{"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/27","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":27,"pages_in_order":56,"rows_per_page":100,"rows":[2601,2700],"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/26","next":"/task/benchmarking/papers/28","papers":[{"url":"/paper/benchmarking-classic-and-learned-navigation","slug":"benchmarking-classic-and-learned-navigation","title":"Benchmarking Classic and Learned Navigation in Complex 3D Environments","date":"2019-01-30","arxiv_id":"1901.10915","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-classic-and-learned-navigation#ran","syntology_url":"https://syntology.ai/paper/1901.10915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.10915"}},"official":{"repos":["ducha-aiki/navigation-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-modular-benchmarking-infrastructure-for","slug":"a-modular-benchmarking-infrastructure-for","title":"A Modular Benchmarking Infrastructure for High-Performance and Reproducible Deep Learning","date":"2019-01-29","arxiv_id":"1901.10183","repositories_listed":1,"syntology":null},{"url":"/paper/quasi-newton-methods-for-deep-learning-forget","slug":"quasi-newton-methods-for-deep-learning-forget","title":"Quasi-Newton Methods for Machine Learning: Forget the Past, Just Sample","date":"2019-01-28","arxiv_id":"1901.09997","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/quasi-newton-methods-for-deep-learning-forget#ran","syntology_url":"https://syntology.ai/paper/1901.09997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.09997"}},"official":{"repos":["OptMLGroup/SQN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/transfer-learning-for-prosthetics-using","slug":"transfer-learning-for-prosthetics-using","title":"Transfer Learning for Prosthetics Using Imitation Learning","date":"2019-01-15","arxiv_id":"1901.04772","repositories_listed":1,"syntology":null},{"url":"/paper/machine-learning-automation-toolbox-mlaut","slug":"machine-learning-automation-toolbox-mlaut","title":"Machine Learning Automation Toolbox (MLaut)","date":"2019-01-11","arxiv_id":"1901.03678","repositories_listed":1,"syntology":null},{"url":"/paper/guidelines-and-benchmarks-for-deployment-of","slug":"guidelines-and-benchmarks-for-deployment-of","title":"Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time Apps","date":"2019-01-08","arxiv_id":"1901.02144","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-keyword-spotting-efficiency-on","slug":"benchmarking-keyword-spotting-efficiency-on","title":"Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware","date":"2018-12-04","arxiv_id":"1812.01739","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-keyword-spotting-efficiency-on#ran","syntology_url":"https://syntology.ai/paper/1812.01739","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.01739"}},"official":{"repos":["abr/power_benchmarks"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/essential-guidelines-for-computational-method","slug":"essential-guidelines-for-computational-method","title":"Essential guidelines for computational method benchmarking","date":"2018-12-03","arxiv_id":"1812.00661","repositories_listed":1,"syntology":null},{"url":"/paper/city-scale-road-audit-system-using-deep","slug":"city-scale-road-audit-system-using-deep","title":"City-Scale Road Audit System using Deep Learning","date":"2018-11-26","arxiv_id":"1811.10210","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-cervical-cytology-dataset-for-nucleus","slug":"a-new-cervical-cytology-dataset-for-nucleus","title":"A New Cervical Cytology Dataset for Nucleus Detection and Image Classification (Cervix93) and Methods for Cervical Nucleus Detection","date":"2018-11-23","arxiv_id":"1811.09651","repositories_listed":1,"syntology":null},{"url":"/paper/clubmark-a-parallel-isolation-framework-for","slug":"clubmark-a-parallel-isolation-framework-for","title":"Clubmark: a Parallel Isolation Framework for Benchmarking and Profiling Clustering Algorithms on NUMA Architectures","date":"2018-11-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-datasets-for-anomaly-based","slug":"benchmarking-datasets-for-anomaly-based","title":"Benchmarking datasets for Anomaly-based Network Intrusion Detection: KDD CUP 99 alternatives","date":"2018-11-13","arxiv_id":"1811.05372","repositories_listed":1,"syntology":null},{"url":"/paper/deep-affinity-network-for-multiple-object","slug":"deep-affinity-network-for-multiple-object","title":"Deep Affinity Network for Multiple Object Tracking","date":"2018-10-28","arxiv_id":"1810.11780","repositories_listed":1,"syntology":null},{"url":"/paper/custom-dual-transportation-mode-detection-by","slug":"custom-dual-transportation-mode-detection-by","title":"Custom Dual Transportation Mode Detection by Smartphone Devices Exploiting Sensor Diversity","date":"2018-10-12","arxiv_id":"1810.05596","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-of-image-registration-methods","slug":"benchmarking-of-image-registration-methods","title":"Benchmarking of image registration methods for differently stained histological slides","date":"2018-10-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/accelerated-training-of-large-scale-gaussian","slug":"accelerated-training-of-large-scale-gaussian","title":"Large Scale Clustering with Variational EM for Gaussian Mixture Models","date":"2018-10-01","arxiv_id":"1810.00803","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-and-regularization-in-dqn","slug":"generalization-and-regularization-in-dqn","title":"Generalization and Regularization in DQN","date":"2018-09-29","arxiv_id":"1810.00123","repositories_listed":1,"syntology":null},{"url":"/paper/fivr-fine-grained-incident-video-retrieval","slug":"fivr-fine-grained-incident-video-retrieval","title":"FIVR: Fine-grained Incident Video Retrieval","date":"2018-09-11","arxiv_id":"1809.04094","repositories_listed":1,"syntology":null},{"url":"/paper/a-continuous-information-gain-measure-to-find","slug":"a-continuous-information-gain-measure-to-find","title":"A Continuous Information Gain Measure to Find the Most Discriminatory Problems for AI Benchmarking","date":"2018-09-09","arxiv_id":"1809.02904","repositories_listed":1,"syntology":null},{"url":"/paper/bubgan-bubble-generative-adversarial-networks","slug":"bubgan-bubble-generative-adversarial-networks","title":"BubGAN: Bubble Generative Adversarial Networks for Synthesizing Realistic Bubbly Flow Images","date":"2018-09-07","arxiv_id":"1809.02266","repositories_listed":1,"syntology":null},{"url":"/paper/look-across-elapse-disentangled","slug":"look-across-elapse-disentangled","title":"Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition","date":"2018-09-02","arxiv_id":"1809.00338","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/look-across-elapse-disentangled#ran","syntology_url":"https://syntology.ai/paper/1809.00338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.00338"}},"official":{"repos":["ZhaoJ9014/High_Performance_Face_Recognition"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-neural-networks-for-sequential","slug":"hierarchical-neural-networks-for-sequential","title":"Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts","date":"2018-08-19","arxiv_id":"1808.06161","repositories_listed":1,"syntology":null},{"url":"/paper/learning-adaptive-discriminative-correlation","slug":"learning-adaptive-discriminative-correlation","title":"Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Tracking","date":"2018-07-30","arxiv_id":"1807.11348","repositories_listed":1,"syntology":null},{"url":"/paper/a-linear-constrained-optimization-benchmark","slug":"a-linear-constrained-optimization-benchmark","title":"A Linear Constrained Optimization Benchmark For Probabilistic Search Algorithms: The Rotated Klee-Minty Problem","date":"2018-07-26","arxiv_id":"1807.10068","repositories_listed":1,"syntology":null},{"url":"/paper/advio-an-authentic-dataset-for-visual","slug":"advio-an-authentic-dataset-for-visual","title":"ADVIO: An authentic dataset for visual-inertial odometry","date":"2018-07-25","arxiv_id":"1807.09828","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-the-hill-valley-evolutionary","slug":"benchmarking-the-hill-valley-evolutionary","title":"Benchmarking the Hill-Valley Evolutionary Algorithm for the GECCO 2018 Competition on Niching Methods Multimodal Optimization","date":"2018-06-30","arxiv_id":"1807.00188","repositories_listed":1,"syntology":null},{"url":"/paper/mlpack-3-a-fast-flexible-machine-learning","slug":"mlpack-3-a-fast-flexible-machine-learning","title":"mlpack 3: a fast, flexible machine learning library","date":"2018-06-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-dataset-for-web-scale-knowledge-base","slug":"a-dataset-for-web-scale-knowledge-base","title":"A Dataset for Web-Scale Knowledge Base Population","date":"2018-06-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cvm-net-cross-view-matching-network-for-image","slug":"cvm-net-cross-view-matching-network-for-image","title":"CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization","date":"2018-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nengodl-combining-deep-learning-and","slug":"nengodl-combining-deep-learning-and","title":"NengoDL: Combining deep learning and neuromorphic modelling methods","date":"2018-05-28","arxiv_id":"1805.11144","repositories_listed":1,"syntology":null},{"url":"/paper/where-are-we-now-a-large-benchmark-study-of","slug":"where-are-we-now-a-large-benchmark-study-of","title":"Where are we now? A large benchmark study of recent symbolic regression methods","date":"2018-04-25","arxiv_id":"1804.09331","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-top-k-keyword-and-top-k-document","slug":"benchmarking-top-k-keyword-and-top-k-document","title":"Benchmarking Top-K Keyword and Top-K Document Processing with T${}^2$K${}^2$ and T${}^2$K${}^2$D${}^2$","date":"2018-04-20","arxiv_id":"1804.07525","repositories_listed":1,"syntology":null},{"url":"/paper/benchmark-data-and-method-for-real-time","slug":"benchmark-data-and-method-for-real-time","title":"Benchmark data and method for real-time people counting in cluttered scenes using depth sensors","date":"2018-04-12","arxiv_id":"1804.04339","repositories_listed":1,"syntology":null},{"url":"/paper/learning-protein-constitutive-motifs-from","slug":"learning-protein-constitutive-motifs-from","title":"Learning protein constitutive motifs from sequence data","date":"2018-03-23","arxiv_id":"1803.08718","repositories_listed":1,"syntology":null},{"url":"/paper/high-dynamic-range-imaging-for-cloud","slug":"high-dynamic-range-imaging-for-cloud","title":"High-Dynamic-Range Imaging for Cloud Segmentation","date":"2018-03-02","arxiv_id":"1803.01071","repositories_listed":1,"syntology":null},{"url":"/paper/back-to-basics-benchmarking-canonical","slug":"back-to-basics-benchmarking-canonical","title":"Back to Basics: Benchmarking Canonical Evolution Strategies for Playing Atari","date":"2018-02-24","arxiv_id":"1802.08842","repositories_listed":1,"syntology":null},{"url":"/paper/texygen-a-benchmarking-platform-for-text","slug":"texygen-a-benchmarking-platform-for-text","title":"Texygen: A Benchmarking Platform for Text Generation Models","date":"2018-02-06","arxiv_id":"1802.01886","repositories_listed":1,"syntology":null},{"url":"/paper/nervenet-learning-structured-policy-with","slug":"nervenet-learning-structured-policy-with","title":"NerveNet: Learning Structured Policy with Graph Neural Networks","date":"2018-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/negbio-a-high-performance-tool-for-negation","slug":"negbio-a-high-performance-tool-for-negation","title":"NegBio: a high-performance tool for negation and uncertainty detection in radiology reports","date":"2017-12-16","arxiv_id":"1712.05898","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/negbio-a-high-performance-tool-for-negation#ran","syntology_url":"https://syntology.ai/paper/1712.05898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.05898"}},"official":{"repos":["ncbi-nlp/NegBio"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/qlbs-q-learner-in-the-black-scholes-merton","slug":"qlbs-q-learner-in-the-black-scholes-merton","title":"QLBS: Q-Learner in the Black-Scholes(-Merton) Worlds","date":"2017-12-13","arxiv_id":"1712.04609","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-single-image-dehazing-and-beyond","slug":"benchmarking-single-image-dehazing-and-beyond","title":"Benchmarking Single Image Dehazing and Beyond","date":"2017-12-12","arxiv_id":"1712.04143","repositories_listed":1,"syntology":null},{"url":"/paper/benchmark-of-deep-learning-models-on-large","slug":"benchmark-of-deep-learning-models-on-large","title":"Benchmark of Deep Learning Models on Large Healthcare MIMIC Datasets","date":"2017-10-23","arxiv_id":"1710.08531","repositories_listed":1,"syntology":null},{"url":"/paper/sweetrs-dataset-for-a-recommender-systems-of","slug":"sweetrs-dataset-for-a-recommender-systems-of","title":"SweetRS: Dataset for a recommender systems of sweets","date":"2017-09-10","arxiv_id":"1709.03496","repositories_listed":1,"syntology":null},{"url":"/paper/what-actions-are-needed-for-understanding","slug":"what-actions-are-needed-for-understanding","title":"What Actions are Needed for Understanding Human Actions in Videos?","date":"2017-08-09","arxiv_id":"1708.02696","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/what-actions-are-needed-for-understanding#ran","syntology_url":"https://syntology.ai/paper/1708.02696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02696"}},"official":{"repos":["gsig/actions-for-actions"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/featsel-a-framework-for-benchmarking-of","slug":"featsel-a-framework-for-benchmarking-of","title":"featsel: A framework for benchmarking of feature selection algorithms and cost functions","date":"2017-07-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/crnn-a-joint-neural-network-for-redundancy","slug":"crnn-a-joint-neural-network-for-redundancy","title":"CRNN: A Joint Neural Network for Redundancy Detection","date":"2017-06-04","arxiv_id":"1706.01069","repositories_listed":1,"syntology":null},{"url":"/paper/libopt-an-open-source-platform-for-fast","slug":"libopt-an-open-source-platform-for-fast","title":"LibOPT: An Open-Source Platform for Fast Prototyping Soft Optimization Techniques","date":"2017-04-18","arxiv_id":"1704.05174","repositories_listed":1,"syntology":null},{"url":"/paper/meet-spinky-an-open-source-spindle-and-k","slug":"meet-spinky-an-open-source-spindle-and-k","title":"Meet Spinky: An Open-Source Spindle and K-Complex Detection Toolbox Validated on the Open-Access Montreal Archive of Sleep Studies (MASS).","date":"2017-03-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pmlb-a-large-benchmark-suite-for-machine","slug":"pmlb-a-large-benchmark-suite-for-machine","title":"PMLB: A Large Benchmark Suite for Machine Learning Evaluation and Comparison","date":"2017-03-01","arxiv_id":"1703.00512","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pmlb-a-large-benchmark-suite-for-machine#ran","syntology_url":"https://syntology.ai/paper/1703.00512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.00512"}},"official":{"repos":["EpistasisLab/penn-ml-benchmarks"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pke-an-open-source-python-based-keyphrase","slug":"pke-an-open-source-python-based-keyphrase","title":"pke: an open source python-based keyphrase extraction toolkit","date":"2016-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/word-embeddings-for-the-construction-domain","slug":"word-embeddings-for-the-construction-domain","title":"Word Embeddings for the Construction Domain","date":"2016-10-28","arxiv_id":"1610.09333","repositories_listed":1,"syntology":null},{"url":"/paper/theres-no-comparison-reference-less","slug":"theres-no-comparison-reference-less","title":"There's No Comparison: Reference-less Evaluation Metrics in Grammatical Error Correction","date":"2016-10-07","arxiv_id":"1610.02124","repositories_listed":1,"syntology":null},{"url":"/paper/coco-performance-assessment","slug":"coco-performance-assessment","title":"COCO: Performance Assessment","date":"2016-05-11","arxiv_id":"1605.03560","repositories_listed":1,"syntology":null},{"url":"/paper/jate-20-java-automatic-term-extraction-with","slug":"jate-20-java-automatic-term-extraction-with","title":"JATE 2.0: Java Automatic Term Extraction with Apache Solr","date":"2016-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-of-lstm-networks","slug":"benchmarking-of-lstm-networks","title":"Benchmarking of LSTM Networks","date":"2015-08-11","arxiv_id":"1508.02774","repositories_listed":1,"syntology":null},{"url":"/paper/a-meta-analysis-of-the-anomaly-detection","slug":"a-meta-analysis-of-the-anomaly-detection","title":"A Meta-Analysis of the Anomaly Detection Problem","date":"2015-03-03","arxiv_id":"1503.01158","repositories_listed":1,"syntology":null},{"url":"/paper/a-wild-bootstrap-for-degenerate-kernel-tests","slug":"a-wild-bootstrap-for-degenerate-kernel-tests","title":"A Wild Bootstrap for Degenerate Kernel Tests","date":"2014-08-23","arxiv_id":"1408.5404","repositories_listed":1,"syntology":null},{"url":"/paper/building-a-scalable-and-interpretable","slug":"building-a-scalable-and-interpretable","title":"Building a Scalable and Interpretable Bayesian Deep Learning Framework for Quality Control of Free Form Surfaces","date":"1994-04-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"visual-place-recognition-for-large-scale-uav","title":"Visual Place Recognition for Large-Scale UAV Applications","date":"2025-07-20","arxiv_id":"2507.15089","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-coincident-cell-events-using","title":"Disentangling coincident cell events using deep transfer learning and compressive sensing","date":"2025-07-17","arxiv_id":"2507.13176","repositories_listed":0,"syntology":null},{"url":null,"slug":"mupax-multidimensional-problem-agnostic","title":"MUPAX: Multidimensional Problem Agnostic eXplainable AI","date":"2025-07-17","arxiv_id":"2507.13090","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-transformers-with-enforced-lipschitz","title":"Training Transformers with Enforced Lipschitz Constants","date":"2025-07-17","arxiv_id":"2507.13338","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-view-high-resolution-foot-ankle","title":"A Multi-View High-Resolution Foot-Ankle Complex Point Cloud Dataset During Gait for Occlusion-Robust 3D Completion","date":"2025-07-15","arxiv_id":"2507.11037","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-and-evaluation-of-ai-models-in","title":"Benchmarking and Evaluation of AI Models in Biology: Outcomes and Recommendations from the CZI Virtual Cells Workshop","date":"2025-07-14","arxiv_id":"2507.10502","repositories_listed":0,"syntology":null},{"url":"/paper/codeassistbench-cab-dataset-benchmarking-for","slug":"codeassistbench-cab-dataset-benchmarking-for","title":"CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance","date":"2025-07-14","arxiv_id":"2507.10646","repositories_listed":0,"syntology":{"n":24,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/codeassistbench-cab-dataset-benchmarking-for#ran","syntology_url":"https://syntology.ai/paper/2507.10646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.10646"}},"official":null}},{"url":null,"slug":"codejudgebench-benchmarking-llm-as-a-judge","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","date":"2025-07-14","arxiv_id":"2507.10535","repositories_listed":0,"syntology":null},{"url":null,"slug":"mlar-multi-layer-large-language-model-based","title":"MLAR: Multi-layer Large Language Model-based Robotic Process Automation Applicant Tracking","date":"2025-07-14","arxiv_id":"2507.10472","repositories_listed":0,"syntology":null},{"url":null,"slug":"calibrated-and-robust-foundation-models-for","title":"Calibrated and Robust Foundation Models for Vision-Language and Medical Image Tasks Under Distribution Shift","date":"2025-07-12","arxiv_id":"2507.09222","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-waitlist-mortality-prediction-in","title":"Benchmarking Waitlist Mortality Prediction in Heart Transplantation Through Time-to-Event Modeling using New Longitudinal UNOS Dataset","date":"2025-07-09","arxiv_id":"2507.07339","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-analysis-of-hybrid-linear","title":"A Systematic Analysis of Hybrid Linear Attention","date":"2025-07-08","arxiv_id":"2507.06457","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperspectral-anomaly-detection-methods-a","title":"Hyperspectral Anomaly Detection Methods: A Survey and Comparative Study","date":"2025-07-08","arxiv_id":"2507.05730","repositories_listed":0,"syntology":null},{"url":null,"slug":"sqlbarber-a-system-leveraging-large-language","title":"SQLBarber: A System Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads","date":"2025-07-08","arxiv_id":"2507.06192","repositories_listed":0,"syntology":null},{"url":null,"slug":"inaugural-moasei-competition-at-aamas-2025-a","title":"Inaugural MOASEI Competition at AAMAS'2025: A Technical Report","date":"2025-07-07","arxiv_id":"2507.05469","repositories_listed":0,"syntology":null},{"url":null,"slug":"core-benchmarking-llms-code-reasoning","title":"CORE: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks","date":"2025-07-03","arxiv_id":"2507.05269","repositories_listed":0,"syntology":null},{"url":null,"slug":"translaw-benchmarking-large-language-models","title":"TransLaw: Benchmarking Large Language Models in Multi-Agent Simulation of the Collaborative Translation","date":"2025-07-01","arxiv_id":"2507.00875","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-and-memory-is-all-you-need-for-robust","title":"State and Memory is All You Need for Robust and Reliable AI Agents","date":"2025-06-30","arxiv_id":"2507.00081","repositories_listed":0,"syntology":null},{"url":null,"slug":"point-cloud-compression-and-objective-quality","title":"Point Cloud Compression and Objective Quality Assessment: A Survey","date":"2025-06-28","arxiv_id":"2506.22902","repositories_listed":0,"syntology":null},{"url":null,"slug":"feda4fair-client-level-federated-datasets-for","title":"FeDa4Fair: Client-Level Federated Datasets for Fairness Evaluation","date":"2025-06-26","arxiv_id":"2506.21095","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind2web-2-evaluating-agentic-search-with","title":"Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge","date":"2025-06-26","arxiv_id":"2506.21506","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-predictive-maintenance-methods-an","title":"A Survey of Predictive Maintenance Methods: An Analysis of Prognostics via Classification and Regression","date":"2025-06-25","arxiv_id":"2506.20090","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-driven-mri-based-brain-tumour-segmentation","title":"AI-Driven MRI-based Brain Tumour Segmentation Benchmarking","date":"2025-06-25","arxiv_id":"2506.20786","repositories_listed":0,"syntology":null},{"url":null,"slug":"brokenvideos-a-benchmark-dataset-for-fine","title":"BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos","date":"2025-06-25","arxiv_id":"2506.20103","repositories_listed":0,"syntology":null},{"url":null,"slug":"fixclr-negative-class-contrastive-learning","title":"FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization","date":"2025-06-25","arxiv_id":"2506.20841","repositories_listed":0,"syntology":null},{"url":"/paper/multihuman-testbench-benchmarking-image","slug":"multihuman-testbench-benchmarking-image","title":"MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans","date":"2025-06-25","arxiv_id":"2506.20879","repositories_listed":0,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multihuman-testbench-benchmarking-image#ran","syntology_url":"https://syntology.ai/paper/2506.20879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.20879"}},"official":null}},{"url":null,"slug":"multimodal-information-retrieval-for-open","title":"Multimodal Information Retrieval for Open World with Edit Distance Weak Supervision","date":"2025-06-25","arxiv_id":"2506.20070","repositories_listed":0,"syntology":null},{"url":null,"slug":"scmamba-a-scalable-foundation-model-for","title":"scMamba: A Scalable Foundation Model for Single-Cell Multi-Omics Integration Beyond Highly Variable Feature Selection","date":"2025-06-25","arxiv_id":"2506.20697","repositories_listed":0,"syntology":null},{"url":null,"slug":"mdr-deepc-model-inspired-distributionally","title":"MDR-DeePC: Model-Inspired Distributionally Robust Data-Enabled Predictive Control","date":"2025-06-24","arxiv_id":"2506.19744","repositories_listed":0,"syntology":null},{"url":null,"slug":"qhackbench-benchmarking-large-language-models","title":"QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges","date":"2025-06-24","arxiv_id":"2506.20008","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantitative-benchmarking-of-anomaly","title":"Quantitative Benchmarking of Anomaly Detection Methods in Digital Pathology","date":"2025-06-24","arxiv_id":"2506.19234","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-music-generation-models-and-1","title":"Benchmarking Music Generation Models and Metrics via Human Preference Studies","date":"2025-06-23","arxiv_id":"2506.19085","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-vision-language-models-to-novel","title":"Generalizing Vision-Language Models to Novel Domains: A Comprehensive Survey","date":"2025-06-23","arxiv_id":"2506.18504","repositories_listed":0,"syntology":null},{"url":null,"slug":"simulation-based-sensitivity-analysis-in","title":"Simulation-Based Sensitivity Analysis in Optimal Treatment Regimes and Causal Decomposition with Individualized Interventions","date":"2025-06-23","arxiv_id":"2506.19010","repositories_listed":0,"syntology":null},{"url":null,"slug":"staining-normalization-in-histopathology","title":"Staining normalization in histopathology: Method benchmarking using multicenter dataset","date":"2025-06-23","arxiv_id":"2506.19106","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-hpc-in-us-research-institutions","title":"Survey of HPC in US Research Institutions","date":"2025-06-23","arxiv_id":"2506.19019","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifiable-convex-concave-regression-via","title":"Identifiable Convex-Concave Regression via Sub-gradient Regularised Least Squares","date":"2025-06-22","arxiv_id":"2506.18078","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-robustness-of-human-object-interaction","title":"On the Robustness of Human-Object Interaction Detection against Distribution Shift","date":"2025-06-22","arxiv_id":"2506.18021","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveling-the-playing-field-carefully","title":"Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking","date":"2025-06-21","arxiv_id":"2506.17832","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-analysis-of-principal-component","title":"A Comparative Analysis of Principal Component Analysis (PCA) and Singular Value Decomposition (SVD) as Dimensionality Reduction Techniques","date":"2025-06-20","arxiv_id":"2506.16663","repositories_listed":0,"syntology":null},{"url":null,"slug":"osworld-human-benchmarking-the-efficiency-of","title":"OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents","date":"2025-06-19","arxiv_id":"2506.16042","repositories_listed":0,"syntology":null},{"url":null,"slug":"spotting-tell-tale-visual-artifacts-in-face","title":"Spotting tell-tale visual artifacts in face swapping videos: strengths and pitfalls of CNN detectors","date":"2025-06-19","arxiv_id":"2506.16497","repositories_listed":0,"syntology":null}],"record_sha256":"fd5726635527f3c74c6b3fcd902430cf1abc5f5fe7b778004d3264c9ad365ed2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}