{"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/25","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":25,"pages_in_order":56,"rows_per_page":100,"rows":[2401,2500],"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/24","next":"/task/benchmarking/papers/26","papers":[{"url":"/paper/graphgallery-a-platform-for-fast-benchmarking","slug":"graphgallery-a-platform-for-fast-benchmarking","title":"GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software","date":"2021-02-16","arxiv_id":"2102.07933","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-deep-graph-generative-models-for","slug":"benchmarking-deep-graph-generative-models-for","title":"Benchmarking Deep Graph Generative Models for Optimizing New Drug Molecules for COVID-19","date":"2021-02-09","arxiv_id":"2102.04977","repositories_listed":1,"syntology":null},{"url":"/paper/graph-joint-attention-networks-1","slug":"graph-joint-attention-networks-1","title":"Learning Conjoint Attentions for Graph Neural Nets","date":"2021-02-05","arxiv_id":"2102.03147","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-quantized-neural-networks-on","slug":"benchmarking-quantized-neural-networks-on","title":"Benchmarking Quantized Neural Networks on FPGAs with FINN","date":"2021-02-02","arxiv_id":"2102.01341","repositories_listed":1,"syntology":null},{"url":"/paper/bold-dataset-and-metrics-for-measuring-biases","slug":"bold-dataset-and-metrics-for-measuring-biases","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","date":"2021-01-27","arxiv_id":"2101.11718","repositories_listed":1,"syntology":null},{"url":"/paper/arabic-speech-recognition-by-end-to-end","slug":"arabic-speech-recognition-by-end-to-end","title":"Arabic Speech Recognition by End-to-End, Modular Systems and Human","date":"2021-01-21","arxiv_id":"2101.08454","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-perturbation-based-saliency-maps","slug":"benchmarking-perturbation-based-saliency-maps","title":"Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents","date":"2021-01-18","arxiv_id":"2101.07312","repositories_listed":1,"syntology":null},{"url":"/paper/machine-learning-approach-for-quantum-non","slug":"machine-learning-approach-for-quantum-non","title":"Machine learning classification of non-Markovian noise disturbing quantum dynamics","date":"2021-01-08","arxiv_id":"2101.03221","repositories_listed":1,"syntology":null},{"url":"/paper/shallow-uwnet-compressed-model-for-underwater","slug":"shallow-uwnet-compressed-model-for-underwater","title":"Shallow-UWnet : Compressed Model for Underwater Image Enhancement","date":"2021-01-06","arxiv_id":"2101.02073","repositories_listed":1,"syntology":null},{"url":"/paper/descending-through-a-crowded-valley-1","slug":"descending-through-a-crowded-valley-1","title":"Descending through a Crowded Valley — Benchmarking Deep Learning Optimizers","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/robust-2d-3d-vehicle-parsing-in-arbitrary","slug":"robust-2d-3d-vehicle-parsing-in-arbitrary","title":"Robust 2D/3D Vehicle Parsing in Arbitrary Camera Views for CVIS","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sacod-sensor-algorithm-co-design-towards","slug":"sacod-sensor-algorithm-co-design-towards","title":"SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-powered Intelligent PhlatCam","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/weighting-based-treatment-effect-estimation","slug":"weighting-based-treatment-effect-estimation","title":"Weighting-Based Treatment Effect Estimation via Distribution Learning","date":"2020-12-26","arxiv_id":"2012.13805","repositories_listed":1,"syntology":null},{"url":"/paper/an-experimental-study-of-the-transferability","slug":"an-experimental-study-of-the-transferability","title":"An Experimental Study of the Transferability of Spectral Graph Networks","date":"2020-12-18","arxiv_id":"2012.10258","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/an-experimental-study-of-the-transferability#ran","syntology_url":"https://syntology.ai/paper/2012.10258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.10258"}},"official":{"repos":["Axeln78/Transferability-of-spectral-gnns"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/calibrated-adaptive-probabilistic-ode-solvers","slug":"calibrated-adaptive-probabilistic-ode-solvers","title":"Calibrated Adaptive Probabilistic ODE Solvers","date":"2020-12-15","arxiv_id":"2012.08202","repositories_listed":1,"syntology":null},{"url":"/paper/tacto-a-fast-flexible-and-open-source","slug":"tacto-a-fast-flexible-and-open-source","title":"TACTO: A Fast, Flexible, and Open-source Simulator for High-Resolution Vision-based Tactile Sensors","date":"2020-12-15","arxiv_id":"2012.08456","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tacto-a-fast-flexible-and-open-source#ran","syntology_url":"https://syntology.ai/paper/2012.08456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.08456"}},"official":{"repos":["facebookresearch/tacto"],"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/benchmarking-intent-detection-for-task","slug":"benchmarking-intent-detection-for-task","title":"Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations","date":"2020-12-07","arxiv_id":"2012.03929","repositories_listed":1,"syntology":null},{"url":"/paper/a-benchmark-dataset-for-understandable","slug":"a-benchmark-dataset-for-understandable","title":"Benchmarking Automated Clinical Language Simplification: Dataset, Algorithm, and Evaluation","date":"2020-12-04","arxiv_id":"2012.02420","repositories_listed":1,"syntology":null},{"url":"/paper/a-general-benchmarking-framework-for-text","slug":"a-general-benchmarking-framework-for-text","title":"A General Benchmarking Framework for Text Generation","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-attribution-for-graph-neural","slug":"evaluating-attribution-for-graph-neural","title":"Evaluating Attribution for Graph Neural Networks","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mlosp-towards-a-unified-implementation-of","slug":"mlosp-towards-a-unified-implementation-of","title":"mlOSP: Towards a Unified Implementation of Regression Monte Carlo Algorithms","date":"2020-12-01","arxiv_id":"2012.00729","repositories_listed":1,"syntology":null},{"url":"/paper/cable-tree-wiring-benchmarking-solvers-on-a","slug":"cable-tree-wiring-benchmarking-solvers-on-a","title":"Cable Tree Wiring -- Benchmarking Solvers on a Real-World Scheduling Problem with a Variety of Precedence Constraints","date":"2020-11-25","arxiv_id":"2011.12862","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-image-retrieval-for-visual","slug":"benchmarking-image-retrieval-for-visual","title":"Benchmarking Image Retrieval for Visual Localization","date":"2020-11-24","arxiv_id":"2011.11946","repositories_listed":1,"syntology":null},{"url":"/paper/robustpointset-a-dataset-for-benchmarking","slug":"robustpointset-a-dataset-for-benchmarking","title":"RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud Classifiers","date":"2020-11-23","arxiv_id":"2011.11572","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-polyp-detection-localisation-and","slug":"real-time-polyp-detection-localisation-and","title":"Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning","date":"2020-11-15","arxiv_id":"2011.07631","repositories_listed":1,"syntology":null},{"url":"/paper/tonic-a-deep-reinforcement-learning-library","slug":"tonic-a-deep-reinforcement-learning-library","title":"Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking","date":"2020-11-15","arxiv_id":"2011.07537","repositories_listed":1,"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":0,"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/tonic-a-deep-reinforcement-learning-library#ran","syntology_url":"https://syntology.ai/paper/2011.07537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.07537"}},"official":{"repos":["fabiopardo/tonic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cryo-ralib-a-modular-library-for-accelerating","slug":"cryo-ralib-a-modular-library-for-accelerating","title":"Cryo-RALib -- a modular library for accelerating alignment in cryo-EM","date":"2020-11-11","arxiv_id":"2011.05755","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-marginal-uncertainty-how-accurately","slug":"beyond-marginal-uncertainty-how-accurately","title":"Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?","date":"2020-11-06","arxiv_id":"2011.03178","repositories_listed":1,"syntology":null},{"url":"/paper/defense-friendly-images-in-adversarial","slug":"defense-friendly-images-in-adversarial","title":"Defense-friendly Images in Adversarial Attacks: Dataset and Metrics for Perturbation Difficulty","date":"2020-11-05","arxiv_id":"2011.02675","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-meaning-representations-in","slug":"benchmarking-meaning-representations-in","title":"Benchmarking Meaning Representations in Neural Semantic Parsing","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-sentiment-classification-in-low","slug":"cross-lingual-sentiment-classification-in-low","title":"Cross-lingual sentiment classification in low-resource Bengali language","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neural-network-design-learning-from-neural","slug":"neural-network-design-learning-from-neural","title":"Neural Network Design: Learning from Neural Architecture Search","date":"2020-11-01","arxiv_id":"2011.00521","repositories_listed":1,"syntology":null},{"url":"/paper/a-critical-assessment-of-state-of-the-art-in","slug":"a-critical-assessment-of-state-of-the-art-in","title":"A Critical Assessment of State-of-the-Art in Entity Alignment","date":"2020-10-30","arxiv_id":"2010.16314","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-deep-learning-interpretability","slug":"benchmarking-deep-learning-interpretability","title":"Benchmarking Deep Learning Interpretability in Time Series Predictions","date":"2020-10-26","arxiv_id":"2010.13924","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-deep-learning-interpretability#ran","syntology_url":"https://syntology.ai/paper/2010.13924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.13924"}},"official":{"repos":["ayaabdelsalam91/TS-Interpretability-Benchmark"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/probing-acoustic-representations-for-phonetic","slug":"probing-acoustic-representations-for-phonetic","title":"Probing Acoustic Representations for Phonetic Properties","date":"2020-10-25","arxiv_id":"2010.13007","repositories_listed":1,"syntology":null},{"url":"/paper/kinnews-and-kirnews-benchmarking-cross","slug":"kinnews-and-kirnews-benchmarking-cross","title":"KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi","date":"2020-10-23","arxiv_id":"2010.12174","repositories_listed":1,"syntology":null},{"url":"/paper/kvasir-instrument-diagnostic-and-therapeutic","slug":"kvasir-instrument-diagnostic-and-therapeutic","title":"Kvasir-Instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy","date":"2020-10-23","arxiv_id":"2011.08065","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-true-performance-of","slug":"investigating-the-true-performance-of","title":"Exploiting News Article Structure for Automatic Corpus Generation of Entailment Datasets","date":"2020-10-22","arxiv_id":"2010.11574","repositories_listed":1,"syntology":null},{"url":"/paper/learnability-and-complexity-of-quantum","slug":"learnability-and-complexity-of-quantum","title":"Learnability and Complexity of Quantum Samples","date":"2020-10-22","arxiv_id":"2010.11983","repositories_listed":1,"syntology":null},{"url":"/paper/self-alignment-pre-training-for-biomedical","slug":"self-alignment-pre-training-for-biomedical","title":"Self-Alignment Pretraining for Biomedical Entity Representations","date":"2020-10-22","arxiv_id":"2010.11784","repositories_listed":1,"syntology":null},{"url":"/paper/german-s-next-language-model","slug":"german-s-next-language-model","title":"German's Next Language Model","date":"2020-10-21","arxiv_id":"2010.10906","repositories_listed":1,"syntology":null},{"url":"/paper/promoting-high-diversity-ensemble-learning","slug":"promoting-high-diversity-ensemble-learning","title":"Promoting High Diversity Ensemble Learning with EnsembleBench","date":"2020-10-20","arxiv_id":"2010.10623","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-neural-networks-with-soft-evidence","slug":"bayesian-neural-networks-with-soft-evidence","title":"Bayesian Neural Networks with Soft Evidence","date":"2020-10-19","arxiv_id":"2010.09570","repositories_listed":1,"syntology":null},{"url":"/paper/robustbench-a-standardized-adversarial","slug":"robustbench-a-standardized-adversarial","title":"RobustBench: a standardized adversarial robustness benchmark","date":"2020-10-19","arxiv_id":"2010.09670","repositories_listed":1,"syntology":null},{"url":"/paper/radiate-a-radar-dataset-for-automotive","slug":"radiate-a-radar-dataset-for-automotive","title":"RADIATE: A Radar Dataset for Automotive Perception in Bad Weather","date":"2020-10-18","arxiv_id":"2010.09076","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/radiate-a-radar-dataset-for-automotive#ran","syntology_url":"https://syntology.ai/paper/2010.09076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09076"}},"official":{"repos":["marcelsheeny/radiate_sdk"],"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/a-seq2seq-approach-to-symbolic-regression","slug":"a-seq2seq-approach-to-symbolic-regression","title":"A Seq2Seq approach to Symbolic Regression","date":"2020-10-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/light-field-salient-object-detection-a-review","slug":"light-field-salient-object-detection-a-review","title":"Light Field Salient Object Detection: A Review and Benchmark","date":"2020-10-10","arxiv_id":"2010.04968","repositories_listed":1,"syntology":null},{"url":"/paper/olympus-a-benchmarking-framework-for-noisy","slug":"olympus-a-benchmarking-framework-for-noisy","title":"Olympus: a benchmarking framework for noisy optimization and experiment planning","date":"2020-10-08","arxiv_id":"2010.04153","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-dataset-of-dog-breed-images-and-a","slug":"a-new-dataset-of-dog-breed-images-and-a","title":"A new dataset of dog breed images and a benchmark for fine-grained classification","date":"2020-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/hint3-raising-the-bar-for-intent-detection-in","slug":"hint3-raising-the-bar-for-intent-detection-in","title":"HINT3: Raising the bar for Intent Detection in the Wild","date":"2020-09-29","arxiv_id":"2009.13833","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-deep-inverse-models-over-time","slug":"benchmarking-deep-inverse-models-over-time","title":"Benchmarking deep inverse models over time, and the neural-adjoint method","date":"2020-09-27","arxiv_id":"2009.12919","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-deep-inverse-models-over-time#ran","syntology_url":"https://syntology.ai/paper/2009.12919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12919"}},"official":{"repos":["BensonRen/BDIMNNA"],"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/a-bfs-tree-of-ranking-references-for","slug":"a-bfs-tree-of-ranking-references-for","title":"A BFS-Tree of Ranking References for Unsupervised Manifold Learning","date":"2020-09-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cvpr-2020-continual-learning-in-computer","slug":"cvpr-2020-continual-learning-in-computer","title":"CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions","date":"2020-09-14","arxiv_id":"2009.09929","repositories_listed":1,"syntology":null},{"url":"/paper/deep-metric-learning-meets-deep-clustering-an","slug":"deep-metric-learning-meets-deep-clustering-an","title":"Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach for Feature Embedding","date":"2020-09-09","arxiv_id":"2009.04091","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-normalised-constants-with","slug":"simulating-normalised-constants-with","title":"Referenced Thermodynamic Integration for Bayesian Model Selection: Application to COVID-19 Model Selection","date":"2020-09-08","arxiv_id":"2009.03851","repositories_listed":1,"syntology":null},{"url":"/paper/pt-ranking-a-benchmarking-platform-for-neural","slug":"pt-ranking-a-benchmarking-platform-for-neural","title":"PT-Ranking: A Benchmarking Platform for Neural Learning-to-Rank","date":"2020-08-31","arxiv_id":"2008.13368","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/pt-ranking-a-benchmarking-platform-for-neural#ran","syntology_url":"https://syntology.ai/paper/2008.13368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.13368"}},"official":{"repos":["wildltr/ptranking"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/image-colorization-a-survey-and-dataset","slug":"image-colorization-a-survey-and-dataset","title":"Image Colorization: A Survey and Dataset","date":"2020-08-25","arxiv_id":"2008.10774","repositories_listed":1,"syntology":null},{"url":"/paper/screwnet-category-independent-articulation","slug":"screwnet-category-independent-articulation","title":"ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory","date":"2020-08-24","arxiv_id":"2008.10518","repositories_listed":1,"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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/screwnet-category-independent-articulation#ran","syntology_url":"https://syntology.ai/paper/2008.10518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10518"}},"official":{"repos":["Pearl-UTexas/ScrewNet"],"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/quantitative-survey-of-the-state-of-the-art","slug":"quantitative-survey-of-the-state-of-the-art","title":"Quantitative Survey of the State of the Art in Sign Language Recognition","date":"2020-08-22","arxiv_id":"2008.09918","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-sleep-stage-classification-with","slug":"automatic-sleep-stage-classification-with","title":"Automatic sleep stage classification with deep residual networks in a mixed-cohort setting","date":"2020-08-21","arxiv_id":"2008.09416","repositories_listed":1,"syntology":null},{"url":"/paper/issafe-improving-semantic-segmentation-in","slug":"issafe-improving-semantic-segmentation-in","title":"ISSAFE: Improving Semantic Segmentation in Accidents by Fusing Event-based Data","date":"2020-08-20","arxiv_id":"2008.08974","repositories_listed":1,"syntology":null},{"url":"/paper/aiperf-automated-machine-learning-as-an-ai","slug":"aiperf-automated-machine-learning-as-an-ai","title":"AIPerf: Automated machine learning as an AI-HPC benchmark","date":"2020-08-17","arxiv_id":"2008.07141","repositories_listed":1,"syntology":null},{"url":"/paper/robust-benchmarking-for-machine-learning-of","slug":"robust-benchmarking-for-machine-learning-of","title":"Robust Benchmarking for Machine Learning of Clinical Entity Extraction","date":"2020-07-31","arxiv_id":"2007.16127","repositories_listed":1,"syntology":null},{"url":"/paper/domain2vec-domain-embedding-for-unsupervised","slug":"domain2vec-domain-embedding-for-unsupervised","title":"Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation","date":"2020-07-17","arxiv_id":"2007.09257","repositories_listed":1,"syntology":null},{"url":"/paper/imagenet-performance-correlates-with-pose","slug":"imagenet-performance-correlates-with-pose","title":"ImageNet performance correlates with pose estimation robustness and generalization on out-of-domain data","date":"2020-07-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/wordcraft-an-environment-for-benchmarking","slug":"wordcraft-an-environment-for-benchmarking","title":"WordCraft: An Environment for Benchmarking Commonsense Agents","date":"2020-07-17","arxiv_id":"2007.09185","repositories_listed":1,"syntology":null},{"url":"/paper/are-we-there-yet-evaluating-state-of-the-art","slug":"are-we-there-yet-evaluating-state-of-the-art","title":"Are We There Yet? Evaluating State-of-the-Art Neural Network based Geoparsers Using EUPEG as a Benchmarking Platform","date":"2020-07-15","arxiv_id":"2007.07455","repositories_listed":1,"syntology":null},{"url":"/paper/emoji-prediction-extensions-and-benchmarking","slug":"emoji-prediction-extensions-and-benchmarking","title":"Emoji Prediction: Extensions and Benchmarking","date":"2020-07-14","arxiv_id":"2007.07389","repositories_listed":1,"syntology":null},{"url":"/paper/chexphoto-10000-smartphone-photos-and","slug":"chexphoto-10000-smartphone-photos-and","title":"CheXphoto: 10,000+ Photos and Transformations of Chest X-rays for Benchmarking Deep Learning Robustness","date":"2020-07-13","arxiv_id":"2007.06199","repositories_listed":1,"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/chexphoto-10000-smartphone-photos-and#ran","syntology_url":"https://syntology.ai/paper/2007.06199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06199"}},"official":{"repos":["stanfordmlgroup/cheXphoto"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-causal-benchmarking-of-bias-in-face","slug":"towards-causal-benchmarking-of-bias-in-face","title":"Towards causal benchmarking of bias in face analysis algorithms","date":"2020-07-13","arxiv_id":"2007.06570","repositories_listed":1,"syntology":null},{"url":"/paper/affine-non-negative-collaborative","slug":"affine-non-negative-collaborative","title":"Affine Non-negative Collaborative Representation Based Pattern Classification","date":"2020-07-10","arxiv_id":"2007.05175","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-spatial-and-textual-analysis-with","slug":"enhancing-spatial-and-textual-analysis-with","title":"Enhancing spatial and textual analysis with EUPEG: an extensible and unified platform for evaluating geoparsers","date":"2020-07-09","arxiv_id":"2007.04524","repositories_listed":1,"syntology":null},{"url":"/paper/quaternion-capsule-networks","slug":"quaternion-capsule-networks","title":"Quaternion Capsule Networks","date":"2020-07-08","arxiv_id":"2007.04389","repositories_listed":1,"syntology":null},{"url":"/paper/ursabench-comprehensive-benchmarking-of","slug":"ursabench-comprehensive-benchmarking-of","title":"URSABench: Comprehensive Benchmarking of Approximate Bayesian Inference Methods for Deep Neural Networks","date":"2020-07-08","arxiv_id":"2007.04466","repositories_listed":1,"syntology":null},{"url":"/paper/wiki-cs-a-wikipedia-based-benchmark-for-graph","slug":"wiki-cs-a-wikipedia-based-benchmark-for-graph","title":"Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks","date":"2020-07-06","arxiv_id":"2007.02901","repositories_listed":1,"syntology":null},{"url":"/paper/quo-vadis-skeleton-action-recognition","slug":"quo-vadis-skeleton-action-recognition","title":"Quo Vadis, Skeleton Action Recognition ?","date":"2020-07-04","arxiv_id":"2007.02072","repositories_listed":1,"syntology":null},{"url":"/paper/descending-through-a-crowded-valley","slug":"descending-through-a-crowded-valley","title":"Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers","date":"2020-07-03","arxiv_id":"2007.01547","repositories_listed":1,"syntology":null},{"url":"/paper/meta-sac-auto-tune-the-entropy-temperature-of","slug":"meta-sac-auto-tune-the-entropy-temperature-of","title":"Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient","date":"2020-07-03","arxiv_id":"2007.01932","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":5,"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 5 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; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/meta-sac-auto-tune-the-entropy-temperature-of#ran","syntology_url":"https://syntology.ai/paper/2007.01932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.01932"}},"official":{"repos":["twni2016/Meta-SAC"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/quantitative-evaluation-of-endoscopic-slam","slug":"quantitative-evaluation-of-endoscopic-slam","title":"EndoSLAM Dataset and An Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearner","date":"2020-06-30","arxiv_id":"2006.16670","repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-quantum-neural-networks","slug":"recurrent-quantum-neural-networks","title":"Recurrent Quantum Neural Networks","date":"2020-06-25","arxiv_id":"2006.14619","repositories_listed":1,"syntology":null},{"url":"/paper/labelling-unlabelled-videos-from-scratch-with","slug":"labelling-unlabelled-videos-from-scratch-with","title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","date":"2020-06-24","arxiv_id":"2006.13662","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":5,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/labelling-unlabelled-videos-from-scratch-with#ran","syntology_url":"https://syntology.ai/paper/2006.13662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13662"}},"official":{"repos":["facebookresearch/selavi"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ranking-and-benchmarking-framework-for","slug":"ranking-and-benchmarking-framework-for","title":"Ranking and benchmarking framework for sampling algorithms on synthetic data streams","date":"2020-06-17","arxiv_id":"2006.09895","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-gender-bias-in-captioning-systems","slug":"mitigating-gender-bias-in-captioning-systems","title":"Mitigating Gender Bias in Captioning Systems","date":"2020-06-15","arxiv_id":"2006.08315","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/mitigating-gender-bias-in-captioning-systems#ran","syntology_url":"https://syntology.ai/paper/2006.08315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08315"}},"official":{"repos":["datamllab/Mitigating_Gender_Bias_In_Captioning_System"],"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-collective-knowledge-project-making-ml","slug":"the-collective-knowledge-project-making-ml","title":"The Collective Knowledge project: making ML models more portable and reproducible with open APIs, reusable best practices and MLOps","date":"2020-06-12","arxiv_id":"2006.07161","repositories_listed":1,"syntology":null},{"url":"/paper/unmasking-the-inductive-biases-of","slug":"unmasking-the-inductive-biases-of","title":"Benchmarking Unsupervised Object Representations for Video Sequences","date":"2020-06-12","arxiv_id":"2006.07034","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unmasking-the-inductive-biases-of#ran","syntology_url":"https://syntology.ai/paper/2006.07034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07034"}},"official":{"repos":["ecker-lab/object-centric-representation-benchmark"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prgflow-benchmarking-swap-aware-unified-deep","slug":"prgflow-benchmarking-swap-aware-unified-deep","title":"PRGFlow: Benchmarking SWAP-Aware Unified Deep Visual Inertial Odometry","date":"2020-06-11","arxiv_id":"2006.06753","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-adversarial-robustness-on-image","slug":"benchmarking-adversarial-robustness-on-image","title":"Benchmarking Adversarial Robustness on Image Classification","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-empirical-evaluation-of","slug":"rethinking-empirical-evaluation-of","title":"Rethinking Empirical Evaluation of Adversarial Robustness Using First-Order Attack Methods","date":"2020-06-01","arxiv_id":"2006.01304","repositories_listed":1,"syntology":null},{"url":"/paper/supervised-learning-is-an-accurate-method-for","slug":"supervised-learning-is-an-accurate-method-for","title":"Supervised learning is an accurate method for network-based gene classification","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/taking-a-deeper-look-at-co-salient-object","slug":"taking-a-deeper-look-at-co-salient-object","title":"Taking a Deeper Look at Co-Salient Object Detection","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-differentially-private-residual","slug":"benchmarking-differentially-private-residual","title":"Benchmarking Differentially Private Residual Networks for Medical Imagery","date":"2020-05-27","arxiv_id":"2005.13099","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-neural-embeddings-for-link","slug":"benchmarking-neural-embeddings-for-link","title":"Benchmarking neural embeddings for link prediction in knowledge graphs under semantic and structural changes","date":"2020-05-15","arxiv_id":"2005.07654","repositories_listed":1,"syntology":null},{"url":"/paper/reference-pose-generation-for-visual","slug":"reference-pose-generation-for-visual","title":"Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis","date":"2020-05-11","arxiv_id":"2005.05179","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-detect-3d-objects-from-point","slug":"learning-to-detect-3d-objects-from-point","title":"RUHSNet: 3D Object Detection Using Lidar Data in Real Time","date":"2020-05-09","arxiv_id":"2006.01250","repositories_listed":1,"syntology":null},{"url":"/paper/cornac-a-comparative-framework-for-multimodal","slug":"cornac-a-comparative-framework-for-multimodal","title":"Cornac: A Comparative Framework for Multimodal Recommender Systems","date":"2020-05-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/curious-hierarchical-actor-critic","slug":"curious-hierarchical-actor-critic","title":"Curious Hierarchical Actor-Critic Reinforcement Learning","date":"2020-05-07","arxiv_id":"2005.03420","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"9 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/curious-hierarchical-actor-critic#ran","syntology_url":"https://syntology.ai/paper/2005.03420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.03420"}},"official":{"repos":["knowledgetechnologyuhh/goal_conditioned_RL_baselines"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-ladder-of-causal-distances","slug":"a-ladder-of-causal-distances","title":"A Ladder of Causal Distances","date":"2020-05-05","arxiv_id":"2005.02480","repositories_listed":1,"syntology":null},{"url":"/paper/dqi-measuring-data-quality-in-nlp","slug":"dqi-measuring-data-quality-in-nlp","title":"DQI: Measuring Data Quality in NLP","date":"2020-05-02","arxiv_id":"2005.00816","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dqi-measuring-data-quality-in-nlp#ran","syntology_url":"https://syntology.ai/paper/2005.00816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00816"}},"official":null}},{"url":"/paper/benchmarking-multidomain-english-indonesian","slug":"benchmarking-multidomain-english-indonesian","title":"Benchmarking Multidomain English-Indonesian Machine Translation","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-robustness-of-machine-reading","slug":"benchmarking-robustness-of-machine-reading","title":"Benchmarking Robustness of Machine Reading Comprehension Models","date":"2020-04-29","arxiv_id":"2004.14004","repositories_listed":1,"syntology":null}],"record_sha256":"a0a896a505ce79cf1bcf11a0b685d1916fcece64937cb1f1958b2e27b4cdf3de","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}