{"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/image-classification/papers/44","list_of":"/task/image-classification","task":"Image Classification","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":44,"pages_in_order":105,"rows_per_page":100,"rows":[4301,4400],"of":10488,"counts":{"archive_papers_tagged":10488,"with_a_code_link":4702,"where_syntology_ran_a_sample":1392,"not_listed_spam_title":0,"listed":10488,"listed_where_code_ran":1392,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1164,"every_run_a_failure_of_syntologys_instrument":228,"listed_with_a_run_with_no_instrument_failure":1164,"listed_every_run_a_failure_of_syntologys_instrument":228,"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/image-classification","prev":"/task/image-classification/papers/43","next":"/task/image-classification/papers/45","papers":[{"url":"/paper/single-bit-per-weight-deep-convolutional","slug":"single-bit-per-weight-deep-convolutional","title":"Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems","date":"2019-07-16","arxiv_id":"1907.06916","repositories_listed":1,"syntology":null},{"url":"/paper/batch-shaped-channel-gated-networks","slug":"batch-shaped-channel-gated-networks","title":"Batch-Shaping for Learning Conditional Channel Gated Networks","date":"2019-07-15","arxiv_id":"1907.06627","repositories_listed":1,"syntology":null},{"url":"/paper/multiscale-principle-of-relevant-information","slug":"multiscale-principle-of-relevant-information","title":"Multiscale Principle of Relevant Information for Hyperspectral Image Classification","date":"2019-07-13","arxiv_id":"1907.06022","repositories_listed":1,"syntology":null},{"url":"/paper/towards-debugging-deep-neural-networks-by","slug":"towards-debugging-deep-neural-networks-by","title":"Towards Debugging Deep Neural Networks by Generating Speech Utterances","date":"2019-07-06","arxiv_id":"1907.03164","repositories_listed":1,"syntology":null},{"url":"/paper/blind-image-quality-assessment-using-a-deep","slug":"blind-image-quality-assessment-using-a-deep","title":"Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network","date":"2019-07-05","arxiv_id":"1907.02665","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/blind-image-quality-assessment-using-a-deep#ran","syntology_url":"https://syntology.ai/paper/1907.02665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.02665"}},"official":{"repos":["zwx8981/DBCNN-PyTorch"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/domain-adaptation-via-low-rank-basis","slug":"domain-adaptation-via-low-rank-basis","title":"Low-Rank Subspace Override for Unsupervised Domain Adaptation","date":"2019-07-02","arxiv_id":"1907.01343","repositories_listed":1,"syntology":null},{"url":"/paper/an-automated-ensemble-learning-framework","slug":"an-automated-ensemble-learning-framework","title":"An Automated Ensemble Learning Framework Using Genetic Programming for Image Classification","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generating-natural-language-adversarial-2","slug":"generating-natural-language-adversarial-2","title":"Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/single-path-mobile-automl-efficient-convnet","slug":"single-path-mobile-automl-efficient-convnet","title":"Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization","date":"2019-07-01","arxiv_id":"1907.00959","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-predictive-coding-models-may","slug":"unsupervised-predictive-coding-models-may","title":"Unsupervised predictive coding models may explain visual brain representation","date":"2019-06-30","arxiv_id":"1907.00441","repositories_listed":1,"syntology":null},{"url":"/paper/convolution-based-spectral-partitioning","slug":"convolution-based-spectral-partitioning","title":"Convolution Based Spectral Partitioning Architecture for Hyperspectral Image Classification","date":"2019-06-27","arxiv_id":"1906.11981","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-notion-of-number-in-humans-and","slug":"on-the-notion-of-number-in-humans-and","title":"On the notion of number in humans and machines","date":"2019-06-27","arxiv_id":"1906.12213","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-learning-with-self-supervised","slug":"semi-supervised-learning-with-self-supervised","title":"Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning","date":"2019-06-25","arxiv_id":"1906.10343","repositories_listed":1,"syntology":null},{"url":"/paper/densely-connected-search-space-for-more","slug":"densely-connected-search-space-for-more","title":"Densely Connected Search Space for More Flexible Neural Architecture Search","date":"2019-06-23","arxiv_id":"1906.09607","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/densely-connected-search-space-for-more#ran","syntology_url":"https://syntology.ai/paper/1906.09607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.09607"}},"official":{"repos":["JaminFong/DenseNAS"],"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/one-shot-neural-architecture-search-through-a","slug":"one-shot-neural-architecture-search-through-a","title":"Posterior-Guided Neural Architecture Search","date":"2019-06-23","arxiv_id":"1906.09557","repositories_listed":1,"syntology":null},{"url":"/paper/the-functional-neural-process","slug":"the-functional-neural-process","title":"The Functional Neural Process","date":"2019-06-19","arxiv_id":"1906.08324","repositories_listed":1,"syntology":null},{"url":"/paper/vip-virtual-pooling-for-accelerating-cnn","slug":"vip-virtual-pooling-for-accelerating-cnn","title":"ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection","date":"2019-06-19","arxiv_id":"1906.07912","repositories_listed":1,"syntology":null},{"url":"/paper/fast-and-flexible-multi-task-classification","slug":"fast-and-flexible-multi-task-classification","title":"Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes","date":"2019-06-18","arxiv_id":"1906.07697","repositories_listed":1,"syntology":null},{"url":"/paper/equivariant-neural-networks-and","slug":"equivariant-neural-networks-and","title":"Equivariant neural networks and equivarification","date":"2019-06-16","arxiv_id":"1906.07172","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/equivariant-neural-networks-and#ran","syntology_url":"https://syntology.ai/paper/1906.07172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.07172"}},"official":{"repos":["symplecticgeometry/equivariant-neural-networks-and-equivarification"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/selfie-refurbishing-unclean-samples-for","slug":"selfie-refurbishing-unclean-samples-for","title":"SELFIE: Refurbishing Unclean Samples for Robust Deep Learning","date":"2019-06-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-signal-propagation-perspective-for-pruning","slug":"a-signal-propagation-perspective-for-pruning","title":"A Signal Propagation Perspective for Pruning Neural Networks at Initialization","date":"2019-06-14","arxiv_id":"1906.06307","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/a-signal-propagation-perspective-for-pruning#ran","syntology_url":"https://syntology.ai/paper/1906.06307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.06307"}},"official":{"repos":["namhoonlee/spp-public"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/model-agnostic-dual-quality-assessment-for","slug":"model-agnostic-dual-quality-assessment-for","title":"Adversarial Robustness Assessment: Why both $L_0$ and $L_\\infty$ Attacks Are Necessary","date":"2019-06-14","arxiv_id":"1906.06026","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-development-environment-in","slug":"deep-learning-development-environment-in","title":"Deep Learning Development Environment in Virtual Reality","date":"2019-06-13","arxiv_id":"1906.05925","repositories_listed":1,"syntology":null},{"url":"/paper/the-imaterialist-fashion-attribute-dataset","slug":"the-imaterialist-fashion-attribute-dataset","title":"The iMaterialist Fashion Attribute Dataset","date":"2019-06-13","arxiv_id":"1906.05750","repositories_listed":1,"syntology":null},{"url":"/paper/continual-and-multi-task-architecture-search","slug":"continual-and-multi-task-architecture-search","title":"Continual and Multi-Task Architecture Search","date":"2019-06-12","arxiv_id":"1906.05226","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continual-and-multi-task-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1906.05226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05226"}},"official":{"repos":["ramakanth-pasunuru/CAS-MAS"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/weight-agnostic-neural-networks","slug":"weight-agnostic-neural-networks","title":"Weight Agnostic Neural Networks","date":"2019-06-11","arxiv_id":"1906.04358","repositories_listed":1,"syntology":null},{"url":"/paper/bdnet-bengali-handwritten-numeral-digit","slug":"bdnet-bengali-handwritten-numeral-digit","title":"BDNet: Bengali Handwritten Numeral Digit Recognition based on Densely connected Convolutional Neural Networks","date":"2019-06-10","arxiv_id":"1906.03786","repositories_listed":1,"syntology":null},{"url":"/paper/simultaneous-classification-and-novelty","slug":"simultaneous-classification-and-novelty","title":"Outlier Exposure with Confidence Control for Out-of-Distribution Detection","date":"2019-06-08","arxiv_id":"1906.03509","repositories_listed":1,"syntology":null},{"url":"/paper/cell-image-classification-a-comparative","slug":"cell-image-classification-a-comparative","title":"Cell image classification: a comparative overview","date":"2019-06-07","arxiv_id":"1906.03316","repositories_listed":1,"syntology":null},{"url":"/paper/reliable-classification-explanations-via","slug":"reliable-classification-explanations-via","title":"Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network Robustness","date":"2019-06-07","arxiv_id":"1906.02896","repositories_listed":1,"syntology":null},{"url":"/paper/resampling-based-assessment-of-robustness-to","slug":"resampling-based-assessment-of-robustness-to","title":"Variational Resampling Based Assessment of Deep Neural Networks under Distribution Shift","date":"2019-06-07","arxiv_id":"1906.02972","repositories_listed":1,"syntology":null},{"url":"/paper/tensornetwork-for-machine-learning","slug":"tensornetwork-for-machine-learning","title":"TensorNetwork for Machine Learning","date":"2019-06-07","arxiv_id":"1906.06329","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tensornetwork-for-machine-learning#ran","syntology_url":"https://syntology.ai/paper/1906.06329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.06329"}},"official":{"repos":["google/TensorNetwork"],"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/bad-global-minima-exist-and-sgd-can-reach","slug":"bad-global-minima-exist-and-sgd-can-reach","title":"Bad Global Minima Exist and SGD Can Reach Them","date":"2019-06-06","arxiv_id":"1906.02613","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/bad-global-minima-exist-and-sgd-can-reach#ran","syntology_url":"https://syntology.ai/paper/1906.02613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02613"}},"official":{"repos":["chao1224/BadGlobalMinima"],"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/robust-attacks-against-multiple-classifiers","slug":"robust-attacks-against-multiple-classifiers","title":"Robust Attacks against Multiple Classifiers","date":"2019-06-06","arxiv_id":"1906.02816","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/robust-attacks-against-multiple-classifiers#ran","syntology_url":"https://syntology.ai/paper/1906.02816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02816"}},"official":{"repos":["jcperdomo/robust_attacks"],"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/pi-net-a-deep-learning-approach-to-extract","slug":"pi-net-a-deep-learning-approach-to-extract","title":"PI-Net: A Deep Learning Approach to Extract Topological Persistence Images","date":"2019-06-05","arxiv_id":"1906.01769","repositories_listed":1,"syntology":null},{"url":"/paper/geo-aware-networks-for-fine-grained","slug":"geo-aware-networks-for-fine-grained","title":"Geo-Aware Networks for Fine-Grained Recognition","date":"2019-06-04","arxiv_id":"1906.01737","repositories_listed":1,"syntology":null},{"url":"/paper/information-competing-process-for-learning","slug":"information-competing-process-for-learning","title":"Information Competing Process for Learning Diversified Representations","date":"2019-06-04","arxiv_id":"1906.01288","repositories_listed":1,"syntology":null},{"url":"/paper/pca-driven-hybrid-network-design-for-enabling","slug":"pca-driven-hybrid-network-design-for-enabling","title":"Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge Intelligence","date":"2019-06-04","arxiv_id":"1906.01493","repositories_listed":1,"syntology":null},{"url":"/paper/190600675","slug":"190600675","title":"Deeply-supervised Knowledge Synergy","date":"2019-06-03","arxiv_id":"1906.00675","repositories_listed":1,"syntology":null},{"url":"/paper/190600204","slug":"190600204","title":"Perceptual Evaluation of Adversarial Attacks for CNN-based Image Classification","date":"2019-06-01","arxiv_id":"1906.00204","repositories_listed":1,"syntology":null},{"url":"/paper/190600297","slug":"190600297","title":"GANchors: Realistic Image Perturbation Distributions for Anchors Using Generative Models","date":"2019-06-01","arxiv_id":"1906.00297","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-object-detectors-via-selective-cross","slug":"adapting-object-detectors-via-selective-cross","title":"Adapting Object Detectors via Selective Cross-Domain Alignment","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/detecting-anomalies-in-image-classification","slug":"detecting-anomalies-in-image-classification","title":"Detecting Anomalies in Image Classification by Means of Semantic Relationships","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/structured-knowledge-distillation-for-1","slug":"structured-knowledge-distillation-for-1","title":"Structured Knowledge Distillation for Semantic Segmentation","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/visual-attention-consistency-under-image","slug":"visual-attention-consistency-under-image","title":"Visual Attention Consistency Under Image Transforms for Multi-Label Image Classification","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fast-solar-image-classification-using-deep","slug":"fast-solar-image-classification-using-deep","title":"Fast Solar Image Classification Using Deep Learning and its Importance for Automation in Solar Physics","date":"2019-05-31","arxiv_id":"1905.13575","repositories_listed":1,"syntology":null},{"url":"/paper/reverse-kl-divergence-training-of-prior","slug":"reverse-kl-divergence-training-of-prior","title":"Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness","date":"2019-05-31","arxiv_id":"1905.13472","repositories_listed":1,"syntology":null},{"url":"/paper/characterizing-bias-in-classifiers-using","slug":"characterizing-bias-in-classifiers-using","title":"Characterizing Bias in Classifiers using Generative Models","date":"2019-05-30","arxiv_id":"1906.11891","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/characterizing-bias-in-classifiers-using#ran","syntology_url":"https://syntology.ai/paper/1906.11891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.11891"}},"official":{"repos":["danmcduff/characterizingBias"],"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/empirically-measuring-concentration","slug":"empirically-measuring-concentration","title":"Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness","date":"2019-05-29","arxiv_id":"1905.12202","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/empirically-measuring-concentration#ran","syntology_url":"https://syntology.ai/paper/1905.12202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12202"}},"official":{"repos":["xiaozhanguva/Measure-Concentration"],"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/analysis-of-gradient-clipping-and-adaptive","slug":"analysis-of-gradient-clipping-and-adaptive","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","date":"2019-05-28","arxiv_id":"1905.11881","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"4 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/analysis-of-gradient-clipping-and-adaptive#ran","syntology_url":"https://syntology.ai/paper/1905.11881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11881"}},"official":{"repos":["JingzhaoZhang/why-clipping-accelerates"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bayesian-nonparametric-federated-learning-of","slug":"bayesian-nonparametric-federated-learning-of","title":"Bayesian Nonparametric Federated Learning of Neural Networks","date":"2019-05-28","arxiv_id":"1905.12022","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":0,"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/bayesian-nonparametric-federated-learning-of#ran","syntology_url":"https://syntology.ai/paper/1905.12022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12022"}},"official":{"repos":["IBM/probabilistic-federated-neural-matching"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/compactnet-platform-aware-automatic","slug":"compactnet-platform-aware-automatic","title":"CompactNet: Platform-Aware Automatic Optimization for Convolutional Neural Networks","date":"2019-05-28","arxiv_id":"1905.11669","repositories_listed":1,"syntology":null},{"url":"/paper/differential-privacy-has-disparate-impact-on","slug":"differential-privacy-has-disparate-impact-on","title":"Differential Privacy Has Disparate Impact on Model Accuracy","date":"2019-05-28","arxiv_id":"1905.12101","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/differential-privacy-has-disparate-impact-on#ran","syntology_url":"https://syntology.ai/paper/1905.12101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12101"}},"official":{"repos":["ebagdasa/differential-privacy-vs-fairness"],"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/capsule-routing-via-variational-bayes","slug":"capsule-routing-via-variational-bayes","title":"Capsule Routing via Variational Bayes","date":"2019-05-27","arxiv_id":"1905.11455","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/capsule-routing-via-variational-bayes#ran","syntology_url":"https://syntology.ai/paper/1905.11455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11455"}},"official":{"repos":["fabio-deep/Variational-Capsule-Routing"],"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/probact-a-probabilistic-activation-function","slug":"probact-a-probabilistic-activation-function","title":"ProbAct: A Probabilistic Activation Function for Deep Neural Networks","date":"2019-05-26","arxiv_id":"1905.10761","repositories_listed":1,"syntology":null},{"url":"/paper/why-do-these-match-explaining-the-behavior-of","slug":"why-do-these-match-explaining-the-behavior-of","title":"Why do These Match? Explaining the Behavior of Image Similarity Models","date":"2019-05-26","arxiv_id":"1905.10797","repositories_listed":1,"syntology":null},{"url":"/paper/bivariate-beta-lstm","slug":"bivariate-beta-lstm","title":"Bivariate Beta-LSTM","date":"2019-05-25","arxiv_id":"1905.10521","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/bivariate-beta-lstm#ran","syntology_url":"https://syntology.ai/paper/1905.10521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.10521"}},"official":{"repos":["gtshs2/BetaLSTM"],"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/cold-case-the-lost-mnist-digits","slug":"cold-case-the-lost-mnist-digits","title":"Cold Case: The Lost MNIST Digits","date":"2019-05-25","arxiv_id":"1905.10498","repositories_listed":1,"syntology":null},{"url":"/paper/additive-noise-annealing-and-approximation","slug":"additive-noise-annealing-and-approximation","title":"Additive Noise Annealing and Approximation Properties of Quantized Neural Networks","date":"2019-05-24","arxiv_id":"1905.10452","repositories_listed":1,"syntology":null},{"url":"/paper/x-traincaps-accelerated-training-of-capsule","slug":"x-traincaps-accelerated-training-of-capsule","title":"FasTrCaps: An Integrated Framework for Fast yet Accurate Training of Capsule Networks","date":"2019-05-24","arxiv_id":"1905.10142","repositories_listed":1,"syntology":null},{"url":"/paper/a-direct-approach-to-robust-deep-learning-1","slug":"a-direct-approach-to-robust-deep-learning-1","title":"A Direct Approach to Robust Deep Learning Using Adversarial Networks","date":"2019-05-23","arxiv_id":"1905.09591","repositories_listed":1,"syntology":{"n":15,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":12,"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) · 12 unverified","sample_list":"/paper/a-direct-approach-to-robust-deep-learning-1#ran","syntology_url":"https://syntology.ai/paper/1905.09591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09591"}},"official":{"repos":["whxbergkamp/RobustDL_GAN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/dual-active-sampling-on-batch-incremental","slug":"dual-active-sampling-on-batch-incremental","title":"Dual Active Sampling on Batch-Incremental Active Learning","date":"2019-05-22","arxiv_id":"1905.09247","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-optimization-of-deep-neural","slug":"fine-grained-optimization-of-deep-neural","title":"Fine-grained Optimization of Deep Neural Networks","date":"2019-05-22","arxiv_id":"1905.09054","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-stochastic-natural-gradient-method","slug":"adaptive-stochastic-natural-gradient-method","title":"Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search","date":"2019-05-21","arxiv_id":"1905.08537","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/adaptive-stochastic-natural-gradient-method#ran","syntology_url":"https://syntology.ai/paper/1905.08537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08537"}},"official":{"repos":["shirakawas/ASNG-NAS"],"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/testing-deep-neural-network-based-image","slug":"testing-deep-neural-network-based-image","title":"Testing DNN Image Classifiers for Confusion & Bias Errors","date":"2019-05-20","arxiv_id":"1905.07831","repositories_listed":1,"syntology":null},{"url":"/paper/spectral-metric-for-dataset-complexity","slug":"spectral-metric-for-dataset-complexity","title":"Spectral Metric for Dataset Complexity Assessment","date":"2019-05-17","arxiv_id":"1905.07299","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-based-detection-of-diabetic","slug":"transfer-learning-based-detection-of-diabetic","title":"Transfer Learning based Detection of Diabetic Retinopathy from Small Dataset","date":"2019-05-17","arxiv_id":"1905.07203","repositories_listed":1,"syntology":null},{"url":"/paper/joint-learning-of-neural-networks-via","slug":"joint-learning-of-neural-networks-via","title":"Joint Learning of Neural Networks via Iterative Reweighted Least Squares","date":"2019-05-16","arxiv_id":"1905.06526","repositories_listed":1,"syntology":null},{"url":"/paper/paganda-an-adaptive-task-independent","slug":"paganda-an-adaptive-task-independent","title":"PAGANDA: An Adaptive Task-Independent Automatic Data Augmentation","date":"2019-05-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bira-net-bilinear-attention-net-for-diabetic","slug":"bira-net-bilinear-attention-net-for-diabetic","title":"BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading","date":"2019-05-15","arxiv_id":"1905.06312","repositories_listed":1,"syntology":null},{"url":"/paper/online-normalization-for-training-neural","slug":"online-normalization-for-training-neural","title":"Online Normalization for Training Neural Networks","date":"2019-05-15","arxiv_id":"1905.05894","repositories_listed":1,"syntology":{"n":16,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":7,"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) · 7 unverified","sample_list":"/paper/online-normalization-for-training-neural#ran","syntology_url":"https://syntology.ai/paper/1905.05894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05894"}},"official":{"repos":["cerebras/online-normalization"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/orthogonal-deep-neural-networks","slug":"orthogonal-deep-neural-networks","title":"Orthogonal Deep Neural Networks","date":"2019-05-15","arxiv_id":"1905.05929","repositories_listed":1,"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":1,"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/orthogonal-deep-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1905.05929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.05929"}},"official":null}},{"url":"/paper/multi-scale-dynamic-graph-convolutional","slug":"multi-scale-dynamic-graph-convolutional","title":"Multi-scale Dynamic Graph Convolutional Network for Hyperspectral Image Classification","date":"2019-05-14","arxiv_id":"1905.06133","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchically-structured-meta-learning","slug":"hierarchically-structured-meta-learning","title":"Hierarchically Structured Meta-learning","date":"2019-05-13","arxiv_id":"1905.05301","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-image-classification-via","slug":"multi-agent-image-classification-via","title":"Multi-Agent Image Classification via Reinforcement Learning","date":"2019-05-13","arxiv_id":"1905.04835","repositories_listed":1,"syntology":null},{"url":"/paper/breast-cancer-image-classification-on-wsi","slug":"breast-cancer-image-classification-on-wsi","title":"Breast cancer image classification on WSI with spatial correlations","date":"2019-05-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/budgeted-training-rethinking-deep-neural","slug":"budgeted-training-rethinking-deep-neural","title":"Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints","date":"2019-05-12","arxiv_id":"1905.04753","repositories_listed":1,"syntology":null},{"url":"/paper/190503670","slug":"190503670","title":"S4L: Self-Supervised Semi-Supervised Learning","date":"2019-05-09","arxiv_id":"1905.03670","repositories_listed":1,"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":19,"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/190503670#ran","syntology_url":"https://syntology.ai/paper/1905.03670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.03670"}},"official":null}},{"url":"/paper/190503333","slug":"190503333","title":"Enhancing Cross-task Transferability of Adversarial Examples with Dispersion Reduction","date":"2019-05-08","arxiv_id":"1905.03333","repositories_listed":1,"syntology":null},{"url":"/paper/190503381","slug":"190503381","title":"AutoAssist: A Framework to Accelerate Training of Deep Neural Networks","date":"2019-05-08","arxiv_id":"1905.03381","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":0,"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/190503381#ran","syntology_url":"https://syntology.ai/paper/1905.03381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.03381"}},"official":null}},{"url":"/paper/skin-lesion-classification-using-cnns-with","slug":"skin-lesion-classification-using-cnns-with","title":"Skin Lesion Classification Using CNNs with Patch-Based Attention and Diagnosis-Guided Loss Weighting","date":"2019-05-07","arxiv_id":"1905.02793","repositories_listed":1,"syntology":null},{"url":"/paper/deep-visual-city-recognition-visualization","slug":"deep-visual-city-recognition-visualization","title":"Deep Visual City Recognition Visualization","date":"2019-05-06","arxiv_id":"1905.01932","repositories_listed":1,"syntology":null},{"url":"/paper/learning-optimal-data-augmentation-policies","slug":"learning-optimal-data-augmentation-policies","title":"Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification Tasks","date":"2019-05-06","arxiv_id":"1905.02610","repositories_listed":1,"syntology":null},{"url":"/paper/displacenet-recognising-displaced-people-from","slug":"displacenet-recognising-displaced-people-from","title":"DisplaceNet: Recognising Displaced People from Images by Exploiting Dominance Level","date":"2019-05-03","arxiv_id":"1905.02025","repositories_listed":1,"syntology":null},{"url":"/paper/a-synaptic-neural-network-and-synapse","slug":"a-synaptic-neural-network-and-synapse","title":"A Synaptic Neural Network and Synapse Learning","date":"2019-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/causal-importance-of-orientation-selectivity","slug":"causal-importance-of-orientation-selectivity","title":"Causal importance of orientation selectivity for generalization in image recognition","date":"2019-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/harmonic-networks-with-limited-training","slug":"harmonic-networks-with-limited-training","title":"Harmonic Networks with Limited Training Samples","date":"2019-04-30","arxiv_id":"1905.00135","repositories_listed":1,"syntology":null},{"url":"/paper/domain-agnostic-learning-with-disentangled","slug":"domain-agnostic-learning-with-disentangled","title":"Domain Agnostic Learning with Disentangled Representations","date":"2019-04-28","arxiv_id":"1904.12347","repositories_listed":1,"syntology":null},{"url":"/paper/analysis-of-confident-classifiers-for-out-of","slug":"analysis-of-confident-classifiers-for-out-of","title":"Analysis of Confident-Classifiers for Out-of-distribution Detection","date":"2019-04-27","arxiv_id":"1904.12220","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-deep-learning-by-neighbourhood","slug":"unsupervised-deep-learning-by-neighbourhood","title":"Unsupervised Deep Learning by Neighbourhood Discovery","date":"2019-04-25","arxiv_id":"1904.11567","repositories_listed":1,"syntology":null},{"url":"/paper/190411093","slug":"190411093","title":"Deep Sparse Representation-based Classification","date":"2019-04-24","arxiv_id":"1904.11093","repositories_listed":1,"syntology":null},{"url":"/paper/switchable-whitening-for-deep-representation","slug":"switchable-whitening-for-deep-representation","title":"Switchable Whitening for Deep Representation Learning","date":"2019-04-22","arxiv_id":"1904.09739","repositories_listed":1,"syntology":{"n":10,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/switchable-whitening-for-deep-representation#ran","syntology_url":"https://syntology.ai/paper/1904.09739","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09739"}},"official":{"repos":["XingangPan/Switchable-Whitening"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/190409460","slug":"190409460","title":"Data-Driven Neuron Allocation for Scale Aggregation Networks","date":"2019-04-20","arxiv_id":"1904.09460","repositories_listed":1,"syntology":null},{"url":"/paper/sparseout-controlling-sparsity-in-deep","slug":"sparseout-controlling-sparsity-in-deep","title":"Sparseout: Controlling Sparsity in Deep Networks","date":"2019-04-17","arxiv_id":"1904.08050","repositories_listed":1,"syntology":null},{"url":"/paper/counterfactual-visual-explanations","slug":"counterfactual-visual-explanations","title":"Counterfactual Visual Explanations","date":"2019-04-16","arxiv_id":"1904.07451","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-loss-function-for-cnn-classifier-based","slug":"a-new-loss-function-for-cnn-classifier-based","title":"A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroids","date":"2019-04-12","arxiv_id":"1904.06008","repositories_listed":1,"syntology":null},{"url":"/paper/big-but-imperceptible-adversarial","slug":"big-but-imperceptible-adversarial","title":"Unrestricted Adversarial Examples via Semantic Manipulation","date":"2019-04-12","arxiv_id":"1904.06347","repositories_listed":1,"syntology":null},{"url":"/paper/automated-search-for-configurations-of-deep","slug":"automated-search-for-configurations-of-deep","title":"Automated Search for Configurations of Deep Neural Network Architectures","date":"2019-04-09","arxiv_id":"1904.04612","repositories_listed":1,"syntology":null},{"url":"/paper/punch-positive-unlabelled-classification","slug":"punch-positive-unlabelled-classification","title":"PUNCH: Positive UNlabelled Classification based information retrieval in Hyperspectral images","date":"2019-04-09","arxiv_id":"1904.04547","repositories_listed":1,"syntology":null},{"url":"/paper/towards-analyzing-semantic-robustness-of-deep","slug":"towards-analyzing-semantic-robustness-of-deep","title":"Towards Analyzing Semantic Robustness of Deep Neural Networks","date":"2019-04-09","arxiv_id":"1904.04621","repositories_listed":1,"syntology":null}],"record_sha256":"b7c606c2ede0b4b0bb3f80f20f86f273242bf3f8e1df71bd90a18671865aaae4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}