{"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/benchmarking/papers/ran/8","list_of":"/task/benchmarking","task":"Benchmarking","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":8,"pages_in_order":8,"rows_per_page":100,"rows":[701,749],"of":749,"counts":{"archive_papers_tagged":5548,"with_a_code_link":2658,"where_syntology_ran_a_sample":749,"not_listed_spam_title":0,"listed":5548,"listed_where_code_ran":749,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":624,"every_run_a_failure_of_syntologys_instrument":125,"listed_with_a_run_with_no_instrument_failure":624,"listed_every_run_a_failure_of_syntologys_instrument":125,"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/benchmarking/papers/ran/1","prev":"/task/benchmarking/papers/ran/7","next":null,"papers":[{"url":"/paper/benchmarking-tpu-gpu-and-cpu-platforms-for","slug":"benchmarking-tpu-gpu-and-cpu-platforms-for","title":"Benchmarking TPU, GPU, and CPU Platforms for Deep Learning","date":"2019-07-24","arxiv_id":"1907.10701","repositories_listed":1,"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/benchmarking-tpu-gpu-and-cpu-platforms-for#ran","syntology_url":"https://syntology.ai/paper/1907.10701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10701"}},"official":{"repos":["Emma926/paradnn"],"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":["official"]}}},{"url":"/paper/bim-towards-quantitative-evaluation-of","slug":"bim-towards-quantitative-evaluation-of","title":"Benchmarking Attribution Methods with Relative Feature Importance","date":"2019-07-23","arxiv_id":"1907.09701","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bim-towards-quantitative-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/1907.09701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.09701"}},"official":{"repos":["google-research-datasets/bim"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deepcr-cosmic-ray-rejection-with-deep","slug":"deepcr-cosmic-ray-rejection-with-deep","title":"deepCR: Cosmic Ray Rejection with Deep Learning","date":"2019-07-22","arxiv_id":"1907.09500","repositories_listed":2,"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/deepcr-cosmic-ray-rejection-with-deep#ran","syntology_url":"https://syntology.ai/paper/1907.09500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.09500"}},"official":{"repos":["profjsb/deepCR","kmzzhang/deepCR-paper"],"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/benchmarking-a-catchment-aware-long-short","slug":"benchmarking-a-catchment-aware-long-short","title":"Towards Learning Universal, Regional, and Local Hydrological Behaviors via Machine-Learning Applied to Large-Sample Datasets","date":"2019-07-19","arxiv_id":"1907.08456","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-a-catchment-aware-long-short#ran","syntology_url":"https://syntology.ai/paper/1907.08456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.08456"}},"official":{"repos":["kratzert/ealstm_regional_modeling"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-robustness-in-object-detection","slug":"benchmarking-robustness-in-object-detection","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","date":"2019-07-17","arxiv_id":"1907.07484","repositories_listed":4,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-robustness-in-object-detection#ran","syntology_url":"https://syntology.ai/paper/1907.07484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.07484"}},"official":{"repos":["bethgelab/mmdetection","bethgelab/imagecorruptions","bethgelab/robust-detection-benchmark","bethgelab/stylize-datasets"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-evaluation-of-conditional-gans","slug":"on-the-evaluation-of-conditional-gans","title":"On the Evaluation of Conditional GANs","date":"2019-07-11","arxiv_id":"1907.08175","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"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) · 2 unverified","sample_list":"/paper/on-the-evaluation-of-conditional-gans#ran","syntology_url":"https://syntology.ai/paper/1907.08175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.08175"}},"official":{"repos":["facebookresearch/fjd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mmdetection-open-mmlab-detection-toolbox-and","slug":"mmdetection-open-mmlab-detection-toolbox-and","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","date":"2019-06-17","arxiv_id":"1906.07155","repositories_listed":142,"syntology":{"n":82,"n_ran":62,"n_constructed":0,"n_ran_checked":58,"n_instrument":4,"n_unverified":20,"n_honours":0,"n_violates":2,"n_no_contract":56,"n_pointer_only":12,"phrase":"62 ran (of which 0 constructed an object rather than computing a result; 58 with no instrument failure: 0 honoured, 2 violated, 56 with no contract checked; 4 where Syntology's instrument failed) · 20 unverified","sample_list":"/paper/mmdetection-open-mmlab-detection-toolbox-and#ran","syntology_url":"https://syntology.ai/paper/1906.07155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.07155"}},"official":{"repos":["open-mmlab/mmdetection"],"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/transfer-learning-in-biomedical-natural","slug":"transfer-learning-in-biomedical-natural","title":"Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets","date":"2019-06-13","arxiv_id":"1906.05474","repositories_listed":4,"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/transfer-learning-in-biomedical-natural#ran","syntology_url":"https://syntology.ai/paper/1906.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05474"}},"official":{"repos":["ncbi-nlp/BLUE_Benchmark","ncbi-nlp/NCBI_BERT"],"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/mnist-c-a-robustness-benchmark-for-computer","slug":"mnist-c-a-robustness-benchmark-for-computer","title":"MNIST-C: A Robustness Benchmark for Computer Vision","date":"2019-06-05","arxiv_id":"1906.02337","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/mnist-c-a-robustness-benchmark-for-computer#ran","syntology_url":"https://syntology.ai/paper/1906.02337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02337"}},"official":{"repos":["google-research/mnist-c"],"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":["listed","official"]}}},{"url":"/paper/190602125","slug":"190602125","title":"Strong and Simple Baselines for Multimodal Utterance Embeddings","date":"2019-05-14","arxiv_id":"1906.02125","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/190602125#ran","syntology_url":"https://syntology.ai/paper/1906.02125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02125"}},"official":{"repos":["yaochie/multimodal-baselines"],"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/viznet-towards-a-large-scale-visualization","slug":"viznet-towards-a-large-scale-visualization","title":"VizNet: Towards A Large-Scale Visualization Learning and Benchmarking Repository","date":"2019-05-12","arxiv_id":"1905.04616","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/viznet-towards-a-large-scale-visualization#ran","syntology_url":"https://syntology.ai/paper/1905.04616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04616"}},"official":null}},{"url":"/paper/on-the-use-of-arxiv-as-a-dataset","slug":"on-the-use-of-arxiv-as-a-dataset","title":"On the Use of ArXiv as a Dataset","date":"2019-04-30","arxiv_id":"1905.00075","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/on-the-use-of-arxiv-as-a-dataset#ran","syntology_url":"https://syntology.ai/paper/1905.00075","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.00075"}},"official":{"repos":["mattbierbaum/arxiv-public-datasets"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/habitat-a-platform-for-embodied-ai-research","slug":"habitat-a-platform-for-embodied-ai-research","title":"Habitat: A Platform for Embodied AI Research","date":"2019-04-02","arxiv_id":"1904.01201","repositories_listed":13,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/habitat-a-platform-for-embodied-ai-research#ran","syntology_url":"https://syntology.ai/paper/1904.01201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01201"}},"official":{"repos":["facebookresearch/habitat-sim"],"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/the-kits19-challenge-data-300-kidney-tumor","slug":"the-kits19-challenge-data-300-kidney-tumor","title":"The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomes","date":"2019-03-31","arxiv_id":"1904.00445","repositories_listed":7,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-kits19-challenge-data-300-kidney-tumor#ran","syntology_url":"https://syntology.ai/paper/1904.00445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00445"}},"official":{"repos":["neheller/kits19"],"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"]}}},{"url":"/paper/benchmarking-neural-network-robustness-to-2","slug":"benchmarking-neural-network-robustness-to-2","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","date":"2019-03-28","arxiv_id":"1903.12261","repositories_listed":14,"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/benchmarking-neural-network-robustness-to-2#ran","syntology_url":"https://syntology.ai/paper/1903.12261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.12261"}},"official":{"repos":["hendrycks/robustness"],"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/deepobs-a-deep-learning-optimizer-benchmark-1","slug":"deepobs-a-deep-learning-optimizer-benchmark-1","title":"DeepOBS: A Deep Learning Optimizer Benchmark Suite","date":"2019-03-13","arxiv_id":"1903.05499","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":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) · 1 unverified","sample_list":"/paper/deepobs-a-deep-learning-optimizer-benchmark-1#ran","syntology_url":"https://syntology.ai/paper/1903.05499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.05499"}},"official":{"repos":["fsschneider/deepobs"],"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/adaptive-power-system-emergency-control-using","slug":"adaptive-power-system-emergency-control-using","title":"Adaptive Power System Emergency Control using Deep Reinforcement Learning","date":"2019-03-09","arxiv_id":"1903.03712","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-power-system-emergency-control-using#ran","syntology_url":"https://syntology.ai/paper/1903.03712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.03712"}},"official":{"repos":["RLGC-Project/RLGC"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-large-annotated-medical-image-dataset-for","slug":"a-large-annotated-medical-image-dataset-for","title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms","date":"2019-02-25","arxiv_id":"1902.09063","repositories_listed":12,"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/a-large-annotated-medical-image-dataset-for#ran","syntology_url":"https://syntology.ai/paper/1902.09063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09063"}},"official":null}},{"url":"/paper/nas-bench-101-towards-reproducible-neural","slug":"nas-bench-101-towards-reproducible-neural","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","date":"2019-02-25","arxiv_id":"1902.09635","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/nas-bench-101-towards-reproducible-neural#ran","syntology_url":"https://syntology.ai/paper/1902.09635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09635"}},"official":{"repos":["google-research/nasbench","automl/nas_benchmarks"],"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/2017-robotic-instrument-segmentation","slug":"2017-robotic-instrument-segmentation","title":"2017 Robotic Instrument Segmentation Challenge","date":"2019-02-18","arxiv_id":"1902.06426","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2017-robotic-instrument-segmentation#ran","syntology_url":"https://syntology.ai/paper/1902.06426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.06426"}},"official":{"repos":["duggalrahul/MICCAI17_EndoVis_RoboSeg","ternaus/robot-surgery-segmentation"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-starcraft-multi-agent-challenge","slug":"the-starcraft-multi-agent-challenge","title":"The StarCraft Multi-Agent Challenge","date":"2019-02-11","arxiv_id":"1902.04043","repositories_listed":23,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":14,"phrase":"10 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; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-starcraft-multi-agent-challenge#ran","syntology_url":"https://syntology.ai/paper/1902.04043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.04043"}},"official":{"repos":["oxwhirl/pymarl","oxwhirl/smac"],"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/elki-a-large-open-source-library-for-data","slug":"elki-a-large-open-source-library-for-data","title":"ELKI: A large open-source library for data analysis - ELKI Release 0.7.5 \"Heidelberg\"","date":"2019-02-10","arxiv_id":"1902.03616","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":1,"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/elki-a-large-open-source-library-for-data#ran","syntology_url":"https://syntology.ai/paper/1902.03616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.03616"}},"official":{"repos":["elki-project/elki"],"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/benchmarking-classic-and-learned-navigation","slug":"benchmarking-classic-and-learned-navigation","title":"Benchmarking Classic and Learned Navigation in Complex 3D Environments","date":"2019-01-30","arxiv_id":"1901.10915","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":1,"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/benchmarking-classic-and-learned-navigation#ran","syntology_url":"https://syntology.ai/paper/1901.10915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10915"}},"official":{"repos":["ducha-aiki/navigation-benchmark"],"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/the-liver-tumor-segmentation-benchmark-lits","slug":"the-liver-tumor-segmentation-benchmark-lits","title":"The Liver Tumor Segmentation Benchmark (LiTS)","date":"2019-01-13","arxiv_id":"1901.04056","repositories_listed":6,"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/the-liver-tumor-segmentation-benchmark-lits#ran","syntology_url":"https://syntology.ai/paper/1901.04056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.04056"}},"official":null}},{"url":"/paper/benchmarking-keyword-spotting-efficiency-on","slug":"benchmarking-keyword-spotting-efficiency-on","title":"Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware","date":"2018-12-04","arxiv_id":"1812.01739","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/benchmarking-keyword-spotting-efficiency-on#ran","syntology_url":"https://syntology.ai/paper/1812.01739","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.01739"}},"official":{"repos":["abr/power_benchmarks"],"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/moment-matching-for-multi-source-domain","slug":"moment-matching-for-multi-source-domain","title":"Moment Matching for Multi-Source Domain Adaptation","date":"2018-12-04","arxiv_id":"1812.01754","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"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 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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/moment-matching-for-multi-source-domain#ran","syntology_url":"https://syntology.ai/paper/1812.01754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.01754"}},"official":null}},{"url":"/paper/leaf-a-benchmark-for-federated-settings","slug":"leaf-a-benchmark-for-federated-settings","title":"LEAF: A Benchmark for Federated Settings","date":"2018-12-03","arxiv_id":"1812.01097","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/leaf-a-benchmark-for-federated-settings#ran","syntology_url":"https://syntology.ai/paper/1812.01097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.01097"}},"official":{"repos":["TalwalkarLab/leaf"],"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/molecular-sets-moses-a-benchmarking-platform","slug":"molecular-sets-moses-a-benchmarking-platform","title":"Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models","date":"2018-11-29","arxiv_id":"1811.12823","repositories_listed":3,"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/molecular-sets-moses-a-benchmarking-platform#ran","syntology_url":"https://syntology.ai/paper/1811.12823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12823"}},"official":{"repos":["molecularsets/moses"],"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/guacamol-benchmarking-models-for-de-novo","slug":"guacamol-benchmarking-models-for-de-novo","title":"GuacaMol: Benchmarking Models for De Novo Molecular Design","date":"2018-11-22","arxiv_id":"1811.09621","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/guacamol-benchmarking-models-for-de-novo#ran","syntology_url":"https://syntology.ai/paper/1811.09621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.09621"}},"official":{"repos":["benevolentAI/guacamol","benevolentAI/guacamol_baselines"],"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/signsgd-with-majority-vote-is-communication","slug":"signsgd-with-majority-vote-is-communication","title":"signSGD with Majority Vote is Communication Efficient And Fault Tolerant","date":"2018-10-11","arxiv_id":"1810.05291","repositories_listed":4,"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":1,"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/signsgd-with-majority-vote-is-communication#ran","syntology_url":"https://syntology.ai/paper/1810.05291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.05291"}},"official":null}},{"url":"/paper/ai-fairness-360-an-extensible-toolkit-for","slug":"ai-fairness-360-an-extensible-toolkit-for","title":"AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias","date":"2018-10-03","arxiv_id":"1810.01943","repositories_listed":13,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ai-fairness-360-an-extensible-toolkit-for#ran","syntology_url":"https://syntology.ai/paper/1810.01943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.01943"}},"official":{"repos":["IBM/AIF360"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/benchmarking-reinforcement-learning","slug":"benchmarking-reinforcement-learning","title":"Benchmarking Reinforcement Learning Algorithms on Real-World Robots","date":"2018-09-20","arxiv_id":"1809.07731","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":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) · 1 unverified","sample_list":"/paper/benchmarking-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1809.07731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.07731"}},"official":{"repos":["kindredresearch/SenseAct"],"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/look-across-elapse-disentangled","slug":"look-across-elapse-disentangled","title":"Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition","date":"2018-09-02","arxiv_id":"1809.00338","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/look-across-elapse-disentangled#ran","syntology_url":"https://syntology.ai/paper/1809.00338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.00338"}},"official":{"repos":["ZhaoJ9014/High_Performance_Face_Recognition"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/user-guided-deep-anime-line-art-colorization","slug":"user-guided-deep-anime-line-art-colorization","title":"User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks","date":"2018-08-09","arxiv_id":"1808.03240","repositories_listed":2,"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/user-guided-deep-anime-line-art-colorization#ran","syntology_url":"https://syntology.ai/paper/1808.03240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.03240"}},"official":{"repos":["orashi/AlacGAN"],"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/ann-benchmarks-a-benchmarking-tool-for","slug":"ann-benchmarks-a-benchmarking-tool-for","title":"ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms","date":"2018-07-15","arxiv_id":"1807.05614","repositories_listed":2,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ann-benchmarks-a-benchmarking-tool-for#ran","syntology_url":"https://syntology.ai/paper/1807.05614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.05614"}},"official":null}},{"url":"/paper/benchmarking-neural-network-robustness-to","slug":"benchmarking-neural-network-robustness-to","title":"Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations","date":"2018-07-04","arxiv_id":"1807.01697","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"6 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-neural-network-robustness-to#ran","syntology_url":"https://syntology.ai/paper/1807.01697","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.01697"}},"official":null}},{"url":"/paper/hyperspectral-image-dataset-for-benchmarking","slug":"hyperspectral-image-dataset-for-benchmarking","title":"Hyperspectral Image Dataset for Benchmarking on Salient Object Detection","date":"2018-06-29","arxiv_id":"1806.11314","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/hyperspectral-image-dataset-for-benchmarking#ran","syntology_url":"https://syntology.ai/paper/1806.11314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.11314"}},"official":{"repos":["gistairc/HS-SOD"],"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/deep-reinforcement-learning-for-general-video","slug":"deep-reinforcement-learning-for-general-video","title":"Deep Reinforcement Learning for General Video Game AI","date":"2018-06-06","arxiv_id":"1806.02448","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-reinforcement-learning-for-general-video#ran","syntology_url":"https://syntology.ai/paper/1806.02448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02448"}},"official":{"repos":["rubenrtorrado/GVGAI_GYM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/negbio-a-high-performance-tool-for-negation","slug":"negbio-a-high-performance-tool-for-negation","title":"NegBio: a high-performance tool for negation and uncertainty detection in radiology reports","date":"2017-12-16","arxiv_id":"1712.05898","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/negbio-a-high-performance-tool-for-negation#ran","syntology_url":"https://syntology.ai/paper/1712.05898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.05898"}},"official":{"repos":["ncbi-nlp/NegBio"],"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/fashion-mnist-a-novel-image-dataset-for","slug":"fashion-mnist-a-novel-image-dataset-for","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","date":"2017-08-25","arxiv_id":"1708.07747","repositories_listed":37,"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/fashion-mnist-a-novel-image-dataset-for#ran","syntology_url":"https://syntology.ai/paper/1708.07747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.07747"}},"official":{"repos":["zalandoresearch/fashion-mnist"],"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/what-actions-are-needed-for-understanding","slug":"what-actions-are-needed-for-understanding","title":"What Actions are Needed for Understanding Human Actions in Videos?","date":"2017-08-09","arxiv_id":"1708.02696","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/what-actions-are-needed-for-understanding#ran","syntology_url":"https://syntology.ai/paper/1708.02696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02696"}},"official":{"repos":["gsig/actions-for-actions"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multitask-learning-and-benchmarking-with","slug":"multitask-learning-and-benchmarking-with","title":"Multitask learning and benchmarking with clinical time series data","date":"2017-03-22","arxiv_id":"1703.07771","repositories_listed":11,"syntology":{"n":40,"n_ran":25,"n_constructed":0,"n_ran_checked":21,"n_instrument":4,"n_unverified":15,"n_honours":0,"n_violates":0,"n_no_contract":21,"n_pointer_only":5,"phrase":"25 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/multitask-learning-and-benchmarking-with#ran","syntology_url":"https://syntology.ai/paper/1703.07771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.07771"}},"official":{"repos":["yerevann/mimic3-benchmarks"],"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":["listed","official"]}}},{"url":"/paper/pmlb-a-large-benchmark-suite-for-machine","slug":"pmlb-a-large-benchmark-suite-for-machine","title":"PMLB: A Large Benchmark Suite for Machine Learning Evaluation and Comparison","date":"2017-03-01","arxiv_id":"1703.00512","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/pmlb-a-large-benchmark-suite-for-machine#ran","syntology_url":"https://syntology.ai/paper/1703.00512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.00512"}},"official":{"repos":["EpistasisLab/penn-ml-benchmarks"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ms-marco-a-human-generated-machine-reading","slug":"ms-marco-a-human-generated-machine-reading","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","date":"2016-11-28","arxiv_id":"1611.09268","repositories_listed":14,"syntology":{"n":33,"n_ran":28,"n_constructed":0,"n_ran_checked":27,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":27,"n_pointer_only":0,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 27 with no instrument failure: 0 honoured, 0 violated, 27 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ms-marco-a-human-generated-machine-reading#ran","syntology_url":"https://syntology.ai/paper/1611.09268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.09268"}},"official":null}},{"url":"/paper/technical-report-on-the-cleverhans-v210","slug":"technical-report-on-the-cleverhans-v210","title":"Technical Report on the CleverHans v2.1.0 Adversarial Examples Library","date":"2016-10-03","arxiv_id":"1610.00768","repositories_listed":13,"syntology":{"n":26,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":26,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/technical-report-on-the-cleverhans-v210#ran","syntology_url":"https://syntology.ai/paper/1610.00768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.00768"}},"official":{"repos":["tensorflow/cleverhans"],"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/building-a-large-scale-dataset-for-image","slug":"building-a-large-scale-dataset-for-image","title":"Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark","date":"2016-05-09","arxiv_id":"1605.02677","repositories_listed":2,"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/building-a-large-scale-dataset-for-image#ran","syntology_url":"https://syntology.ai/paper/1605.02677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.02677"}},"official":null}},{"url":"/paper/benchmarking-deep-reinforcement-learning-for","slug":"benchmarking-deep-reinforcement-learning-for","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","date":"2016-04-22","arxiv_id":"1604.06778","repositories_listed":15,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/benchmarking-deep-reinforcement-learning-for#ran","syntology_url":"https://syntology.ai/paper/1604.06778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06778"}},"official":{"repos":["rllab/rllab"],"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/cider-consensus-based-image-description","slug":"cider-consensus-based-image-description","title":"CIDEr: Consensus-based Image Description Evaluation","date":"2014-11-20","arxiv_id":"1411.5726","repositories_listed":24,"syntology":{"n":32,"n_ran":13,"n_constructed":7,"n_ran_checked":9,"n_instrument":4,"n_unverified":19,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":27,"phrase":"13 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 19 unverified","sample_list":"/paper/cider-consensus-based-image-description#ran","syntology_url":"https://syntology.ai/paper/1411.5726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1411.5726"}},"official":null}},{"url":"/paper/the-arcade-learning-environment-an-evaluation","slug":"the-arcade-learning-environment-an-evaluation","title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","date":"2012-07-19","arxiv_id":"1207.4708","repositories_listed":3,"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/the-arcade-learning-environment-an-evaluation#ran","syntology_url":"https://syntology.ai/paper/1207.4708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1207.4708"}},"official":null}}],"record_sha256":"4102e7340f8c72935de88ba05ab1e4e2e93b37f8a2b2bc62f3e196113fb41e96","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}