-number/GR7Z6F6IVUFJLAO3K7MEF4DZN5/events.json","paper":"https://pith.science/paper/GR7Z6F6I"},"agent_actions":{"view_html":"https://pith.science/pith/GR7Z6F6IVUFJLAO3K7MEF4DZN5","download_json":"https://pith.science/pith/GR7Z6F6IVUFJLAO3K7MEF4DZN5.json","view_paper":"https://pith.science/paper/GR7Z6F6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03254&json=true","fetch_graph":"https://pith.science/api/pith-number/GR7Z6F6IVUFJLAO3K7MEF4DZN5/graph.json","fetch_events":"https://pith.science/api/pith-number/GR7Z6F6IVUFJLAO3K7MEF4DZN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GR7Z6F6IVUFJLAO3K7MEF4DZN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GR7Z6F6IVUFJLAO3K7MEF4DZN5/action/storage_attestation","attest_author":"https://pith.science/pith/GR7Z6F6IVUFJLAO3K7MEF4DZN5/action/author_attestation","sign_citation":"https://pith.science/pith/GR7Z6F6IVUFJLAO3K7MEF4DZN5/action/citation_signature","submit_replication":"https://pith.science/pith/GR7Z6F6IVUFJLAO3K7MEF4DZN5/action/replication_record"}},"created_at":"2026-07-05T06:28:39.914911+00:00","updated_at":"2026-07-05T06:28:39.914911+00:00"}