{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GR7Z6F6IVUFJLAO3K7MEF4DZN5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"53bfbd379bfee7245fe18eebd9531748c7be1009072812cb719bdbf3001177d1","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-06T19:08:56Z","title_canon_sha256":"504df1b350ee4f4dec3268f88a0fdd69a489c81f99e9ced52fa2931aac0ffb02"},"schema_version":"1.0","source":{"id":"2307.03254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03254","created_at":"2026-07-05T06:28:39Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03254v1","created_at":"2026-07-05T06:28:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03254","created_at":"2026-07-05T06:28:39Z"},{"alias_kind":"pith_short_12","alias_value":"GR7Z6F6IVUFJ","created_at":"2026-07-05T06:28:39Z"},{"alias_kind":"pith_short_16","alias_value":"GR7Z6F6IVUFJLAO3","created_at":"2026-07-05T06:28:39Z"},{"alias_kind":"pith_short_8","alias_value":"GR7Z6F6I","created_at":"2026-07-05T06:28:39Z"}],"graph_snapshots":[{"event_id":"sha256:8609f4fff8edf00bc2d39f9e9629aaa3340e8faab02d02968d9f8b1be53c883a","target":"graph","created_at":"2026-07-05T06:28:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2307.03254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Casey Kennington, Clayton Fields","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-06T19:08:56Z","title":"Vision Language Transformers: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03254","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:07067a1a08f7006501b7932415c5b847a74c3ed8fd59f5a3bb4adfe0ae0a859b","target":"record","created_at":"2026-07-05T06:28:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"53bfbd379bfee7245fe18eebd9531748c7be1009072812cb719bdbf3001177d1","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-06T19:08:56Z","title_canon_sha256":"504df1b350ee4f4dec3268f88a0fdd69a489c81f99e9ced52fa2931aac0ffb02"},"schema_version":"1.0","source":{"id":"2307.03254","kind":"arxiv","version":1}},"canonical_sha256":"347f9f17c8ad0a9581db57d842f0796f7a0b0b7e2b9cd742addb35b562c795d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"347f9f17c8ad0a9581db57d842f0796f7a0b0b7e2b9cd742addb35b562c795d7","first_computed_at":"2026-07-05T06:28:39.914850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:39.914850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nxcdT9CW3QlGsFU0HwjKtdqvxTD6L/C8qya4OOnc2eXk2thYGUzqvHEQa3qOmxyayDA0s0znYJBLoNwQmJPECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:39.915408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.03254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07067a1a08f7006501b7932415c5b847a74c3ed8fd59f5a3bb4adfe0ae0a859b","sha256:8609f4fff8edf00bc2d39f9e9629aaa3340e8faab02d02968d9f8b1be53c883a"],"state_sha256":"ac3de25311a2859c60d08f6c3f37e5728bf5f5856f088a595f2d6d04db277cfe"}