{"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":"/task/visual-question-answering-1/papers/ran/4","list_of":"/task/visual-question-answering-1","task":"Visual Question Answering","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":4,"pages_in_order":4,"rows_per_page":100,"rows":[301,378],"of":378,"counts":{"archive_papers_tagged":2177,"with_a_code_link":1042,"where_syntology_ran_a_sample":378,"not_listed_spam_title":0,"listed":2177,"listed_where_code_ran":378,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":308,"every_run_a_failure_of_syntologys_instrument":70,"listed_with_a_run_with_no_instrument_failure":308,"listed_every_run_a_failure_of_syntologys_instrument":70,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/visual-question-answering-1/papers/ran/1","prev":"/task/visual-question-answering-1/papers/ran/3","next":null,"papers":[{"url":"/paper/an-empirical-study-of-gpt-3-for-few-shot","slug":"an-empirical-study-of-gpt-3-for-few-shot","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","date":"2021-09-10","arxiv_id":"2109.05014","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/an-empirical-study-of-gpt-3-for-few-shot#ran","syntology_url":"https://syntology.ai/paper/2109.05014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05014"}},"official":{"repos":["microsoft/PICa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/weakly-supervised-visual-retriever-reader-for","slug":"weakly-supervised-visual-retriever-reader-for","title":"Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering","date":"2021-09-09","arxiv_id":"2109.04014","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/weakly-supervised-visual-retriever-reader-for#ran","syntology_url":"https://syntology.ai/paper/2109.04014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04014"}},"official":{"repos":["luomancs/retriever_reader_for_okvqa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/webqa-multihop-and-multimodal-qa","slug":"webqa-multihop-and-multimodal-qa","title":"WebQA: Multihop and Multimodal QA","date":"2021-09-01","arxiv_id":"2109.00590","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/webqa-multihop-and-multimodal-qa#ran","syntology_url":"https://syntology.ai/paper/2109.00590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00590"}},"official":null}},{"url":"/paper/simvlm-simple-visual-language-model","slug":"simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","date":"2021-08-24","arxiv_id":"2108.10904","repositories_listed":2,"syntology":{"n":37,"n_ran":22,"n_constructed":8,"n_ran_checked":16,"n_instrument":6,"n_unverified":15,"n_honours":1,"n_violates":3,"n_no_contract":12,"n_pointer_only":32,"phrase":"22 ran (of which 8 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 3 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/simvlm-simple-visual-language-model#ran","syntology_url":"https://syntology.ai/paper/2108.10904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10904"}},"official":null}},{"url":"/paper/sparse-continuous-distributions-and-fenchel","slug":"sparse-continuous-distributions-and-fenchel","title":"Sparse Continuous Distributions and Fenchel-Young Losses","date":"2021-08-04","arxiv_id":"2108.01988","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sparse-continuous-distributions-and-fenchel#ran","syntology_url":"https://syntology.ai/paper/2108.01988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.01988"}},"official":{"repos":["deep-spin/sparse_continuous_distributions"],"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":["official"]}}},{"url":"/paper/greedy-gradient-ensemble-for-robust-visual","slug":"greedy-gradient-ensemble-for-robust-visual","title":"Greedy Gradient Ensemble for Robust Visual Question Answering","date":"2021-07-27","arxiv_id":"2107.12651","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/greedy-gradient-ensemble-for-robust-visual#ran","syntology_url":"https://syntology.ai/paper/2107.12651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12651"}},"official":{"repos":["GeraldHan/GGE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/separating-skills-and-concepts-for-novel-1","slug":"separating-skills-and-concepts-for-novel-1","title":"Separating Skills and Concepts for Novel Visual Question Answering","date":"2021-07-19","arxiv_id":"2107.09106","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/separating-skills-and-concepts-for-novel-1#ran","syntology_url":"https://syntology.ai/paper/2107.09106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09106"}},"official":{"repos":["SpencerWhitehead/novelvqa"],"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"]}}},{"url":"/paper/how-much-can-clip-benefit-vision-and-language","slug":"how-much-can-clip-benefit-vision-and-language","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","date":"2021-07-13","arxiv_id":"2107.06383","repositories_listed":4,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/how-much-can-clip-benefit-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2107.06383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06383"}},"official":{"repos":["clip-vil/CLIP-ViL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/mind-your-outliers-investigating-the-negative","slug":"mind-your-outliers-investigating-the-negative","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","date":"2021-07-06","arxiv_id":"2107.02331","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mind-your-outliers-investigating-the-negative#ran","syntology_url":"https://syntology.ai/paper/2107.02331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02331"}},"official":{"repos":["siddk/vqa-outliers"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/naaqa-a-neural-architecture-for-acoustic","slug":"naaqa-a-neural-architecture-for-acoustic","title":"NAAQA: A Neural Architecture for Acoustic Question Answering","date":"2021-06-11","arxiv_id":"2106.06147","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/naaqa-a-neural-architecture-for-acoustic#ran","syntology_url":"https://syntology.ai/paper/2106.06147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06147"}},"official":null}},{"url":"/paper/multi-modal-understanding-and-generation-for","slug":"multi-modal-understanding-and-generation-for","title":"Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training","date":"2021-05-24","arxiv_id":"2105.11333","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-modal-understanding-and-generation-for#ran","syntology_url":"https://syntology.ai/paper/2105.11333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11333"}},"official":{"repos":["SuperSupermoon/MedViLL"],"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"]}}},{"url":"/paper/multiple-meta-model-quantifying-for-medical","slug":"multiple-meta-model-quantifying-for-medical","title":"Multiple Meta-model Quantifying for Medical Visual Question Answering","date":"2021-05-19","arxiv_id":"2105.08913","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":3,"n_no_contract":4,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 3 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multiple-meta-model-quantifying-for-medical#ran","syntology_url":"https://syntology.ai/paper/2105.08913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08913"}},"official":{"repos":["aioz-ai/MICCAI21_MMQ"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/passage-retrieval-for-outside-knowledge","slug":"passage-retrieval-for-outside-knowledge","title":"Passage Retrieval for Outside-Knowledge Visual Question Answering","date":"2021-05-09","arxiv_id":"2105.03938","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/passage-retrieval-for-outside-knowledge#ran","syntology_url":"https://syntology.ai/paper/2105.03938","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03938"}},"official":{"repos":["prdwb/okvqa-release"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mdetr-modulated-detection-for-end-to-end","slug":"mdetr-modulated-detection-for-end-to-end","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","date":"2021-04-26","arxiv_id":"2104.12763","repositories_listed":5,"syntology":{"n":11,"n_ran":7,"n_constructed":4,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mdetr-modulated-detection-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2104.12763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.12763"}},"official":{"repos":["ashkamath/mdetr"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/beyond-question-based-biases-assessing","slug":"beyond-question-based-biases-assessing","title":"Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering","date":"2021-04-07","arxiv_id":"2104.03149","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/beyond-question-based-biases-assessing#ran","syntology_url":"https://syntology.ai/paper/2104.03149","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03149"}},"official":{"repos":["cdancette/detect-shortcuts"],"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"]}}},{"url":"/paper/an-investigation-of-critical-issues-in-bias","slug":"an-investigation-of-critical-issues-in-bias","title":"Are Bias Mitigation Techniques for Deep Learning Effective?","date":"2021-04-01","arxiv_id":"2104.00170","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/an-investigation-of-critical-issues-in-bias#ran","syntology_url":"https://syntology.ai/paper/2104.00170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00170"}},"official":{"repos":["erobic/bias-mitigators"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-general-purpose-vision-systems","slug":"towards-general-purpose-vision-systems","title":"Towards General Purpose Vision Systems","date":"2021-04-01","arxiv_id":"2104.00743","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-general-purpose-vision-systems#ran","syntology_url":"https://syntology.ai/paper/2104.00743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00743"}},"official":{"repos":["allenai/gpv-1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/generic-attention-model-explainability-for","slug":"generic-attention-model-explainability-for","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","date":"2021-03-29","arxiv_id":"2103.15679","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generic-attention-model-explainability-for#ran","syntology_url":"https://syntology.ai/paper/2103.15679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15679"}},"official":{"repos":["hila-chefer/Transformer-MM-Explainability"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-generation-of-contrast-sets-from","slug":"automatic-generation-of-contrast-sets-from","title":"Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA","date":"2021-03-17","arxiv_id":"2103.09591","repositories_listed":2,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/automatic-generation-of-contrast-sets-from#ran","syntology_url":"https://syntology.ai/paper/2103.09591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.09591"}},"official":{"repos":["yonatanbitton/AutoGenOfContrastSetsFromSceneGraphs"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/unifying-vision-and-language-tasks-via-text","slug":"unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","repositories_listed":2,"syntology":{"n":12,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/unifying-vision-and-language-tasks-via-text#ran","syntology_url":"https://syntology.ai/paper/2102.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02779"}},"official":{"repos":["j-min/VL-T5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/overcoming-language-priors-with-self","slug":"overcoming-language-priors-with-self","title":"Overcoming Language Priors with Self-supervised Learning for Visual Question Answering","date":"2020-12-17","arxiv_id":"2012.11528","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":3,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/overcoming-language-priors-with-self#ran","syntology_url":"https://syntology.ai/paper/2012.11528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.11528"}},"official":{"repos":["CrossmodalGroup/SSL-VQA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-model-and-ignore-dataset-bias","slug":"learning-to-model-and-ignore-dataset-bias","title":"Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles","date":"2020-11-07","arxiv_id":"2011.03856","repositories_listed":1,"syntology":{"n":18,"n_ran":10,"n_constructed":5,"n_ran_checked":8,"n_instrument":2,"n_unverified":8,"n_honours":2,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"10 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/learning-to-model-and-ignore-dataset-bias#ran","syntology_url":"https://syntology.ai/paper/2011.03856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.03856"}},"official":{"repos":["chrisc36/autobias"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":5,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/loss-rescaling-vqa-revisiting-language-prior","slug":"loss-rescaling-vqa-revisiting-language-prior","title":"Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View","date":"2020-10-30","arxiv_id":"2010.16010","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/loss-rescaling-vqa-revisiting-language-prior#ran","syntology_url":"https://syntology.ai/paper/2010.16010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.16010"}},"official":{"repos":["guoyang9/class-imbalance-VQA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sort-ing-vqa-models-contrastive-gradient","slug":"sort-ing-vqa-models-contrastive-gradient","title":"SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency","date":"2020-10-20","arxiv_id":"2010.10038","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sort-ing-vqa-models-contrastive-gradient#ran","syntology_url":"https://syntology.ai/paper/2010.10038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10038"}},"official":{"repos":["sameerdharur/sorting-vqa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/x-lxmert-paint-caption-and-answer-questions","slug":"x-lxmert-paint-caption-and-answer-questions","title":"X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers","date":"2020-09-23","arxiv_id":"2009.11278","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/x-lxmert-paint-caption-and-answer-questions#ran","syntology_url":"https://syntology.ai/paper/2009.11278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.11278"}},"official":{"repos":["allenai/x-lxmert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/docvqa-a-dataset-for-vqa-on-document-images","slug":"docvqa-a-dataset-for-vqa-on-document-images","title":"DocVQA: A Dataset for VQA on Document Images","date":"2020-07-01","arxiv_id":"2007.00398","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/docvqa-a-dataset-for-vqa-on-document-images#ran","syntology_url":"https://syntology.ai/paper/2007.00398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00398"}},"official":null}},{"url":"/paper/graph-optimal-transport-for-cross-domain","slug":"graph-optimal-transport-for-cross-domain","title":"Graph Optimal Transport for Cross-Domain Alignment","date":"2020-06-26","arxiv_id":"2006.14744","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":6,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/graph-optimal-transport-for-cross-domain#ran","syntology_url":"https://syntology.ai/paper/2006.14744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.14744"}},"official":{"repos":["LiqunChen0606/Graph-Optimal-Transport"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/neuro-symbolic-visual-reasoning-disentangling","slug":"neuro-symbolic-visual-reasoning-disentangling","title":"Neuro-Symbolic Visual Reasoning: Disentangling \"Visual\" from \"Reasoning\"","date":"2020-06-20","arxiv_id":"2006.11524","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neuro-symbolic-visual-reasoning-disentangling#ran","syntology_url":"https://syntology.ai/paper/2006.11524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11524"}},"official":null}},{"url":"/paper/sparse-and-continuous-attention-mechanisms","slug":"sparse-and-continuous-attention-mechanisms","title":"Sparse and Continuous Attention Mechanisms","date":"2020-06-12","arxiv_id":"2006.07214","repositories_listed":2,"syntology":{"n":15,"n_ran":12,"n_constructed":9,"n_ran_checked":9,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"12 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sparse-and-continuous-attention-mechanisms#ran","syntology_url":"https://syntology.ai/paper/2006.07214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07214"}},"official":{"repos":["deep-spin/mcan-vqa-continuous-attention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"url":"/paper/large-scale-adversarial-training-for-vision","slug":"large-scale-adversarial-training-for-vision","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","date":"2020-06-11","arxiv_id":"2006.06195","repositories_listed":2,"syntology":{"n":20,"n_ran":12,"n_constructed":5,"n_ran_checked":9,"n_instrument":3,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/large-scale-adversarial-training-for-vision#ran","syntology_url":"https://syntology.ai/paper/2006.06195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06195"}},"official":{"repos":["zhegan27/LXMERT-AdvTrain","zhegan27/VILLA"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/closed-loop-neural-symbolic-learning-via","slug":"closed-loop-neural-symbolic-learning-via","title":"Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning","date":"2020-06-11","arxiv_id":"2006.06649","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/closed-loop-neural-symbolic-learning-via#ran","syntology_url":"https://syntology.ai/paper/2006.06649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06649"}},"official":{"repos":["liqing-ustc/NGS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cobra-contrastive-bi-modal-representation","slug":"cobra-contrastive-bi-modal-representation","title":"COBRA: Contrastive Bi-Modal Representation Algorithm","date":"2020-05-07","arxiv_id":"2005.03687","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cobra-contrastive-bi-modal-representation#ran","syntology_url":"https://syntology.ai/paper/2005.03687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.03687"}},"official":{"repos":["ovshake/cobra"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dynamic-language-binding-in-relational-visual","slug":"dynamic-language-binding-in-relational-visual","title":"Dynamic Language Binding in Relational Visual Reasoning","date":"2020-04-30","arxiv_id":"2004.14603","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":5,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dynamic-language-binding-in-relational-visual#ran","syntology_url":"https://syntology.ai/paper/2004.14603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14603"}},"official":null}},{"url":"/paper/pragmatic-issue-sensitive-image-captioning","slug":"pragmatic-issue-sensitive-image-captioning","title":"Pragmatic Issue-Sensitive Image Captioning","date":"2020-04-29","arxiv_id":"2004.14451","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pragmatic-issue-sensitive-image-captioning#ran","syntology_url":"https://syntology.ai/paper/2004.14451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14451"}},"official":{"repos":["windweller/Pragmatic-ISIC"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/a-negative-case-analysis-of-visual-grounding","slug":"a-negative-case-analysis-of-visual-grounding","title":"Visual Grounding Methods for VQA are Working for the Wrong Reasons!","date":"2020-04-12","arxiv_id":"2004.05704","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-negative-case-analysis-of-visual-grounding#ran","syntology_url":"https://syntology.ai/paper/2004.05704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.05704"}},"official":{"repos":["erobic/negative_analysis_of_grounding"],"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"]}}},{"url":"/paper/towards-ground-truth-evaluation-of-visual","slug":"towards-ground-truth-evaluation-of-visual","title":"Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI","date":"2020-03-16","arxiv_id":"2003.07258","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-ground-truth-evaluation-of-visual#ran","syntology_url":"https://syntology.ai/paper/2003.07258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07258"}},"official":{"repos":["ahmedmagdiosman/clevr-xai","ahmedmagdiosman/simply-clevr-dataset"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-samples-synthesizing-for","slug":"counterfactual-samples-synthesizing-for","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","date":"2020-03-14","arxiv_id":"2003.06576","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/counterfactual-samples-synthesizing-for#ran","syntology_url":"https://syntology.ai/paper/2003.06576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06576"}},"official":{"repos":["yanxinzju/CSS-VQA"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/pathvqa-30000-questions-for-medical-visual","slug":"pathvqa-30000-questions-for-medical-visual","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","date":"2020-03-07","arxiv_id":"2003.10286","repositories_listed":5,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pathvqa-30000-questions-for-medical-visual#ran","syntology_url":"https://syntology.ai/paper/2003.10286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10286"}},"official":null}},{"url":"/paper/12-in-1-multi-task-vision-and-language","slug":"12-in-1-multi-task-vision-and-language","title":"12-in-1: Multi-Task Vision and Language Representation Learning","date":"2019-12-05","arxiv_id":"1912.02315","repositories_listed":5,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":13,"n_instrument":2,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":20,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/12-in-1-multi-task-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/1912.02315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02315"}},"official":{"repos":["facebookresearch/vilbert-multi-task"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/large-scale-pretraining-for-visual-dialog-a","slug":"large-scale-pretraining-for-visual-dialog-a","title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline","date":"2019-12-05","arxiv_id":"1912.02379","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/large-scale-pretraining-for-visual-dialog-a#ran","syntology_url":"https://syntology.ai/paper/1912.02379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02379"}},"official":{"repos":["vmurahari3/visdial-bert"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/remind-your-neural-network-to-prevent","slug":"remind-your-neural-network-to-prevent","title":"REMIND Your Neural Network to Prevent Catastrophic Forgetting","date":"2019-10-06","arxiv_id":"1910.02509","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/remind-your-neural-network-to-prevent#ran","syntology_url":"https://syntology.ai/paper/1910.02509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.02509"}},"official":{"repos":["tyler-hayes/REMIND"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/compact-trilinear-interaction-for-visual","slug":"compact-trilinear-interaction-for-visual","title":"Compact Trilinear Interaction for Visual Question Answering","date":"2019-09-26","arxiv_id":"1909.11874","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/compact-trilinear-interaction-for-visual#ran","syntology_url":"https://syntology.ai/paper/1909.11874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11874"}},"official":{"repos":["aioz-ai/ICCV19_VQA-CTI"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}},"official":{"repos":["ChenRocks/UNITER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","repositories_listed":3,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unified-vision-language-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/1909.11059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11059"}},"official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/dont-take-the-easy-way-out-ensemble-based","slug":"dont-take-the-easy-way-out-ensemble-based","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","date":"2019-09-09","arxiv_id":"1909.03683","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dont-take-the-easy-way-out-ensemble-based#ran","syntology_url":"https://syntology.ai/paper/1909.03683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03683"}},"official":{"repos":["chrisc36/debias"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/vl-bert-pre-training-of-generic-visual","slug":"vl-bert-pre-training-of-generic-visual","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","date":"2019-08-22","arxiv_id":"1908.08530","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vl-bert-pre-training-of-generic-visual#ran","syntology_url":"https://syntology.ai/paper/1908.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08530"}},"official":{"repos":["jackroos/VL-BERT"],"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":["official"]}}},{"url":"/paper/lxmert-learning-cross-modality-encoder","slug":"lxmert-learning-cross-modality-encoder","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","date":"2019-08-20","arxiv_id":"1908.07490","repositories_listed":9,"syntology":{"n":15,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/lxmert-learning-cross-modality-encoder#ran","syntology_url":"https://syntology.ai/paper/1908.07490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07490"}},"official":{"repos":["airsplay/lxmert"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/vilbert-pretraining-task-agnostic","slug":"vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","arxiv_id":"1908.02265","repositories_listed":11,"syntology":{"n":34,"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":24,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":34,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 24 unverified","sample_list":"/paper/vilbert-pretraining-task-agnostic#ran","syntology_url":"https://syntology.ai/paper/1908.02265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02265"}},"official":null}},{"url":"/paper/deep-modular-co-attention-networks-for-visual-1","slug":"deep-modular-co-attention-networks-for-visual-1","title":"Deep Modular Co-Attention Networks for Visual Question Answering","date":"2019-06-25","arxiv_id":"1906.10770","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-modular-co-attention-networks-for-visual-1#ran","syntology_url":"https://syntology.ai/paper/1906.10770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10770"}},"official":{"repos":["MILVLG/mcan-vqa"],"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":["official"]}}},{"url":"/paper/adversarial-regularization-for-visual","slug":"adversarial-regularization-for-visual","title":"Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects","date":"2019-06-20","arxiv_id":"1906.08430","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-regularization-for-visual#ran","syntology_url":"https://syntology.ai/paper/1906.08430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08430"}},"official":{"repos":["gabegrand/adversarial-vqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/routing-networks-and-the-challenges-of","slug":"routing-networks-and-the-challenges-of","title":"Routing Networks and the Challenges of Modular and Compositional Computation","date":"2019-04-29","arxiv_id":"1904.12774","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/routing-networks-and-the-challenges-of#ran","syntology_url":"https://syntology.ai/paper/1904.12774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12774"}},"official":null}},{"url":"/paper/the-neuro-symbolic-concept-learner-1","slug":"the-neuro-symbolic-concept-learner-1","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","date":"2019-04-26","arxiv_id":"1904.12584","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-neuro-symbolic-concept-learner-1#ran","syntology_url":"https://syntology.ai/paper/1904.12584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12584"}},"official":{"repos":["vacancy/NSCL-PyTorch-Release"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/scene-graph-prediction-with-limited-labels","slug":"scene-graph-prediction-with-limited-labels","title":"Scene Graph Prediction with Limited Labels","date":"2019-04-25","arxiv_id":"1904.11622","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scene-graph-prediction-with-limited-labels#ran","syntology_url":"https://syntology.ai/paper/1904.11622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11622"}},"official":null}},{"url":"/paper/relation-aware-graph-attention-network-for","slug":"relation-aware-graph-attention-network-for","title":"Relation-Aware Graph Attention Network for Visual Question Answering","date":"2019-03-29","arxiv_id":"1903.12314","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/relation-aware-graph-attention-network-for#ran","syntology_url":"https://syntology.ai/paper/1903.12314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.12314"}},"official":{"repos":["linjieli222/VQA_ReGAT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dual-attention-networks-for-visual-reference","slug":"dual-attention-networks-for-visual-reference","title":"Dual Attention Networks for Visual Reference Resolution in Visual Dialog","date":"2019-02-25","arxiv_id":"1902.09368","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dual-attention-networks-for-visual-reference#ran","syntology_url":"https://syntology.ai/paper/1902.09368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09368"}},"official":{"repos":["gicheonkang/DAN-VisDial"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/block-bilinear-superdiagonal-fusion-for","slug":"block-bilinear-superdiagonal-fusion-for","title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","date":"2019-01-31","arxiv_id":"1902.00038","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/block-bilinear-superdiagonal-fusion-for#ran","syntology_url":"https://syntology.ai/paper/1902.00038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.00038"}},"official":{"repos":["Cadene/block.bootstrap.pytorch"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/clevr-ref-diagnosing-visual-reasoning-with","slug":"clevr-ref-diagnosing-visual-reasoning-with","title":"CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions","date":"2019-01-03","arxiv_id":"1901.00850","repositories_listed":3,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clevr-ref-diagnosing-visual-reasoning-with#ran","syntology_url":"https://syntology.ai/paper/1901.00850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.00850"}},"official":null}},{"url":"/paper/learning-representations-of-sets-through","slug":"learning-representations-of-sets-through","title":"Learning Representations of Sets through Optimized Permutations","date":"2018-12-10","arxiv_id":"1812.03928","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-representations-of-sets-through#ran","syntology_url":"https://syntology.ai/paper/1812.03928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03928"}},"official":{"repos":["Cyanogenoid/perm-optim","iclr2019-anon123456/perm-optim"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-symbolic-vqa-disentangling-reasoning","slug":"neural-symbolic-vqa-disentangling-reasoning","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","date":"2018-10-04","arxiv_id":"1810.02338","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-symbolic-vqa-disentangling-reasoning#ran","syntology_url":"https://syntology.ai/paper/1810.02338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.02338"}},"official":null}},{"url":"/paper/latent-alignment-and-variational-attention","slug":"latent-alignment-and-variational-attention","title":"Latent Alignment and Variational Attention","date":"2018-07-10","arxiv_id":"1807.03756","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/latent-alignment-and-variational-attention#ran","syntology_url":"https://syntology.ai/paper/1807.03756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03756"}},"official":{"repos":["harvardnlp/var-attn"],"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"]}}},{"url":"/paper/end-to-end-audio-visual-scene-aware-dialog","slug":"end-to-end-audio-visual-scene-aware-dialog","title":"End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features","date":"2018-06-21","arxiv_id":"1806.08409","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/end-to-end-audio-visual-scene-aware-dialog#ran","syntology_url":"https://syntology.ai/paper/1806.08409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.08409"}},"official":null}},{"url":"/paper/learning-conditioned-graph-structures-for","slug":"learning-conditioned-graph-structures-for","title":"Learning Conditioned Graph Structures for Interpretable Visual Question Answering","date":"2018-06-19","arxiv_id":"1806.07243","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-conditioned-graph-structures-for#ran","syntology_url":"https://syntology.ai/paper/1806.07243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.07243"}},"official":{"repos":["aimbrain/vqa-project"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bilinear-attention-networks","slug":"bilinear-attention-networks","title":"Bilinear Attention Networks","date":"2018-05-21","arxiv_id":"1805.07932","repositories_listed":8,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":3,"n_no_contract":9,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 3 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bilinear-attention-networks#ran","syntology_url":"https://syntology.ai/paper/1805.07932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07932"}},"official":{"repos":["jnhwkim/ban-vqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/did-the-model-understand-the-question","slug":"did-the-model-understand-the-question","title":"Did the Model Understand the Question?","date":"2018-05-14","arxiv_id":"1805.05492","repositories_listed":4,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/did-the-model-understand-the-question#ran","syntology_url":"https://syntology.ai/paper/1805.05492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.05492"}},"official":{"repos":["pramodkaushik/acl18_results"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/transparency-by-design-closing-the-gap","slug":"transparency-by-design-closing-the-gap","title":"Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning","date":"2018-03-14","arxiv_id":"1803.05268","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/transparency-by-design-closing-the-gap#ran","syntology_url":"https://syntology.ai/paper/1803.05268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.05268"}},"official":{"repos":["davidmascharka/tbd-nets"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-explanations-justifying-decisions","slug":"multimodal-explanations-justifying-decisions","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","date":"2018-02-15","arxiv_id":"1802.08129","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multimodal-explanations-justifying-decisions#ran","syntology_url":"https://syntology.ai/paper/1802.08129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.08129"}},"official":{"repos":["Seth-Park/MultimodalExplanations"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ai2-thor-an-interactive-3d-environment-for","slug":"ai2-thor-an-interactive-3d-environment-for","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","date":"2017-12-14","arxiv_id":"1712.05474","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ai2-thor-an-interactive-3d-environment-for#ran","syntology_url":"https://syntology.ai/paper/1712.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.05474"}},"official":{"repos":["allenai/ai2thor"],"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":["official"]}}},{"url":"/paper/bottom-up-and-top-down-attention-for-image","slug":"bottom-up-and-top-down-attention-for-image","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","date":"2017-07-25","arxiv_id":"1707.07998","repositories_listed":65,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":1,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bottom-up-and-top-down-attention-for-image#ran","syntology_url":"https://syntology.ai/paper/1707.07998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.07998"}},"official":{"repos":["peteanderson80/bottom-up-attention"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/a-simple-neural-network-module-for-relational","slug":"a-simple-neural-network-module-for-relational","title":"A simple neural network module for relational reasoning","date":"2017-06-05","arxiv_id":"1706.01427","repositories_listed":20,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/a-simple-neural-network-module-for-relational#ran","syntology_url":"https://syntology.ai/paper/1706.01427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.01427"}},"official":null}},{"url":"/paper/show-ask-attend-and-answer-a-strong-baseline","slug":"show-ask-attend-and-answer-a-strong-baseline","title":"Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question Answering","date":"2017-04-11","arxiv_id":"1704.03162","repositories_listed":13,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":2,"n_instrument":7,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/show-ask-attend-and-answer-a-strong-baseline#ran","syntology_url":"https://syntology.ai/paper/1704.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.03162"}},"official":null}},{"url":"/paper/learning-cooperative-visual-dialog-agents","slug":"learning-cooperative-visual-dialog-agents","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","date":"2017-03-20","arxiv_id":"1703.06585","repositories_listed":7,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-cooperative-visual-dialog-agents#ran","syntology_url":"https://syntology.ai/paper/1703.06585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06585"}},"official":null}},{"url":"/paper/clevr-a-diagnostic-dataset-for-compositional","slug":"clevr-a-diagnostic-dataset-for-compositional","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","date":"2016-12-20","arxiv_id":"1612.06890","repositories_listed":5,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/clevr-a-diagnostic-dataset-for-compositional#ran","syntology_url":"https://syntology.ai/paper/1612.06890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.06890"}},"official":null}},{"url":"/paper/grad-cam-visual-explanations-from-deep","slug":"grad-cam-visual-explanations-from-deep","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","date":"2016-10-07","arxiv_id":"1610.02391","repositories_listed":126,"syntology":{"n":141,"n_ran":90,"n_constructed":32,"n_ran_checked":65,"n_instrument":25,"n_unverified":51,"n_honours":5,"n_violates":4,"n_no_contract":56,"n_pointer_only":69,"phrase":"90 ran (of which 32 constructed an object rather than computing a result; 65 with no instrument failure: 5 honoured, 4 violated, 56 with no contract checked; 25 where Syntology's instrument failed) · 51 unverified","sample_list":"/paper/grad-cam-visual-explanations-from-deep#ran","syntology_url":"https://syntology.ai/paper/1610.02391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.02391"}},"official":{"repos":["ramprs/grad-cam"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/analyzing-the-behavior-of-visual-question","slug":"analyzing-the-behavior-of-visual-question","title":"Analyzing the Behavior of Visual Question Answering Models","date":"2016-06-23","arxiv_id":"1606.07356","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/analyzing-the-behavior-of-visual-question#ran","syntology_url":"https://syntology.ai/paper/1606.07356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.07356"}},"official":{"repos":["akirafukui/vqa-mcb"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-question-image-co-attention-for","slug":"hierarchical-question-image-co-attention-for","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","date":"2016-05-31","arxiv_id":"1606.00061","repositories_listed":9,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hierarchical-question-image-co-attention-for#ran","syntology_url":"https://syntology.ai/paper/1606.00061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.00061"}},"official":{"repos":["jiasenlu/HieCoAttenVQA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/end-to-end-instance-segmentation-with","slug":"end-to-end-instance-segmentation-with","title":"End-to-End Instance Segmentation with Recurrent Attention","date":"2016-05-30","arxiv_id":"1605.09410","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-instance-segmentation-with#ran","syntology_url":"https://syntology.ai/paper/1605.09410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.09410"}},"official":null}},{"url":"/paper/dynamic-memory-networks-for-visual-and","slug":"dynamic-memory-networks-for-visual-and","title":"Dynamic Memory Networks for Visual and Textual Question Answering","date":"2016-03-04","arxiv_id":"1603.01417","repositories_listed":10,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":0,"n_instrument":7,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamic-memory-networks-for-visual-and#ran","syntology_url":"https://syntology.ai/paper/1603.01417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.01417"}},"official":null}},{"url":"/paper/vqa-visual-question-answering","slug":"vqa-visual-question-answering","title":"VQA: Visual Question Answering","date":"2015-05-03","arxiv_id":"1505.00468","repositories_listed":21,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vqa-visual-question-answering#ran","syntology_url":"https://syntology.ai/paper/1505.00468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1505.00468"}},"official":null}}],"record_sha256":"d68452e7fbbd068f72be8247dcf30c3bcc2728312761a0a6d4a60669e311a87f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}