{"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/4","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":56,"rows_per_page":100,"rows":[301,400],"of":5548,"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","prev":"/task/benchmarking/papers/3","next":"/task/benchmarking/papers/5","papers":[{"url":"/paper/changepoint-detection-in-noisy-data-using-a","slug":"changepoint-detection-in-noisy-data-using-a","title":"Changepoint Detection in Noisy Data Using a Novel Residuals Permutation-Based Method (RESPERM): Benchmarking and Application to Single Trial ERPs","date":"2022-04-21","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/k-lite-learning-transferable-visual-models","slug":"k-lite-learning-transferable-visual-models","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","date":"2022-04-20","arxiv_id":"2204.09222","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":3,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/k-lite-learning-transferable-visual-models#ran","syntology_url":"https://syntology.ai/paper/2204.09222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.09222"}},"official":null}},{"url":"/paper/nico-towards-better-benchmarking-for-domain","slug":"nico-towards-better-benchmarking-for-domain","title":"NICO++: Towards Better Benchmarking for Domain Generalization","date":"2022-04-17","arxiv_id":"2204.08040","repositories_listed":2,"syntology":null},{"url":"/paper/the-moral-integrity-corpus-a-benchmark-for","slug":"the-moral-integrity-corpus-a-benchmark-for","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","date":"2022-04-06","arxiv_id":"2204.03021","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/the-moral-integrity-corpus-a-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2204.03021","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03021"}},"official":{"repos":["gt-salt/mic"],"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-unified-framework-for-rank-based-evaluation","slug":"a-unified-framework-for-rank-based-evaluation","title":"A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphs","date":"2022-03-14","arxiv_id":"2203.07544","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/a-unified-framework-for-rank-based-evaluation#ran","syntology_url":"https://syntology.ai/paper/2203.07544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07544"}},"official":{"repos":["pykeen/pykeen","pykeen/ranking-metrics-manuscript"],"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/pmc-patients-a-large-scale-dataset-of-patient","slug":"pmc-patients-a-large-scale-dataset-of-patient","title":"PMC-Patients: A Large-scale Dataset of Patient Summaries and Relations for Benchmarking Retrieval-based Clinical Decision Support Systems","date":"2022-02-28","arxiv_id":"2202.13876","repositories_listed":2,"syntology":null},{"url":"/paper/evaluating-feature-attribution-methods-in-the","slug":"evaluating-feature-attribution-methods-in-the","title":"Evaluating Feature Attribution Methods in the Image Domain","date":"2022-02-22","arxiv_id":"2202.12270","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-the-linear-algebra-awareness-of","slug":"benchmarking-the-linear-algebra-awareness-of","title":"Benchmarking the Linear Algebra Awareness of TensorFlow and PyTorch","date":"2022-02-20","arxiv_id":"2202.09888","repositories_listed":2,"syntology":{"n":19,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/benchmarking-the-linear-algebra-awareness-of#ran","syntology_url":"https://syntology.ai/paper/2202.09888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09888"}},"official":{"repos":["as641651/linearalgebra-awareness-benchmark"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/structured-prediction-problem-archive","slug":"structured-prediction-problem-archive","title":"Structured Prediction Problem Archive","date":"2022-02-04","arxiv_id":"2202.03574","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-subset-selection-from-large","slug":"benchmarking-subset-selection-from-large","title":"Benchmarking Subset Selection from Large Candidate Solution Sets in Evolutionary Multi-objective Optimization","date":"2022-01-18","arxiv_id":"2201.06700","repositories_listed":2,"syntology":null},{"url":"/paper/are-we-really-making-much-progress-revisiting","slug":"are-we-really-making-much-progress-revisiting","title":"Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks","date":"2021-12-30","arxiv_id":"2112.14936","repositories_listed":2,"syntology":null},{"url":"/paper/autonomous-reinforcement-learning-formalism-1","slug":"autonomous-reinforcement-learning-formalism-1","title":"Autonomous Reinforcement Learning: Formalism and Benchmarking","date":"2021-12-17","arxiv_id":"2112.09605","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/autonomous-reinforcement-learning-formalism-1#ran","syntology_url":"https://syntology.ai/paper/2112.09605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.09605"}},"official":{"repos":["architsharma97/earl_benchmark"],"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/benchml-an-extensible-pipelining-framework","slug":"benchml-an-extensible-pipelining-framework","title":"BenchML: an extensible pipelining framework for benchmarking representations of materials and molecules at scale","date":"2021-12-04","arxiv_id":"2112.02287","repositories_listed":2,"syntology":null},{"url":"/paper/csaw-m-an-ordinal-classification-dataset-for","slug":"csaw-m-an-ordinal-classification-dataset-for","title":"CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer","date":"2021-12-02","arxiv_id":"2112.01330","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-deep-deblurring-algorithms-a","slug":"benchmarking-deep-deblurring-algorithms-a","title":"MC-Blur: A Comprehensive Benchmark for Image Deblurring","date":"2021-12-01","arxiv_id":"2112.00234","repositories_listed":2,"syntology":null},{"url":"/paper/hrnet-ai-on-edge-for-mask-detection-and","slug":"hrnet-ai-on-edge-for-mask-detection-and","title":"HRNET: AI on Edge for mask detection and social distancing","date":"2021-11-30","arxiv_id":"2111.15208","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-detection-transfer-learning-with","slug":"benchmarking-detection-transfer-learning-with","title":"Benchmarking Detection Transfer Learning with Vision Transformers","date":"2021-11-22","arxiv_id":"2111.11429","repositories_listed":2,"syntology":null},{"url":"/paper/cleanrl-high-quality-single-file","slug":"cleanrl-high-quality-single-file","title":"CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms","date":"2021-11-16","arxiv_id":"2111.08819","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cleanrl-high-quality-single-file#ran","syntology_url":"https://syntology.ai/paper/2111.08819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08819"}},"official":{"repos":["vwxyzjn/cleanrl"],"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/which-priors-matter-benchmarking-models-for","slug":"which-priors-matter-benchmarking-models-for","title":"Which priors matter? Benchmarking models for learning latent dynamics","date":"2021-11-09","arxiv_id":"2111.05458","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/which-priors-matter-benchmarking-models-for#ran","syntology_url":"https://syntology.ai/paper/2111.05458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.05458"}},"official":{"repos":["deepmind/dm_hamiltonian_dynamics_suite"],"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/personalized-benchmarking-with-the-ludwig","slug":"personalized-benchmarking-with-the-ludwig","title":"Personalized Benchmarking with the Ludwig Benchmarking Toolkit","date":"2021-11-08","arxiv_id":"2111.04260","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/personalized-benchmarking-with-the-ludwig#ran","syntology_url":"https://syntology.ai/paper/2111.04260","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.04260"}},"official":{"repos":["ludwig-ai/ludwig"],"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/benchmarking-multimodal-automl-for-tabular","slug":"benchmarking-multimodal-automl-for-tabular","title":"Benchmarking Multimodal AutoML for Tabular Data with Text Fields","date":"2021-11-04","arxiv_id":"2111.02705","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/benchmarking-multimodal-automl-for-tabular#ran","syntology_url":"https://syntology.ai/paper/2111.02705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02705"}},"official":{"repos":["sxjscience/automl_multimodal_benchmark","awslabs/autogluon"],"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/openfwi-benchmark-seismic-datasets-for","slug":"openfwi-benchmark-seismic-datasets-for","title":"OpenFWI: Large-Scale Multi-Structural Benchmark Datasets for Seismic Full Waveform Inversion","date":"2021-11-04","arxiv_id":"2111.02926","repositories_listed":2,"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/openfwi-benchmark-seismic-datasets-for#ran","syntology_url":"https://syntology.ai/paper/2111.02926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02926"}},"official":{"repos":["lanl/openfwi"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/codabench-flexible-easy-to-use-and","slug":"codabench-flexible-easy-to-use-and","title":"Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform","date":"2021-10-12","arxiv_id":"2110.05802","repositories_listed":2,"syntology":null},{"url":"/paper/s3prl-vc-open-source-voice-conversion","slug":"s3prl-vc-open-source-voice-conversion","title":"S3PRL-VC: Open-source Voice Conversion Framework with Self-supervised Speech Representations","date":"2021-10-12","arxiv_id":"2110.06280","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"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 1 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/s3prl-vc-open-source-voice-conversion#ran","syntology_url":"https://syntology.ai/paper/2110.06280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06280"}},"official":{"repos":["s3prl/s3prl"],"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/chaos-as-an-interpretable-benchmark-for","slug":"chaos-as-an-interpretable-benchmark-for","title":"Chaos as an interpretable benchmark for forecasting and data-driven modelling","date":"2021-10-11","arxiv_id":"2110.05266","repositories_listed":2,"syntology":null},{"url":"/paper/process-extraction-from-text-state-of-the-art","slug":"process-extraction-from-text-state-of-the-art","title":"Process Extraction from Text: Benchmarking the State of the Art and Paving the Way for Future Challenges","date":"2021-10-07","arxiv_id":"2110.03754","repositories_listed":2,"syntology":null},{"url":"/paper/serab-a-multi-lingual-benchmark-for-speech","slug":"serab-a-multi-lingual-benchmark-for-speech","title":"SERAB: A multi-lingual benchmark for speech emotion recognition","date":"2021-10-07","arxiv_id":"2110.03414","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/serab-a-multi-lingual-benchmark-for-speech#ran","syntology_url":"https://syntology.ai/paper/2110.03414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03414"}},"official":{"repos":["neclow/serab"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/entqa-entity-linking-as-question-answering","slug":"entqa-entity-linking-as-question-answering","title":"EntQA: Entity Linking as Question Answering","date":"2021-10-05","arxiv_id":"2110.02369","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":3,"n_ran_checked":3,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/entqa-entity-linking-as-question-answering#ran","syntology_url":"https://syntology.ai/paper/2110.02369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02369"}},"official":{"repos":["wenzhengzhang/entqa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/metadrive-composing-diverse-driving-scenarios","slug":"metadrive-composing-diverse-driving-scenarios","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","date":"2021-09-26","arxiv_id":"2109.12674","repositories_listed":2,"syntology":null},{"url":"/paper/subseasonalclimateusa-a-dataset-for-1","slug":"subseasonalclimateusa-a-dataset-for-1","title":"SubseasonalClimateUSA: A Dataset for Subseasonal Forecasting and Benchmarking","date":"2021-09-21","arxiv_id":"2109.10399","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/subseasonalclimateusa-a-dataset-for-1#ran","syntology_url":"https://syntology.ai/paper/2109.10399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10399"}},"official":{"repos":["microsoft/subseasonal_toolkit","microsoft/subseasonal_data"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/benchmarking-the-combinatorial","slug":"benchmarking-the-combinatorial","title":"Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphs","date":"2021-09-18","arxiv_id":"2109.08925","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/benchmarking-the-combinatorial#ran","syntology_url":"https://syntology.ai/paper/2109.08925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08925"}},"official":{"repos":["hkust-knowcomp/efo-1-qa-benchmark"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/benchmarking-commonsense-knowledge-base","slug":"benchmarking-commonsense-knowledge-base","title":"Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset","date":"2021-09-16","arxiv_id":"2109.07679","repositories_listed":2,"syntology":null},{"url":"/paper/opv2v-an-open-benchmark-dataset-and-fusion","slug":"opv2v-an-open-benchmark-dataset-and-fusion","title":"OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication","date":"2021-09-16","arxiv_id":"2109.07644","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-the-spectrum-of-agent","slug":"benchmarking-the-spectrum-of-agent","title":"Benchmarking the Spectrum of Agent Capabilities","date":"2021-09-14","arxiv_id":"2109.06780","repositories_listed":2,"syntology":null},{"url":"/paper/generative-wind-power-curve-modeling-via","slug":"generative-wind-power-curve-modeling-via","title":"Generative Wind Power Curve Modeling Via Machine Vision: A Self-learning Deep Convolutional Network Based Method","date":"2021-08-19","arxiv_id":"2109.00894","repositories_listed":2,"syntology":null},{"url":"/paper/a-systematic-benchmarking-analysis-of","slug":"a-systematic-benchmarking-analysis-of","title":"A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysis","date":"2021-08-12","arxiv_id":"2108.05930","repositories_listed":2,"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/a-systematic-benchmarking-analysis-of#ran","syntology_url":"https://syntology.ai/paper/2108.05930","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.05930"}},"official":{"repos":["jlianglab/benchmarktransferlearning"],"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/a-multi-schematic-classifier-independent","slug":"a-multi-schematic-classifier-independent","title":"A multi-schematic classifier-independent oversampling approach for imbalanced datasets","date":"2021-07-15","arxiv_id":"2107.07349","repositories_listed":2,"syntology":null},{"url":"/paper/inverse-contextual-bandits-learning-how","slug":"inverse-contextual-bandits-learning-how","title":"Inverse Contextual Bandits: Learning How Behavior Evolves over Time","date":"2021-07-13","arxiv_id":"2107.06317","repositories_listed":2,"syntology":null},{"url":"/paper/benchpress-a-scalable-and-platform","slug":"benchpress-a-scalable-and-platform","title":"Benchpress: A Scalable and Versatile Workflow for Benchmarking Structure Learning Algorithms","date":"2021-07-08","arxiv_id":"2107.03863","repositories_listed":2,"syntology":null},{"url":"/paper/the-rsna-asnr-miccai-brats-2021-benchmark-on","slug":"the-rsna-asnr-miccai-brats-2021-benchmark-on","title":"The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification","date":"2021-07-05","arxiv_id":"2107.02314","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":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/the-rsna-asnr-miccai-brats-2021-benchmark-on#ran","syntology_url":"https://syntology.ai/paper/2107.02314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02314"}},"official":null}},{"url":"/paper/fedscale-benchmarking-model-and-system","slug":"fedscale-benchmarking-model-and-system","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","date":"2021-05-24","arxiv_id":"2105.11367","repositories_listed":2,"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/fedscale-benchmarking-model-and-system#ran","syntology_url":"https://syntology.ai/paper/2105.11367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11367"}},"official":{"repos":["SymbioticLab/FedScale"],"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":["listed","official"]}}},{"url":"/paper/anabranch-network-for-camouflaged-object-1","slug":"anabranch-network-for-camouflaged-object-1","title":"Anabranch Network for Camouflaged Object Segmentation","date":"2021-05-20","arxiv_id":"2105.09451","repositories_listed":2,"syntology":null},{"url":"/paper/best-practices-for-constructing-preparing-and","slug":"best-practices-for-constructing-preparing-and","title":"Best practices for constructing, preparing, and evaluating protein-ligand binding affinity benchmarks","date":"2021-05-13","arxiv_id":"2105.06222","repositories_listed":2,"syntology":null},{"url":"/paper/dechorate-a-calibrated-room-impulse-response","slug":"dechorate-a-calibrated-room-impulse-response","title":"dEchorate: a Calibrated Room Impulse Response Database for Echo-aware Signal Processing","date":"2021-04-27","arxiv_id":"2104.13168","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/dechorate-a-calibrated-room-impulse-response#ran","syntology_url":"https://syntology.ai/paper/2104.13168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.13168"}},"official":{"repos":["Chutlhu/dEchorate"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/measuring-what-really-matters-optimizing","slug":"measuring-what-really-matters-optimizing","title":"Measuring what Really Matters: Optimizing Neural Networks for TinyML","date":"2021-04-21","arxiv_id":"2104.10645","repositories_listed":2,"syntology":null},{"url":"/paper/styleptb-a-compositional-benchmark-for-fine","slug":"styleptb-a-compositional-benchmark-for-fine","title":"StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer","date":"2021-04-12","arxiv_id":"2104.05196","repositories_listed":2,"syntology":null},{"url":"/paper/roughness-index-and-roughness-distance-for","slug":"roughness-index-and-roughness-distance-for","title":"Roughness Index and Roughness Distance for Benchmarking Medical Segmentation","date":"2021-03-23","arxiv_id":"2103.12350","repositories_listed":2,"syntology":null},{"url":"/paper/neural-multi-hop-reasoning-with-logical-rules","slug":"neural-multi-hop-reasoning-with-logical-rules","title":"Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphs","date":"2021-03-18","arxiv_id":"2103.10367","repositories_listed":2,"syntology":null},{"url":"/paper/emerging-paradigms-of-neural-network-pruning","slug":"emerging-paradigms-of-neural-network-pruning","title":"Recent Advances on Neural Network Pruning at Initialization","date":"2021-03-11","arxiv_id":"2103.06460","repositories_listed":2,"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/emerging-paradigms-of-neural-network-pruning#ran","syntology_url":"https://syntology.ai/paper/2103.06460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06460"}},"official":{"repos":["mingsun-tse/awesome-pruning-at-initialization","mingsun-tse/smile-pruning"],"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-deep-learning-classifiers-beyond","slug":"benchmarking-deep-learning-classifiers-beyond","title":"Benchmarking Robustness of Deep Learning Classifiers Using Two-Factor Perturbation","date":"2021-03-02","arxiv_id":"2103.03102","repositories_listed":2,"syntology":null},{"url":"/paper/nucls-a-scalable-crowdsourcing-deep-learning","slug":"nucls-a-scalable-crowdsourcing-deep-learning","title":"NuCLS: A scalable crowdsourcing, deep learning approach and dataset for nucleus classification, localization and segmentation","date":"2021-02-18","arxiv_id":"2102.09099","repositories_listed":2,"syntology":null},{"url":"/paper/hawks-evolving-challenging-benchmark-sets-for","slug":"hawks-evolving-challenging-benchmark-sets-for","title":"HAWKS: Evolving Challenging Benchmark Sets for Cluster Analysis","date":"2021-02-13","arxiv_id":"2102.06940","repositories_listed":2,"syntology":null},{"url":"/paper/towards-large-scale-automated-algorithm","slug":"towards-large-scale-automated-algorithm","title":"Towards Large Scale Automated Algorithm Design by Integrating Modular Benchmarking Frameworks","date":"2021-02-12","arxiv_id":"2102.06435","repositories_listed":2,"syntology":null},{"url":"/paper/evaluating-large-vocabulary-object-detectors","slug":"evaluating-large-vocabulary-object-detectors","title":"Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details","date":"2021-02-01","arxiv_id":"2102.01066","repositories_listed":2,"syntology":null},{"url":"/paper/generating-a-doppelganger-graph-resembling","slug":"generating-a-doppelganger-graph-resembling","title":"Generating a Doppelganger Graph: Resembling but Distinct","date":"2021-01-23","arxiv_id":"2101.09593","repositories_listed":2,"syntology":null},{"url":"/paper/automated-model-design-and-benchmarking-of-3d","slug":"automated-model-design-and-benchmarking-of-3d","title":"Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans","date":"2021-01-14","arxiv_id":"2101.05442","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-simulation-based-inference","slug":"benchmarking-simulation-based-inference","title":"Benchmarking Simulation-Based Inference","date":"2021-01-12","arxiv_id":"2101.04653","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":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/benchmarking-simulation-based-inference#ran","syntology_url":"https://syntology.ai/paper/2101.04653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.04653"}},"official":{"repos":["sbi-benchmark/sbibm"],"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/pyhealth-a-python-library-for-health","slug":"pyhealth-a-python-library-for-health","title":"PyHealth: A Python Library for Health Predictive Models","date":"2021-01-11","arxiv_id":"2101.04209","repositories_listed":2,"syntology":null},{"url":"/paper/karsl-arabic-sign-language-database","slug":"karsl-arabic-sign-language-database","title":"KArSL: Arabic Sign Language Database","date":"2021-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/rotation-equivariant-siamese-networks-for","slug":"rotation-equivariant-siamese-networks-for","title":"Rotation Equivariant Siamese Networks for Tracking","date":"2020-12-24","arxiv_id":"2012.13078","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/rotation-equivariant-siamese-networks-for#ran","syntology_url":"https://syntology.ai/paper/2012.13078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.13078"}},"official":{"repos":["dkgupta90/re-siamnet"],"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/authnet-a-deep-learning-based-authentication","slug":"authnet-a-deep-learning-based-authentication","title":"AuthNet: A Deep Learning based Authentication Mechanism using Temporal Facial Feature Movements","date":"2020-12-04","arxiv_id":"2012.02515","repositories_listed":2,"syntology":null},{"url":"/paper/softgym-benchmarking-deep-reinforcement","slug":"softgym-benchmarking-deep-reinforcement","title":"SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation","date":"2020-11-14","arxiv_id":"2011.07215","repositories_listed":2,"syntology":null},{"url":"/paper/tvopt-a-python-framework-for-time-varying","slug":"tvopt-a-python-framework-for-time-varying","title":"tvopt: A Python Framework for Time-Varying Optimization","date":"2020-11-12","arxiv_id":"2011.07119","repositories_listed":2,"syntology":null},{"url":"/paper/opentraj-assessing-prediction-complexity-in","slug":"opentraj-assessing-prediction-complexity-in","title":"OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets","date":"2020-10-02","arxiv_id":"2010.00890","repositories_listed":2,"syntology":null},{"url":"/paper/bag-of-tricks-for-adversarial-training","slug":"bag-of-tricks-for-adversarial-training","title":"Bag of Tricks for Adversarial Training","date":"2020-10-01","arxiv_id":"2010.00467","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bag-of-tricks-for-adversarial-training#ran","syntology_url":"https://syntology.ai/paper/2010.00467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.00467"}},"official":{"repos":["P2333/Bag-of-Tricks-for-AT","fra31/auto-attack"],"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","unlocated"]}}},{"url":"/paper/codex-a-comprehensive-knowledge-graph","slug":"codex-a-comprehensive-knowledge-graph","title":"CoDEx: A Comprehensive Knowledge Graph Completion Benchmark","date":"2020-09-16","arxiv_id":"2009.07810","repositories_listed":2,"syntology":null},{"url":"/paper/searching-for-a-search-method-benchmarking","slug":"searching-for-a-search-method-benchmarking","title":"Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples","date":"2020-09-09","arxiv_id":"2009.06368","repositories_listed":2,"syntology":null},{"url":"/paper/continuous-optimization-benchmarks-by","slug":"continuous-optimization-benchmarks-by","title":"Continuous Optimization Benchmarks by Simulation","date":"2020-08-14","arxiv_id":"2008.06249","repositories_listed":2,"syntology":null},{"url":"/paper/scission-context-aware-and-performance-driven","slug":"scission-context-aware-and-performance-driven","title":"Scission: Performance-driven and Context-aware Cloud-Edge Distribution of Deep Neural Networks","date":"2020-08-08","arxiv_id":"2008.03523","repositories_listed":2,"syntology":null},{"url":"/paper/dmelodies-a-music-dataset-for-disentanglement","slug":"dmelodies-a-music-dataset-for-disentanglement","title":"dMelodies: A Music Dataset for Disentanglement Learning","date":"2020-07-29","arxiv_id":"2007.15067","repositories_listed":2,"syntology":null},{"url":"/paper/a-survey-on-performance-metrics-for-object","slug":"a-survey-on-performance-metrics-for-object","title":"A Survey on Performance Metrics for Object-Detection Algorithms","date":"2020-07-21","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/delving-into-the-adversarial-robustness-on","slug":"delving-into-the-adversarial-robustness-on","title":"RobFR: Benchmarking Adversarial Robustness on Face Recognition","date":"2020-07-08","arxiv_id":"2007.04118","repositories_listed":2,"syntology":{"n":23,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"16 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; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/delving-into-the-adversarial-robustness-on#ran","syntology_url":"https://syntology.ai/paper/2007.04118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.04118"}},"official":{"repos":["ShawnXYang/Face-Robustness-Benchmark"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/re-thinking-co-salient-object-detection","slug":"re-thinking-co-salient-object-detection","title":"Re-thinking Co-Salient Object Detection","date":"2020-07-07","arxiv_id":"2007.03380","repositories_listed":2,"syntology":null},{"url":"/paper/bringing-light-into-the-dark-a-large-scale","slug":"bringing-light-into-the-dark-a-large-scale","title":"Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework","date":"2020-06-23","arxiv_id":"2006.13365","repositories_listed":2,"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/bringing-light-into-the-dark-a-large-scale#ran","syntology_url":"https://syntology.ai/paper/2006.13365","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13365"}},"official":{"repos":["pykeen/benchmarking"],"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/monash-university-uea-ucr-time-series","slug":"monash-university-uea-ucr-time-series","title":"Monash University, UEA, UCR Time Series Extrinsic Regression Archive","date":"2020-06-19","arxiv_id":"2006.10996","repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-for-ecg-analysis-benchmarks-and","slug":"deep-learning-for-ecg-analysis-benchmarks-and","title":"Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL","date":"2020-04-28","arxiv_id":"2004.13701","repositories_listed":2,"syntology":null},{"url":"/paper/shortcut-learning-in-deep-neural-networks","slug":"shortcut-learning-in-deep-neural-networks","title":"Shortcut Learning in Deep Neural Networks","date":"2020-04-16","arxiv_id":"2004.07780","repositories_listed":2,"syntology":null},{"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/dnnneurosim-v20-an-end-to-end-benchmarking","slug":"dnnneurosim-v20-an-end-to-end-benchmarking","title":"DNN+NeuroSim V2.0: An End-to-End Benchmarking Framework for Compute-in-Memory Accelerators for On-chip Training","date":"2020-03-13","arxiv_id":"2003.06471","repositories_listed":2,"syntology":null},{"url":"/paper/airsim-drone-racing-lab","slug":"airsim-drone-racing-lab","title":"AirSim Drone Racing Lab","date":"2020-03-12","arxiv_id":"2003.05654","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/airsim-drone-racing-lab#ran","syntology_url":"https://syntology.ai/paper/2003.05654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05654"}},"official":{"repos":["microsoft/AirSim-NeurIPS2019-Drone-Racing"],"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-tinyml-systems-challenges-and","slug":"benchmarking-tinyml-systems-challenges-and","title":"Benchmarking TinyML Systems: Challenges and Direction","date":"2020-03-10","arxiv_id":"2003.04821","repositories_listed":2,"syntology":null},{"url":"/paper/malliavin-mancino-estimators-implemented-with","slug":"malliavin-mancino-estimators-implemented-with","title":"Malliavin-Mancino estimators implemented with non-uniform fast Fourier transforms","date":"2020-03-05","arxiv_id":"2003.02842","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-emotion-cause-pair-extraction-via","slug":"end-to-end-emotion-cause-pair-extraction-via","title":"End-to-end Emotion-Cause Pair Extraction via Learning to Link","date":"2020-02-25","arxiv_id":"2002.10710","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/end-to-end-emotion-cause-pair-extraction-via#ran","syntology_url":"https://syntology.ai/paper/2002.10710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10710"}},"official":{"repos":["shl5133/E2EECPE"],"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/network-representation-learning-for-link","slug":"network-representation-learning-for-link","title":"Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?","date":"2020-02-25","arxiv_id":"2002.11522","repositories_listed":2,"syntology":null},{"url":"/paper/a-neural-embedded-choice-model-tastenet-mnl","slug":"a-neural-embedded-choice-model-tastenet-mnl","title":"A Neural-embedded Choice Model: TasteNet-MNL Modeling Taste Heterogeneity with Flexibility and Interpretability","date":"2020-02-03","arxiv_id":"2002.00922","repositories_listed":2,"syntology":null},{"url":"/paper/codereef-an-open-platform-for-portable-mlops","slug":"codereef-an-open-platform-for-portable-mlops","title":"CodeReef: an open platform for portable MLOps, reusable automation actions and reproducible benchmarking","date":"2020-01-22","arxiv_id":"2001.07935","repositories_listed":2,"syntology":null},{"url":"/paper/human-and-automatic-detection-of-generated","slug":"human-and-automatic-detection-of-generated","title":"Automatic Detection of Generated Text is Easiest when Humans are Fooled","date":"2019-11-02","arxiv_id":"1911.00650","repositories_listed":2,"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/human-and-automatic-detection-of-generated#ran","syntology_url":"https://syntology.ai/paper/1911.00650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00650"}},"official":null}},{"url":"/paper/opendenoising-an-extensible-benchmark-for","slug":"opendenoising-an-extensible-benchmark-for","title":"OpenDenoising: an Extensible Benchmark for Building Comparative Studies of Image Denoisers","date":"2019-10-18","arxiv_id":"1910.08328","repositories_listed":2,"syntology":null},{"url":"/paper/on-empirical-comparisons-of-optimizers-for","slug":"on-empirical-comparisons-of-optimizers-for","title":"On Empirical Comparisons of Optimizers for Deep Learning","date":"2019-10-11","arxiv_id":"1910.05446","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-machine-learning-models-on-eicu","slug":"benchmarking-machine-learning-models-on-eicu","title":"Benchmarking machine learning models on multi-centre eICU critical care dataset","date":"2019-10-02","arxiv_id":"1910.00964","repositories_listed":2,"syntology":null},{"url":"/paper/mlperf-training-benchmark","slug":"mlperf-training-benchmark","title":"MLPerf Training Benchmark","date":"2019-10-02","arxiv_id":"1910.01500","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"10 ran (of which 0 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) · 0 unverified","sample_list":"/paper/mlperf-training-benchmark#ran","syntology_url":"https://syntology.ai/paper/1910.01500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01500"}},"official":{"repos":["mlperf/training"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/pixelhop-a-successive-subspace-learning-ssl","slug":"pixelhop-a-successive-subspace-learning-ssl","title":"PixelHop: A Successive Subspace Learning (SSL) Method for Object Classification","date":"2019-09-17","arxiv_id":"1909.08190","repositories_listed":2,"syntology":null},{"url":"/paper/aspect-based-sentiment-classification-with","slug":"aspect-based-sentiment-classification-with","title":"Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks","date":"2019-09-08","arxiv_id":"1909.03477","repositories_listed":2,"syntology":null},{"url":"/paper/an-empirical-comparison-between-stochastic","slug":"an-empirical-comparison-between-stochastic","title":"An empirical comparison between stochastic and deterministic centroid initialisation for K-Means variations","date":"2019-08-26","arxiv_id":"1908.09946","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-hillvallea-for-the-gecco-2019","slug":"benchmarking-hillvallea-for-the-gecco-2019","title":"Benchmarking HillVallEA for the GECCO 2019 Competition on Multimodal Optimization","date":"2019-07-25","arxiv_id":"1907.10988","repositories_listed":2,"syntology":null},{"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/to-model-or-to-intervene-a-comparison-of","slug":"to-model-or-to-intervene-a-comparison-of","title":"To Model or to Intervene: A Comparison of Counterfactual and Online Learning to Rank from User Interactions","date":"2019-07-15","arxiv_id":"1907.06412","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-model-based-reinforcement","slug":"benchmarking-model-based-reinforcement","title":"Benchmarking Model-Based Reinforcement Learning","date":"2019-07-03","arxiv_id":"1907.02057","repositories_listed":2,"syntology":null},{"url":"/paper/safe-trajectory-generation-for-complex-urban","slug":"safe-trajectory-generation-for-complex-urban","title":"Safe Trajectory Generation for Complex Urban Environments Using Spatio-temporal Semantic Corridor","date":"2019-06-24","arxiv_id":"1906.09788","repositories_listed":2,"syntology":null}],"record_sha256":"43610596c978540a2be2a4e8f7718df39a9d6dc6414f8576f441778d070dfea3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}