{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","arxiv_id":"2301.12597","date":"2023-01-30","proceeding":"Conference 2023 2","authors":["Junnan Li","Dongxu Li","Silvio Savarese","Steven Hoi"],"abstract":"The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models. This paper proposes BLIP-2, a generic and efficient pre-training strategy that bootstraps vision-language pre-training from off-the-shelf frozen pre-trained image encoders and frozen large language models. BLIP-2 bridges the modality gap with a lightweight Querying Transformer, which is pre-trained in two stages. The first stage bootstraps vision-language representation learning from a frozen image encoder. The second stage bootstraps vision-to-language generative learning from a frozen language model. BLIP-2 achieves state-of-the-art performance on various vision-language tasks, despite having significantly fewer trainable parameters than existing methods. For example, our model outperforms Flamingo80B by 8.7% on zero-shot VQAv2 with 54x fewer trainable parameters. We also demonstrate the model's emerging capabilities of zero-shot image-to-text generation that can follow natural language instructions.","url_abs":"https://arxiv.org/abs/2301.12597v3","url_pdf":"https://arxiv.org/pdf/2301.12597v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/salesforce/lavis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/albertotestoni/ndq_visual_objects","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/alibaba/graphtranslator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/baaivision/eva","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/facebookresearch/multimodal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/gregor-ge/mblip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/jiwanchung/vlis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/junshutang/Make-It-3D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/kdr/videorag-mrr2024","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/linzhiqiu/clip-flant5","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/rabiulcste/vqazero","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/thudm/visualglm-6b","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/yukw777/videoblip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"blip-2-bootstrapping-language-image-pre","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"generative-visual-question-answering","task_name":"Generative Visual Question Answering"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"medical-visual-question-answering","task_name":"Medical Visual Question Answering"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"open-vocabulary-attribute-detection","task_name":"Open Vocabulary Attribute Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"},{"task_slug":"zero-shot-text-to-image-retrieval","task_name":"Zero-shot Text-to-Image Retrieval"},{"task_slug":"visual-instruction-following","task_name":"visual instruction following"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generative-visual-question-answering-on-pmc","task":"Generative Visual Question Answering","dataset":"PMC-VQA","model":"BLIP-2","rank_in_archive_order":2,"of":3,"metrics":{"BLEU-1":"7.6"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":4,"of":41,"metrics":{"BLEU-4":"43.7","CIDER":"145.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":5,"of":41,"metrics":{"BLEU-4":"43.5","CIDER":"145.2"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":8,"of":41,"metrics":{"BLEU-4":"42.4","CIDER":"144.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-in-domain","task":"Image Captioning","dataset":"nocaps-val-in-domain","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":1,"of":11,"metrics":{"CIDEr":"123.7","Pre-train (#images)":"1.1B","SPICE":"16.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-in-domain","task":"Image Captioning","dataset":"nocaps-val-in-domain","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":2,"of":11,"metrics":{"CIDEr":"123.7","Pre-train (#images)":"1.1B","SPICE":"15.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-in-domain","task":"Image Captioning","dataset":"nocaps-val-in-domain","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":3,"of":11,"metrics":{"CIDEr":"123","Pre-train (#images)":"1.1B","SPICE":"15.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-near-domain","task":"Image Captioning","dataset":"nocaps-val-near-domain","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":1,"of":10,"metrics":{"CIDEr":"120.2","Pre-train (#images)":"1.1B","SPICE":"15.9"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-near-domain","task":"Image Captioning","dataset":"nocaps-val-near-domain","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":2,"of":10,"metrics":{"CIDEr":"119.2","Pre-train (#images)":"1.1B","SPICE":"15.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-near-domain","task":"Image Captioning","dataset":"nocaps-val-near-domain","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":3,"of":10,"metrics":{"CIDEr":"117.8","Pre-train (#images)":"1.1B","SPICE":"15.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-out-domain","task":"Image Captioning","dataset":"nocaps-val-out-domain","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":1,"of":10,"metrics":{"CIDEr":"124.8","Pretrain (#images)":"1.1B","SPICE":"15.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-out-domain","task":"Image Captioning","dataset":"nocaps-val-out-domain","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":2,"of":10,"metrics":{"CIDEr":"124.4","Pretrain (#images)":"1.1B","SPICE":"14.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-out-domain","task":"Image Captioning","dataset":"nocaps-val-out-domain","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":3,"of":10,"metrics":{"CIDEr":"123.4","Pretrain (#images)":"1.1B","SPICE":"15.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-overall","task":"Image Captioning","dataset":"nocaps-val-overall","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":1,"of":11,"metrics":{"CIDEr":"121.6","Pretrain (#images)":"1.1B","SPICE":"15.8"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-overall","task":"Image Captioning","dataset":"nocaps-val-overall","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":2,"of":11,"metrics":{"CIDEr":"121.0","Pretrain (#images)":"1.1B","SPICE":"15.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-overall","task":"Image Captioning","dataset":"nocaps-val-overall","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":3,"of":11,"metrics":{"CIDEr":"119.7","Pretrain (#images)":"1.1B","SPICE":"15.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-coco","task":"Image Retrieval","dataset":"COCO (Common Objects in Context)","model":"BLIP-2 ViT-G (fine-tuned)","rank_in_archive_order":1,"of":6,"metrics":{"Recall@10":"92.6","recall@1":"68.3","recall@5":"87.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-coco","task":"Image Retrieval","dataset":"COCO (Common Objects in Context)","model":"BLIP-2 ViT-L (fine-tuned)","rank_in_archive_order":3,"of":6,"metrics":{"Recall@10":"91.8","recall@1":"66.3","recall@5":"86.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-flickr30k","task":"Image Retrieval","dataset":"Flickr30k","model":"BLIP-2 ViT-G (zero-shot, 1K test set)","rank_in_archive_order":1,"of":9,"metrics":{"Recall@1":"89.7","Recall@10":"98.9","Recall@5":"98.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-flickr30k","task":"Image Retrieval","dataset":"Flickr30k","model":"BLIP-2 ViT-L (zero-shot, 1K test set)","rank_in_archive_order":2,"of":9,"metrics":{"Recall@1":"88.6","Recall@10":"98.9","Recall@5":"97.6"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-coco","task":"Image-to-Text Retrieval","dataset":"COCO (Common Objects in Context)","model":"BLIP-2 (ViT-G, fine-tuned)","rank_in_archive_order":1,"of":9,"metrics":{"Recall@1":"85.4","Recall@10":"98.5","Recall@5":"97.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-coco","task":"Image-to-Text Retrieval","dataset":"COCO (Common Objects in Context)","model":"BLIP-2 (ViT-L, fine-tuned)","rank_in_archive_order":3,"of":9,"metrics":{"Recall@1":"83.5","Recall@10":"98.0","Recall@5":"96.0"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-flickr30k","task":"Image-to-Text Retrieval","dataset":"Flickr30k","model":"BLIP-2 ViT-G (zero-shot, 1K test set)","rank_in_archive_order":2,"of":11,"metrics":{"Recall@1":"97.6","Recall@10":"100","Recall@5":"100"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-flickr30k","task":"Image-to-Text Retrieval","dataset":"Flickr30k","model":"BLIP-2 ViT-L (zero-shot, 1K test set)","rank_in_archive_order":5,"of":11,"metrics":{"Recall@1":"96.9","Recall@10":"100","Recall@5":"100"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-attribute-detection-on-ovad-1","task":"Open Vocabulary Attribute Detection","dataset":"OVAD-Box benchmark","model":"BLIP 2 (pretrained)","rank_in_archive_order":2,"of":7,"metrics":{"mean average precision":"25.5"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"BLIP-2-12B","rank_in_archive_order":226,"of":231,"metrics":{"GPT-4 score":"22.4±0.2","Params":"12B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev-1","task":"Visual Question Answering","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G OPT 6.7B (fine-tuned)","rank_in_archive_order":1,"of":11,"metrics":{"Accuracy":"82.30"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev-1","task":"Visual Question Answering","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G OPT 2.7B (fine-tuned)","rank_in_archive_order":4,"of":11,"metrics":{"Accuracy":"81.74"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev-1","task":"Visual Question Answering","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G FlanT5 XL (fine-tuned)","rank_in_archive_order":5,"of":11,"metrics":{"Accuracy":"81.66"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val-1","task":"Visual Question Answering","dataset":"VQA v2 val","model":"BLIP-2 ViT-G OPT 6.7B (fine-tuned)","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"82.19"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val-1","task":"Visual Question Answering","dataset":"VQA v2 val","model":"BLIP-2 ViT-G OPT 2.7B (fine-tuned)","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"81.59"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val-1","task":"Visual Question Answering","dataset":"VQA v2 val","model":"BLIP-2 ViT-G FlanT5 XL (fine-tuned)","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"81.55"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-G FlanT5 XXL (zero-shot)","rank_in_archive_order":10,"of":17,"metrics":{"Accuracy":"44.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-L FlanT5 XL (zero-shot)","rank_in_archive_order":11,"of":17,"metrics":{"Accuracy":"44.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":12,"of":17,"metrics":{"Accuracy":"44.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":14,"of":17,"metrics":{"Accuracy":"36.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":15,"of":17,"metrics":{"Accuracy":"34.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"BLIP-2 ViT-L OPT 2.7B (zero-shot)","rank_in_archive_order":16,"of":17,"metrics":{"Accuracy":"33.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-core-mm","task":"Visual Question Answering (VQA)","dataset":"InfiMM-Eval","model":"BLIP-2-OPT2.7B","rank_in_archive_order":12,"of":14,"metrics":{"Abductive":"18.96","Analogical":"7.5","Deductive":"2.76","Overall score":"19.31","Params":"3B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-infoseek","task":"Visual Question Answering (VQA)","dataset":"InfoSeek","model":"BLIP2","rank_in_archive_order":6,"of":7,"metrics":{"Accuracy":"14.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-G FlanT5 XXL (zero-shot)","rank_in_archive_order":23,"of":37,"metrics":{"Accuracy":"45.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":28,"of":37,"metrics":{"Accuracy":"40.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-L FlanT5 XL (zero-shot)","rank_in_archive_order":29,"of":37,"metrics":{"Accuracy":"39.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":30,"of":37,"metrics":{"Accuracy":"36.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":32,"of":37,"metrics":{"Accuracy":"31.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-ok-vqa","task":"Visual Question Answering (VQA)","dataset":"OK-VQA","model":"BLIP-2 ViT-L OPT 2.7B (zero-shot)","rank_in_archive_order":33,"of":37,"metrics":{"Accuracy":"30.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-vqa-on-pmc-vqa","task":"Visual Question Answering (VQA)","dataset":"PMC-VQA","model":"BLIP-2","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"24.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G FlanT5 XXL (zero-shot)","rank_in_archive_order":42,"of":56,"metrics":{"Accuracy":"65"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":47,"of":56,"metrics":{"Accuracy":"63"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-L FlanT5 XL (zero-shot)","rank_in_archive_order":48,"of":56,"metrics":{"Accuracy":"62.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":50,"of":56,"metrics":{"Accuracy":"52.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":51,"of":56,"metrics":{"Accuracy":"52.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"BLIP-2 ViT-L OPT 2.7B (zero-shot)","rank_in_archive_order":54,"of":56,"metrics":{"Accuracy":"49.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-G FlanT5 XXL (zero-shot)","rank_in_archive_order":1,"of":11,"metrics":{"Accuracy":"65.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-G FlanT5 XL (zero-shot)","rank_in_archive_order":3,"of":11,"metrics":{"Accuracy":"63.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-L FlanT5 XL (zero-shot)","rank_in_archive_order":4,"of":11,"metrics":{"Accuracy":"62.6"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-G OPT 6.7B (zero-shot)","rank_in_archive_order":5,"of":11,"metrics":{"Accuracy":"54.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-G OPT 2.7B (zero-shot)","rank_in_archive_order":6,"of":11,"metrics":{"Accuracy":"53.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset":"VQA v2 val","model":"BLIP-2 ViT-L OPT 2.7B (zero-shot)","rank_in_archive_order":7,"of":11,"metrics":{"Accuracy":"50.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-instruction-following-on-llava-bench","task":"visual instruction following","dataset":"LLaVA-Bench","model":"BLIP-2","rank_in_archive_order":8,"of":8,"metrics":{"avg score":"38.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2301.12597","atlas_url":"https://app.syntology.ai/?focus=2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.12597"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.12597"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.12597\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2301.12597"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2301.12597\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2301.12597"},"call":"get_concepts_for_paper(arxiv_id=\"2301.12597\")"}],"by_repo":[{"repo":"salesforce/lavis","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2401.01827","2502.09507"],"harvested_for_calls":[{"arxiv_id":"2401.01827","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2401.01827"},"call":"get_harvested_code_for_paper(arxiv_id=\"2401.01827\")"},{"arxiv_id":"2502.09507","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.09507"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.09507\")"}]},{"repo":"albertotestoni/ndq_visual_objects","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2301.13823"],"harvested_for_calls":[{"arxiv_id":"2301.13823","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.13823"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.13823\")"}]},{"repo":"alibaba/graphtranslator","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2402.07197"],"harvested_for_calls":[{"arxiv_id":"2402.07197","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.07197"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.07197\")"}]},{"repo":"baaivision/eva","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2211.07636","2402.04252"],"harvested_for_calls":[{"arxiv_id":"2211.07636","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2211.07636"},"call":"get_harvested_code_for_paper(arxiv_id=\"2211.07636\")"},{"arxiv_id":"2402.04252","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.04252"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.04252\")"}]},{"repo":"facebookresearch/multimodal","kind":"listed","samples":3,"ran":3,"instrument":0,"unverified":0},{"repo":"gregor-ge/mblip","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2307.06930"],"harvested_for_calls":[{"arxiv_id":"2307.06930","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2307.06930"},"call":"get_harvested_code_for_paper(arxiv_id=\"2307.06930\")"}]},{"repo":"huggingface/transformers","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1706.03762","1910.03771","2006.03654","2010.01057"],"harvested_for_calls":[{"arxiv_id":"1706.03762","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.03762"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.03762\")"},{"arxiv_id":"1910.03771","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.03771"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.03771\")"},{"arxiv_id":"2006.03654","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.03654"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.03654\")"},{"arxiv_id":"2010.01057","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.01057"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.01057\")"}]},{"repo":"jiwanchung/vlis","kind":"listed","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"junshutang/Make-It-3D","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kdr/videorag-mrr2024","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"linzhiqiu/clip-flant5","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"rabiulcste/vqazero","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2306.09996"],"harvested_for_calls":[{"arxiv_id":"2306.09996","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.09996"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.09996\")"}]},{"repo":"thudm/visualglm-6b","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.12524"],"harvested_for_calls":[{"arxiv_id":"2305.12524","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.12524"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.12524\")"}]},{"repo":"unispac/visual-adversarial-examples-jailbreak-large-language-models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yukw777/videoblip","kind":"listed","samples":2,"ran":0,"instrument":0,"unverified":2},{"repo":"2024-MindSpore-1/Code2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"yangyucheng000/University","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2409.12191"],"harvested_for_calls":[{"arxiv_id":"2409.12191","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2409.12191"},"call":"get_harvested_code_for_paper(arxiv_id=\"2409.12191\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","assemblies":[{"assembly_sha256":"104619b3f46b0a48","source_kind":"harvested","method_name":"BLIP-2","realizes_method":"BLIP-2","graph_method":"BLIP-2","realizes_severed":false,"claim":"BLIP-2 is a pre-training strategy that bootstraps vision-language pre-training from frozen image encoders and frozen large language models (LLMs) using a Querying Transformer (Q-former) to bridge the modality gap.","centrality":"contribution","entry":"BLIP2","entry_sha256":"dbb9b4ef6b0f95dd","n_bricks":3,"bricks":[{"entry":"BLIP2","code_sha256":"dbb9b4ef6b0f95dd","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"Blip2Output","code_sha256":"b939479f3d2573b8","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"TransformerOutput","code_sha256":"e62bffe433f61ff1","role":"helper","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":3,"ran_individually_by_status":{"ran":3},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"1ff2f12e5c6a","n_siblings":3,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"177c9792f40beada","source_kind":"harvested","method_name":"BLIP-2","realizes_method":"BLIP-2","graph_method":"BLIP-2","realizes_severed":false,"claim":"BLIP-2 proposes a generic and efficient pre-training strategy that bootstraps vision-language pre-training from off-the-shelf frozen pre-trained image encoders and large language models.","centrality":"contribution","entry":"VideoBlipForConditionalGeneration","entry_sha256":"b67db6a1705fb783","n_bricks":2,"bricks":[{"entry":"VideoBlipForConditionalGeneration","code_sha256":"b67db6a1705fb783","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"VideoBlipVisionModel","code_sha256":"c4125cdecc4964aa","role":"helper","order":1,"level":0,"status":"unverified"}],"ran_individually":0,"ran_individually_constructed":0,"ran_individually_by_status":{},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"COMPONENT","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"cannot_tell","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"1ff2f12e5c6a","n_siblings":3,"retention":"defer","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"3996ca69f9f55c3e","source_kind":"harvested","method_name":"BLIP-2","realizes_method":"BLIP-2","graph_method":"BLIP-2","realizes_severed":false,"claim":"BLIP-2 is a generic and efficient pre-training strategy that bootstraps vision-language pre-training from off-the-shelf frozen pre-trained image encoders and large language models, specifically using a lightweight Querying Transformer (Q-Former) to bridge the modality gap.","centrality":"contribution","entry":"CLIPT5ForConditionalGeneration","entry_sha256":"11e6ad12cf0667b0","n_bricks":6,"bricks":[{"entry":"CLIPT5ForConditionalGeneration","code_sha256":"11e6ad12cf0667b0","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"CLIPT5Config","code_sha256":"196ad3b77304e23c","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"build_vision_projector","code_sha256":"ef4db0da176c674c","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"},{"entry":"build_vision_tower","code_sha256":"014050859277825c","role":"helper","order":3,"level":0,"status":"unverified"},{"entry":"IdentityMap","code_sha256":"9f0f5d62445adabe","role":"helper","order":4,"level":1,"status":"ran"},{"entry":"CLIPVisionTower","code_sha256":"6422a6162a5e6169","role":"model","order":5,"level":0,"status":"unverified"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"1ff2f12e5c6a","n_siblings":3,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"8ee48ca038641fe3","source_kind":"harvested","method_name":"BLIP-2","realizes_method":"BLIP-2","graph_method":"BLIP-2","realizes_severed":false,"claim":"BLIP-2 is a generic and efficient pre-training strategy that bootstraps vision-language pre-training from off-the-shelf frozen pre-trained image encoders and large language models.","centrality":"contribution","entry":"LynxBase","entry_sha256":"6e342d36cf541d23","n_bricks":2,"bricks":[{"entry":"LynxBase","code_sha256":"6e342d36cf541d23","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"disabled_train","code_sha256":"4cb732f513d69dfd","role":"helper","order":1,"level":1,"status":"ran_violates"}],"ran_individually":1,"ran_individually_constructed":0,"ran_individually_by_status":{"ran_violates":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"1ff2f12e5c6a","n_siblings":3,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"1ff2f12e5c6a","realizes_method":"BLIP-2","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["104619b3f46b0a48","177c9792f40beada","3996ca69f9f55c3e","8ee48ca038641fe3"]}],"assemblies_is":{"about":"What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists","bricks_level":"each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level","ran_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as \"by construction\" or \"not judged by a model\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"2301.12597"},"call":"assembly(arxiv_id=\"2301.12597\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2301.12597.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2301.12597.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salesforce/lavis","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yukw777/videoblip","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rabiulcste/vqazero","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/albertotestoni/ndq_visual_objects","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiwanchung/vlis","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gregor-ge/mblip","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baaivision/eva","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thudm/visualglm-6b","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/linzhiqiu/clip-flant5","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junshutang/Make-It-3D","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kdr/videorag-mrr2024","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba/graphtranslator","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/multimodal","reach":null}],"summary":{"ran":4,"unverified":4},"n_samples":8,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":8,"ran":4,"n_ran_checked":4,"n_instrument":0,"repositories":4}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"official_not_harvested":{"repositories":["salesforce/lavis"],"harvested_for_other_papers":[2],"samples_from_other_repositories":8,"other_repositories":4,"samples_unlocated":0},"n_pointer_only_for_licence":1,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":4,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-22","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"dbb9b4ef6b0f95dd","code_sha256_prefix":"dbb9b4ef6b0f95dd","entry":"BLIP2","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/blip2/blip2.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/blip2/blip2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"BLIP2","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"dbb9b4ef6b0f95dd"}},{"code_sha256":"b939479f3d2573b8","code_sha256_prefix":"b939479f3d2573b8","entry":"Blip2Output","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/blip2/blip2.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/blip2/blip2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"Blip2Output","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b939479f3d2573b8"}},{"code_sha256":"196ad3b77304e23c","code_sha256_prefix":"196ad3b77304e23c","entry":"CLIPT5Config","repo":"linzhiqiu/clip-flant5","repo_kind":"listed","path":"llava/model/language_model/clip_t5.py","file_url":"https://github.com/linzhiqiu/clip-flant5/blob/HEAD/llava/model/language_model/clip_t5.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"CLIPT5Config","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"196ad3b77304e23c"}},{"code_sha256":"e62bffe433f61ff1","code_sha256_prefix":"e62bffe433f61ff1","entry":"TransformerOutput","repo":"facebookresearch/multimodal","repo_kind":"listed","path":"torchmultimodal/models/blip2/blip2.py","file_url":"https://github.com/facebookresearch/multimodal/blob/HEAD/torchmultimodal/models/blip2/blip2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"TransformerOutput","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/transformeroutput","census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e62bffe433f61ff1"}},{"code_sha256":"11e6ad12cf0667b0","code_sha256_prefix":"11e6ad12cf0667b0","entry":"CLIPT5ForConditionalGeneration","repo":"linzhiqiu/clip-flant5","repo_kind":"listed","path":"llava/model/language_model/clip_t5.py","file_url":"https://github.com/linzhiqiu/clip-flant5/blob/HEAD/llava/model/language_model/clip_t5.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"11e6ad12cf0667b0"}},{"code_sha256":"6e342d36cf541d23","code_sha256_prefix":"6e342d36cf541d23","entry":"LynxBase","repo":"jiwanchung/vlis","repo_kind":"listed","path":"code/lynx/lynx_llm/models/lynx.py","file_url":"https://github.com/jiwanchung/vlis/blob/HEAD/code/lynx/lynx_llm/models/lynx.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jiwanchung/vlis when it was checked","mcp_get_code":{"code_sha256":"6e342d36cf541d23"}},{"code_sha256":"b67db6a1705fb783","code_sha256_prefix":"b67db6a1705fb783","entry":"VideoBlipForConditionalGeneration","repo":"yukw777/videoblip","repo_kind":"listed","path":"video_blip/model.py","file_url":"https://github.com/yukw777/videoblip/blob/HEAD/video_blip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b67db6a1705fb783"}},{"code_sha256":"c4125cdecc4964aa","code_sha256_prefix":"c4125cdecc4964aa","entry":"VideoBlipVisionModel","repo":"yukw777/videoblip","repo_kind":"listed","path":"video_blip/model.py","file_url":"https://github.com/yukw777/videoblip/blob/HEAD/video_blip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c4125cdecc4964aa"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f9b8d25aebf5b823f5a1e2a1cc52f55f0a92054437c58a45b49377a11bb37dde","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}