{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6Y4H76CNO5FCBY5EWAV3WUMN2P","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":"e7d1c140d5ce7a513dcd298001e9e413f4c2ed9052c387b92626d243b9ce23cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T18:59:43Z","title_canon_sha256":"13fac5650894a2ccf3aaabed0e65c1607774fdc3fee915ec18b51aaf0746297c"},"schema_version":"1.0","source":{"id":"2312.09251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09251","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09251v1","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09251","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"pith_short_12","alias_value":"6Y4H76CNO5FC","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"pith_short_16","alias_value":"6Y4H76CNO5FCBY5E","created_at":"2026-07-05T07:24:16Z"},{"alias_kind":"pith_short_8","alias_value":"6Y4H76CN","created_at":"2026-07-05T07:24:16Z"}],"graph_snapshots":[{"event_id":"sha256:7e4b5e3e66676f316155eab1d9643e3f820a33dae26fd9eed1c3fd30e88df55f","target":"graph","created_at":"2026-07-05T07:24:16Z","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/2312.09251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for both image and text modalities by employing a straightforward auto-regressive objective, thereby enabling the model to process image and text as seamlessly as a language model processes text. To accomplish this, we initially propose a novel image tokenizer-detokenizer framework for visual data, specifically designed to transform raw images into a sequence o","authors_text":"Hengshuang Zhao, Jinguo Zhu, Sijie Zhao, Xiaohan Ding, Xiaohua Wang, Ying Shan, Yixiao Ge, Yuying Ge","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T18:59:43Z","title":"VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09251","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:cac60f43dc2c2461bb039c880780534312c8ac62340a40e4ed87066bd4a749a3","target":"record","created_at":"2026-07-05T07:24:16Z","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":"e7d1c140d5ce7a513dcd298001e9e413f4c2ed9052c387b92626d243b9ce23cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T18:59:43Z","title_canon_sha256":"13fac5650894a2ccf3aaabed0e65c1607774fdc3fee915ec18b51aaf0746297c"},"schema_version":"1.0","source":{"id":"2312.09251","kind":"arxiv","version":1}},"canonical_sha256":"f6387ff84d774a20e3a4b02bbb518dd3d220e27e4be9f315556ab7d1612b7a98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6387ff84d774a20e3a4b02bbb518dd3d220e27e4be9f315556ab7d1612b7a98","first_computed_at":"2026-07-05T07:24:16.552145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:16.552145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XjxSEBNb7rGHy9MOt5+UOg3WpoqpyglzN/vkuucbftIpWhDEXdHU/2NAraQMjxAwFtx90kJSxfvdKRXDAIBaDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:16.552634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.09251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cac60f43dc2c2461bb039c880780534312c8ac62340a40e4ed87066bd4a749a3","sha256:7e4b5e3e66676f316155eab1d9643e3f820a33dae26fd9eed1c3fd30e88df55f"],"state_sha256":"a314b52ee9a3750c5a3ed495089b7fdec78de13d424b3f5a1b49c460b016593a"}