{"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":"/dataset/winoground","name":"Winoground","full_name":null,"description_markdown":"Winoground is a dataset for evaluating the ability of vision and language models to conduct visio-linguistic compositional reasoning. Given two images and two captions, the goal is to match them correctly -- but crucially, both captions contain a completely identical set of words, only in a different order. The dataset was carefully hand-curated by expert annotators and is labeled with a rich set of fine-grained tags to assist in analyzing model performance.","description_withheld":null,"homepage":"https://huggingface.co/datasets/facebook/winoground","introduced_date":"2022-04-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/winoground-probing-vision-and-language-models","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","first_author":"Tristan Thrush","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"},{"name":"Visual Reasoning","url":"/task/visual-reasoning","datasets_with_task":"/datasets/task/visual-reasoning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Winoground"],"data_loaders":[],"num_papers_in_archive":90,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-reasoning-on-winoground","task":"Visual Reasoning","dataset_variant":"Winoground","rows":114,"metrics":["Text Score","Image Score","Group Score"],"first_row_in_archive_order":{"model":"GPT-4o + CA","paper":"/paper/cognitive-paradigms-for-evaluating-vlms-on","metrics":{"Group Score":"52","Image Score":"58.5","Text Score":"75.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":19,"of":19,"counts":{"papers_with_a_benchmark_row":19,"with_a_code_link":12,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":19,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/cognitive-paradigms-for-evaluating-vlms-on","slug":"cognitive-paradigms-for-evaluating-vlms-on","title":"A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs","date":"2025-01-23","arxiv_id":"2501.13620","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/prompting-large-vision-language-models-for","slug":"prompting-large-vision-language-models-for","title":"Prompting Large Vision-Language Models for Compositional Reasoning","date":"2024-01-20","arxiv_id":"2401.11337","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["tossowski/keycomp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prompting-large-vision-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2401.11337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11337"}}}},{"paper":"/paper/cocot-contrastive-chain-of-thought-prompting","slug":"cocot-contrastive-chain-of-thought-prompting","title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","date":"2024-01-05","arxiv_id":"2401.02582","rows_on_this_dataset":13,"code_links":1,"syntology":null},{"paper":"/paper/compositional-chain-of-thought-prompting-for","slug":"compositional-chain-of-thought-prompting-for","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","date":"2023-11-27","arxiv_id":"2311.17076","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["chancharikmitra/ccot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/compositional-chain-of-thought-prompting-for#ran","syntology_url":"https://syntology.ai/paper/2311.17076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17076"}}}},{"paper":"/paper/selfeval-leveraging-the-discriminative-nature","slug":"selfeval-leveraging-the-discriminative-nature","title":"SelfEval: Leveraging the discriminative nature of generative models for evaluation","date":"2023-11-17","arxiv_id":"2311.10708","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/the-role-of-chain-of-thought-in-complex","slug":"the-role-of-chain-of-thought-in-complex","title":"The Role of Chain-of-Thought in Complex Vision-Language Reasoning Task","date":"2023-11-15","arxiv_id":"2311.09193","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mmicl-empowering-vision-language-model-with","slug":"mmicl-empowering-vision-language-model-with","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","date":"2023-09-14","arxiv_id":"2309.07915","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["haozhezhao/mic","pkunlp-icler/mic"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mmicl-empowering-vision-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2309.07915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07915"}}}},{"paper":"/paper/an-examination-of-the-compositionality-of","slug":"an-examination-of-the-compositionality-of","title":"An Examination of the Compositionality of Large Generative Vision-Language Models","date":"2023-08-21","arxiv_id":"2308.10509","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/visualgptscore-visio-linguistic-reasoning","slug":"visualgptscore-visio-linguistic-reasoning","title":"Revisiting the Role of Language Priors in Vision-Language Models","date":"2023-06-02","arxiv_id":"2306.01879","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/what-you-see-is-what-you-read-improving-text-1","slug":"what-you-see-is-what-you-read-improving-text-1","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","date":"2023-05-17","arxiv_id":"2305.10400","rows_on_this_dataset":8,"code_links":1,"syntology":null},{"paper":"/paper/measuring-progress-in-fine-grained-vision-and","slug":"measuring-progress-in-fine-grained-vision-and","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","date":"2023-05-12","arxiv_id":"2305.07558","rows_on_this_dataset":9,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}}}},{"paper":"/paper/simple-token-level-confidence-improves","slug":"simple-token-level-confidence-improves","title":"Simple Token-Level Confidence Improves Caption Correctness","date":"2023-05-11","arxiv_id":"2305.07021","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/incorporating-structured-representations-into","slug":"incorporating-structured-representations-into","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","date":"2023-05-10","arxiv_id":"2305.06343","rows_on_this_dataset":12,"code_links":0,"syntology":null},{"paper":"/paper/going-beyond-nouns-with-vision-language","slug":"going-beyond-nouns-with-vision-language","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","date":"2023-03-30","arxiv_id":"2303.17590","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/your-diffusion-model-is-secretly-a-zero-shot","slug":"your-diffusion-model-is-secretly-a-zero-shot","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","date":"2023-03-28","arxiv_id":"2303.16203","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["diffusion-classifier/diffusion-classifier"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/your-diffusion-model-is-secretly-a-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2303.16203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16203"}}}},{"paper":"/paper/equivariant-similarity-for-vision-language","slug":"equivariant-similarity-for-vision-language","title":"Equivariant Similarity for Vision-Language Foundation Models","date":"2023-03-25","arxiv_id":"2303.14465","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["wangt-cn/eqben"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/equivariant-similarity-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.14465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14465"}}}},{"paper":"/paper/vilem-visual-language-error-modeling-for","slug":"vilem-visual-language-error-modeling-for","title":"ViLEM: Visual-Language Error Modeling for Image-Text Retrieval","date":"2023-01-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/does-structural-attention-improve","slug":"does-structural-attention-improve","title":"Does Structural Attention Improve Compositional Representations in Vision-Language Models?","date":"2022-12-03","arxiv_id":null,"rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/winoground-probing-vision-and-language-models","slug":"winoground-probing-vision-and-language-models","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","date":"2022-04-07","arxiv_id":"2204.03162","rows_on_this_dataset":20,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/cognitive-paradigms-for-evaluating-vlms-on","slug":"cognitive-paradigms-for-evaluating-vlms-on","title":"A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs","date":"2025-01-23","arxiv_id":"2501.13620","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/prompting-large-vision-language-models-for","slug":"prompting-large-vision-language-models-for","title":"Prompting Large Vision-Language Models for Compositional Reasoning","date":"2024-01-20","arxiv_id":"2401.11337","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["tossowski/keycomp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prompting-large-vision-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2401.11337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11337"}}}},{"paper":"/paper/cocot-contrastive-chain-of-thought-prompting","slug":"cocot-contrastive-chain-of-thought-prompting","title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","date":"2024-01-05","arxiv_id":"2401.02582","rows_on_this_dataset":13,"code_links":1,"syntology":null},{"paper":"/paper/compositional-chain-of-thought-prompting-for","slug":"compositional-chain-of-thought-prompting-for","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","date":"2023-11-27","arxiv_id":"2311.17076","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["chancharikmitra/ccot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/compositional-chain-of-thought-prompting-for#ran","syntology_url":"https://syntology.ai/paper/2311.17076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17076"}}}},{"paper":"/paper/selfeval-leveraging-the-discriminative-nature","slug":"selfeval-leveraging-the-discriminative-nature","title":"SelfEval: Leveraging the discriminative nature of generative models for evaluation","date":"2023-11-17","arxiv_id":"2311.10708","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/the-role-of-chain-of-thought-in-complex","slug":"the-role-of-chain-of-thought-in-complex","title":"The Role of Chain-of-Thought in Complex Vision-Language Reasoning Task","date":"2023-11-15","arxiv_id":"2311.09193","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mmicl-empowering-vision-language-model-with","slug":"mmicl-empowering-vision-language-model-with","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","date":"2023-09-14","arxiv_id":"2309.07915","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["haozhezhao/mic","pkunlp-icler/mic"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mmicl-empowering-vision-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2309.07915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07915"}}}},{"paper":"/paper/an-examination-of-the-compositionality-of","slug":"an-examination-of-the-compositionality-of","title":"An Examination of the Compositionality of Large Generative Vision-Language Models","date":"2023-08-21","arxiv_id":"2308.10509","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/visualgptscore-visio-linguistic-reasoning","slug":"visualgptscore-visio-linguistic-reasoning","title":"Revisiting the Role of Language Priors in Vision-Language Models","date":"2023-06-02","arxiv_id":"2306.01879","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/what-you-see-is-what-you-read-improving-text-1","slug":"what-you-see-is-what-you-read-improving-text-1","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","date":"2023-05-17","arxiv_id":"2305.10400","rows_on_this_dataset":8,"code_links":1,"syntology":null},{"paper":"/paper/measuring-progress-in-fine-grained-vision-and","slug":"measuring-progress-in-fine-grained-vision-and","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","date":"2023-05-12","arxiv_id":"2305.07558","rows_on_this_dataset":9,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}}}},{"paper":"/paper/simple-token-level-confidence-improves","slug":"simple-token-level-confidence-improves","title":"Simple Token-Level Confidence Improves Caption Correctness","date":"2023-05-11","arxiv_id":"2305.07021","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/incorporating-structured-representations-into","slug":"incorporating-structured-representations-into","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","date":"2023-05-10","arxiv_id":"2305.06343","rows_on_this_dataset":12,"code_links":0,"syntology":null},{"paper":"/paper/going-beyond-nouns-with-vision-language","slug":"going-beyond-nouns-with-vision-language","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","date":"2023-03-30","arxiv_id":"2303.17590","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/your-diffusion-model-is-secretly-a-zero-shot","slug":"your-diffusion-model-is-secretly-a-zero-shot","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","date":"2023-03-28","arxiv_id":"2303.16203","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["diffusion-classifier/diffusion-classifier"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/your-diffusion-model-is-secretly-a-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2303.16203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16203"}}}},{"paper":"/paper/equivariant-similarity-for-vision-language","slug":"equivariant-similarity-for-vision-language","title":"Equivariant Similarity for Vision-Language Foundation Models","date":"2023-03-25","arxiv_id":"2303.14465","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["wangt-cn/eqben"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/equivariant-similarity-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.14465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14465"}}}},{"paper":"/paper/vilem-visual-language-error-modeling-for","slug":"vilem-visual-language-error-modeling-for","title":"ViLEM: Visual-Language Error Modeling for Image-Text Retrieval","date":"2023-01-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/does-structural-attention-improve","slug":"does-structural-attention-improve","title":"Does Structural Attention Improve Compositional Representations in Vision-Language Models?","date":"2022-12-03","arxiv_id":null,"rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/winoground-probing-vision-and-language-models","slug":"winoground-probing-vision-and-language-models","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","date":"2022-04-07","arxiv_id":"2204.03162","rows_on_this_dataset":20,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}}],"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/dataset/winoground/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/winoground/papers/ran/1","json":"/dataset/winoground/papers/ran/1.json","rows":7}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":7,"samples_harvested":24,"samples_ran":20,"samples_constructed":1,"samples_ran_checked":10,"samples_ran_instrument_failed":10,"samples_unverified":4,"pointer_only_for_licence":15,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":7,"papers_with_a_run_with_no_instrument_failure":6,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"f1af7147f72fb385a179969a155d7c177baff4f9526b6a90144692c8f5c636eb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}