{"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/classification/papers/21","list_of":"/task/classification","task":"General 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":21,"pages_in_order":146,"rows_per_page":100,"rows":[2001,2100],"of":14581,"counts":{"archive_papers_tagged":14581,"with_a_code_link":3945,"where_syntology_ran_a_sample":713,"not_listed_spam_title":0,"listed":14581,"listed_where_code_ran":713,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":560,"every_run_a_failure_of_syntologys_instrument":153,"listed_with_a_run_with_no_instrument_failure":560,"listed_every_run_a_failure_of_syntologys_instrument":153,"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/classification","prev":"/task/classification/papers/20","next":"/task/classification/papers/22","papers":[{"url":"/paper/aideveloper-deep-learning-image","slug":"aideveloper-deep-learning-image","title":"AIDeveloper: deep learning image classification in life science and beyond","date":"2020-03-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/factorized-graph-representations-for-semi","slug":"factorized-graph-representations-for-semi","title":"Factorized Graph Representations for Semi-Supervised Learning from Sparse Data","date":"2020-03-05","arxiv_id":"2003.02829","repositories_listed":1,"syntology":null},{"url":"/paper/feature-extraction-for-hyperspectral-imagery","slug":"feature-extraction-for-hyperspectral-imagery","title":"Feature Extraction for Hyperspectral Imagery: The Evolution from Shallow to Deep (Overview and Toolbox)","date":"2020-03-05","arxiv_id":"2003.02822","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-performance-of-deep-learning-models","slug":"on-the-performance-of-deep-learning-models","title":"On the performance of deep learning models for time series classification in streaming","date":"2020-03-05","arxiv_id":"2003.02544","repositories_listed":1,"syntology":null},{"url":"/paper/pac-bayesian-meta-learning-with-implicit","slug":"pac-bayesian-meta-learning-with-implicit","title":"PAC-Bayes meta-learning with implicit task-specific posteriors","date":"2020-03-05","arxiv_id":"2003.02455","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/pac-bayesian-meta-learning-with-implicit#ran","syntology_url":"https://syntology.ai/paper/2003.02455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02455"}},"official":{"repos":["cnguyen10/few_shot_meta_learning"],"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/nonlinear-time-series-classification-using","slug":"nonlinear-time-series-classification-using","title":"Nonlinear Time Series Classification Using Bispectrum-based Deep Convolutional Neural Networks","date":"2020-03-04","arxiv_id":"2003.02353","repositories_listed":1,"syntology":null},{"url":"/paper/reduced-dilation-erosion-perceptron-for","slug":"reduced-dilation-erosion-perceptron-for","title":"Reduced Dilation-Erosion Perceptron for Binary Classification","date":"2020-03-04","arxiv_id":"2003.02306","repositories_listed":1,"syntology":null},{"url":"/paper/sememnn-a-semantic-matrix-based-memory-neural","slug":"sememnn-a-semantic-matrix-based-memory-neural","title":"SeMemNN: A Semantic Matrix-Based Memory Neural Network for Text Classification","date":"2020-03-04","arxiv_id":"2003.01857","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-zero-shot-video-classification-end","slug":"rethinking-zero-shot-video-classification-end","title":"Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications","date":"2020-03-03","arxiv_id":"2003.01455","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/rethinking-zero-shot-video-classification-end#ran","syntology_url":"https://syntology.ai/paper/2003.01455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01455"}},"official":{"repos":["bbrattoli/ZeroShotVideoClassification"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/fast-predictive-uncertainty-for","slug":"fast-predictive-uncertainty-for","title":"Fast Predictive Uncertainty for Classification with Bayesian Deep Networks","date":"2020-03-02","arxiv_id":"2003.01227","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fast-predictive-uncertainty-for#ran","syntology_url":"https://syntology.ai/paper/2003.01227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01227"}},"official":{"repos":["mariushobbhahn/LB_for_BNNs_official"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/intra-3d-intracranial-aneurysm-dataset-for","slug":"intra-3d-intracranial-aneurysm-dataset-for","title":"IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning","date":"2020-03-02","arxiv_id":"2003.02920","repositories_listed":1,"syntology":null},{"url":"/paper/novelty-prepared-few-shot-classification","slug":"novelty-prepared-few-shot-classification","title":"Novelty-Prepared Few-Shot Classification","date":"2020-03-01","arxiv_id":"2003.00497","repositories_listed":1,"syntology":null},{"url":"/paper/depth-adaptive-graph-recurrent-network-for","slug":"depth-adaptive-graph-recurrent-network-for","title":"Depth-Adaptive Graph Recurrent Network for Text Classification","date":"2020-02-29","arxiv_id":"2003.00166","repositories_listed":1,"syntology":null},{"url":"/paper/drocc-deep-robust-one-class-classification","slug":"drocc-deep-robust-one-class-classification","title":"DROCC: Deep Robust One-Class Classification","date":"2020-02-28","arxiv_id":"2002.12718","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/drocc-deep-robust-one-class-classification#ran","syntology_url":"https://syntology.ai/paper/2002.12718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12718"}},"official":{"repos":["Microsoft/EdgeML"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/brain-inspired-model-for-incremental-learning","slug":"brain-inspired-model-for-incremental-learning","title":"Cognitively-Inspired Model for Incremental Learning Using a Few Examples","date":"2020-02-27","arxiv_id":"2002.12411","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-learning-on-graphs-via-super-classes-1","slug":"few-shot-learning-on-graphs-via-super-classes-1","title":"Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures","date":"2020-02-27","arxiv_id":"2002.12815","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-learning-on-graphs-via-super-classes-1#ran","syntology_url":"https://syntology.ai/paper/2002.12815","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12815"}},"official":{"repos":["chauhanjatin10/GraphsFewShot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/membership-inference-attacks-and-defenses-in","slug":"membership-inference-attacks-and-defenses-in","title":"Membership Inference Attacks and Defenses in Classification Models","date":"2020-02-27","arxiv_id":"2002.12062","repositories_listed":1,"syntology":null},{"url":"/paper/the-data-representativeness-criterion","slug":"the-data-representativeness-criterion","title":"The Data Representativeness Criterion: Predicting the Performance of Supervised Classification Based on Data Set Similarity","date":"2020-02-27","arxiv_id":"2002.12105","repositories_listed":1,"syntology":null},{"url":"/paper/triangle-net-towards-robustness-in-point","slug":"triangle-net-towards-robustness-in-point","title":"Triangle-Net: Towards Robustness in Point Cloud Learning","date":"2020-02-27","arxiv_id":"2003.00856","repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-unsupervised-feature-learning-spiking","slug":"a-deep-unsupervised-feature-learning-spiking","title":"A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow","date":"2020-02-26","arxiv_id":"2002.11843","repositories_listed":1,"syntology":null},{"url":"/paper/a-quadruplet-loss-for-enforcing-semantically","slug":"a-quadruplet-loss-for-enforcing-semantically","title":"A Quadruplet Loss for Enforcing Semantically Coherent Embeddings in Multi-output Classification Problems","date":"2020-02-26","arxiv_id":"2002.11644","repositories_listed":1,"syntology":null},{"url":"/paper/an-open-set-recognition-and-few-shot-learning","slug":"an-open-set-recognition-and-few-shot-learning","title":"An Open-set Recognition and Few-Shot Learning Dataset for Audio Event Classification in Domestic Environments","date":"2020-02-26","arxiv_id":"2002.11561","repositories_listed":1,"syntology":null},{"url":"/paper/fake-review-detection-using-behavioral-and","slug":"fake-review-detection-using-behavioral-and","title":"Fake Review Detection Using Behavioral and Contextual Features","date":"2020-02-26","arxiv_id":"2003.00807","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-the-route-towards-weakly","slug":"rethinking-the-route-towards-weakly","title":"Rethinking the Route Towards Weakly Supervised Object Localization","date":"2020-02-26","arxiv_id":"2002.11359","repositories_listed":1,"syntology":null},{"url":"/paper/diversity-based-generalization-for-neural","slug":"diversity-based-generalization-for-neural","title":"Diversity-Based Generalization for Unsupervised Text Classification under Domain Shift","date":"2020-02-25","arxiv_id":"2002.10937","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-neural-diarization-reformulating","slug":"end-to-end-neural-diarization-reformulating","title":"End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification","date":"2020-02-24","arxiv_id":"2003.02966","repositories_listed":1,"syntology":null},{"url":"/paper/learning-attentive-pairwise-interaction-for","slug":"learning-attentive-pairwise-interaction-for","title":"Learning Attentive Pairwise Interaction for Fine-Grained Classification","date":"2020-02-24","arxiv_id":"2002.10191","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/learning-attentive-pairwise-interaction-for#ran","syntology_url":"https://syntology.ai/paper/2002.10191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10191"}},"official":null}},{"url":"/paper/scheduled-restart-momentum-for-accelerated","slug":"scheduled-restart-momentum-for-accelerated","title":"Scheduled Restart Momentum for Accelerated Stochastic Gradient Descent","date":"2020-02-24","arxiv_id":"2002.10583","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/scheduled-restart-momentum-for-accelerated#ran","syntology_url":"https://syntology.ai/paper/2002.10583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10583"}},"official":{"repos":["minhtannguyen/SRSGD"],"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/sketchformer-transformer-based-representation","slug":"sketchformer-transformer-based-representation","title":"Sketchformer: Transformer-based Representation for Sketched Structure","date":"2020-02-24","arxiv_id":"2002.10381","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/sketchformer-transformer-based-representation#ran","syntology_url":"https://syntology.ai/paper/2002.10381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10381"}},"official":null}},{"url":"/paper/using-wavelets-to-analyze-similarities-in","slug":"using-wavelets-to-analyze-similarities-in","title":"Using Wavelets to Analyze Similarities in Image-Classification Datasets","date":"2020-02-24","arxiv_id":"2002.10257","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-typed-syntactic-dependencies-for","slug":"exploiting-typed-syntactic-dependencies-for","title":"Investigating Typed Syntactic Dependencies for Targeted Sentiment Classification Using Graph Attention Neural Network","date":"2020-02-22","arxiv_id":"2002.09685","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-covariate-acquisition-for-minimizing","slug":"adaptive-covariate-acquisition-for-minimizing","title":"Adaptive Covariate Acquisition for Minimizing Total Cost of Classification","date":"2020-02-21","arxiv_id":"2002.09162","repositories_listed":1,"syntology":null},{"url":"/paper/maxup-a-simple-way-to-improve-generalization","slug":"maxup-a-simple-way-to-improve-generalization","title":"MaxUp: A Simple Way to Improve Generalization of Neural Network Training","date":"2020-02-20","arxiv_id":"2002.09024","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/maxup-a-simple-way-to-improve-generalization#ran","syntology_url":"https://syntology.ai/paper/2002.09024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09024"}},"official":null}},{"url":"/paper/uncovering-coresets-for-classification-with","slug":"uncovering-coresets-for-classification-with","title":"Uncovering Coresets for Classification With Multi-Objective Evolutionary Algorithms","date":"2020-02-20","arxiv_id":"2002.08645","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-models-vs-transfer-learning-for","slug":"hierarchical-models-vs-transfer-learning-for","title":"A Systematic Comparison of Architectures for Document-Level Sentiment Classification","date":"2020-02-19","arxiv_id":"2002.08131","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-classification-of-enzyme","slug":"hierarchical-classification-of-enzyme","title":"Enzyme promiscuity prediction using hierarchy-informed multi-label classification","date":"2020-02-18","arxiv_id":"2002.07327","repositories_listed":1,"syntology":null},{"url":"/paper/self-enhanced-gnn-improving-graph-neural","slug":"self-enhanced-gnn-improving-graph-neural","title":"Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs","date":"2020-02-18","arxiv_id":"2002.07518","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 5 unverified","sample_list":"/paper/self-enhanced-gnn-improving-graph-neural#ran","syntology_url":"https://syntology.ai/paper/2002.07518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.07518"}},"official":{"repos":["yang-han/Self-Enhanced_GNN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"url":"/paper/query-efficient-physical-hard-label-attacks","slug":"query-efficient-physical-hard-label-attacks","title":"GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systems","date":"2020-02-17","arxiv_id":"2002.07088","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/query-efficient-physical-hard-label-attacks#ran","syntology_url":"https://syntology.ai/paper/2002.07088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.07088"}},"official":{"repos":["ryan-feng/graphite"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unraveling-meta-learning-understanding","slug":"unraveling-meta-learning-understanding","title":"Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks","date":"2020-02-17","arxiv_id":"2002.06753","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/unraveling-meta-learning-understanding#ran","syntology_url":"https://syntology.ai/paper/2002.06753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06753"}},"official":{"repos":["goldblum/FeatureClustering"],"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/breast-cancer-histopathology-image","slug":"breast-cancer-histopathology-image","title":"Breast Cancer Histopathology Image Classification and Localization using Multiple Instance Learning","date":"2020-02-16","arxiv_id":"2003.00823","repositories_listed":1,"syntology":null},{"url":"/paper/extreme-classification-via-adversarial-1","slug":"extreme-classification-via-adversarial-1","title":"Extreme Classification via Adversarial Softmax Approximation","date":"2020-02-15","arxiv_id":"2002.06298","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/extreme-classification-via-adversarial-1#ran","syntology_url":"https://syntology.ai/paper/2002.06298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06298"}},"official":{"repos":["mandt-lab/adversarial-negative-sampling"],"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/automatically-discovering-and-learning-new-1","slug":"automatically-discovering-and-learning-new-1","title":"Automatically Discovering and Learning New Visual Categories with Ranking Statistics","date":"2020-02-13","arxiv_id":"2002.05714","repositories_listed":1,"syntology":null},{"url":"/paper/superpixel-image-classification-with-graph","slug":"superpixel-image-classification-with-graph","title":"Superpixel Image Classification with Graph Attention Networks","date":"2020-02-13","arxiv_id":"2002.05544","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-policy-learning-from-surrogate-loss","slug":"efficient-policy-learning-from-surrogate-loss","title":"Efficient Policy Learning from Surrogate-Loss Classification Reductions","date":"2020-02-12","arxiv_id":"2002.05153","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/efficient-policy-learning-from-surrogate-loss#ran","syntology_url":"https://syntology.ai/paper/2002.05153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05153"}},"official":{"repos":["CausalML/ESPRM"],"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/machine-learning-based-multiple-abnormality","slug":"machine-learning-based-multiple-abnormality","title":"Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes","date":"2020-02-12","arxiv_id":"2002.04752","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/machine-learning-based-multiple-abnormality#ran","syntology_url":"https://syntology.ai/paper/2002.04752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.04752"}},"official":{"repos":["rachellea/ct-net-models"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/patternless-adversarial-attacks-on-video","slug":"patternless-adversarial-attacks-on-video","title":"Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks","date":"2020-02-12","arxiv_id":"2002.05123","repositories_listed":1,"syntology":null},{"url":"/paper/275d-convolutional-neural-network-for","slug":"275d-convolutional-neural-network-for","title":"2.75D: Boosting learning by representing 3D Medical imaging to 2D features for small data","date":"2020-02-11","arxiv_id":"2002.04251","repositories_listed":1,"syntology":null},{"url":"/paper/hyperspectral-classification-based-on-3d","slug":"hyperspectral-classification-based-on-3d","title":"Hyperspectral Classification Based on 3D Asymmetric Inception Network with Data Fusion Transfer Learning","date":"2020-02-11","arxiv_id":"2002.04227","repositories_listed":1,"syntology":null},{"url":"/paper/learning-with-out-of-distribution-data-for","slug":"learning-with-out-of-distribution-data-for","title":"Learning with Out-of-Distribution Data for Audio Classification","date":"2020-02-11","arxiv_id":"2002.04683","repositories_listed":1,"syntology":null},{"url":"/paper/a-computational-approach-to-packet","slug":"a-computational-approach-to-packet","title":"A Computational Approach to Packet Classification","date":"2020-02-10","arxiv_id":"2002.07584","repositories_listed":1,"syntology":null},{"url":"/paper/bilinear-graph-neural-network-with-node","slug":"bilinear-graph-neural-network-with-node","title":"Bilinear Graph Neural Network with Neighbor Interactions","date":"2020-02-10","arxiv_id":"2002.03575","repositories_listed":1,"syntology":null},{"url":"/paper/sparseids-learning-packet-sampling-with","slug":"sparseids-learning-packet-sampling-with","title":"SparseIDS: Learning Packet Sampling with Reinforcement Learning","date":"2020-02-10","arxiv_id":"2002.03872","repositories_listed":1,"syntology":null},{"url":"/paper/robust-binary-classification-with-the-01-loss","slug":"robust-binary-classification-with-the-01-loss","title":"Robust binary classification with the 01 loss","date":"2020-02-09","arxiv_id":"2002.03444","repositories_listed":1,"syntology":null},{"url":"/paper/cifar-10-image-classification-using-feature","slug":"cifar-10-image-classification-using-feature","title":"CIFAR-10 Image Classification Using Feature Ensembles","date":"2020-02-07","arxiv_id":"2002.03846","repositories_listed":1,"syntology":null},{"url":"/paper/subspace-capsule-network","slug":"subspace-capsule-network","title":"Subspace Capsule Network","date":"2020-02-07","arxiv_id":"2002.02924","repositories_listed":1,"syntology":null},{"url":"/paper/detection-and-classification-of-cardiac","slug":"detection-and-classification-of-cardiac","title":"Detection and Classification of Cardiac Arrhythmias by a Challenge-Best Deep Learning Neural Network Model","date":"2020-02-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/on-positive-unlabeled-classification-in-gan","slug":"on-positive-unlabeled-classification-in-gan","title":"On Positive-Unlabeled Classification in GAN","date":"2020-02-04","arxiv_id":"2002.01136","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/on-positive-unlabeled-classification-in-gan#ran","syntology_url":"https://syntology.ai/paper/2002.01136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.01136"}},"official":null}},{"url":"/paper/scalable-end-to-end-recurrent-neural-network","slug":"scalable-end-to-end-recurrent-neural-network","title":"Scalable End-to-end Recurrent Neural Network for Variable star classification","date":"2020-02-03","arxiv_id":"2002.00994","repositories_listed":1,"syntology":null},{"url":"/paper/syn2real-forgery-classification-via","slug":"syn2real-forgery-classification-via","title":"Syn2Real: Forgery Classification via Unsupervised Domain Adaptation","date":"2020-02-03","arxiv_id":"2002.00807","repositories_listed":1,"syntology":null},{"url":"/paper/towards-accurate-vehicle-behaviour","slug":"towards-accurate-vehicle-behaviour","title":"Towards Accurate Vehicle Behaviour Classification With Multi-Relational Graph Convolutional Networks","date":"2020-02-03","arxiv_id":"2002.00786","repositories_listed":1,"syntology":null},{"url":"/paper/dropclass-and-dropadapt-dropping-classes-for","slug":"dropclass-and-dropadapt-dropping-classes-for","title":"DropClass and DropAdapt: Dropping classes for deep speaker representation learning","date":"2020-02-02","arxiv_id":"2002.00453","repositories_listed":1,"syntology":null},{"url":"/paper/classification-of-high-dimensional-motor","slug":"classification-of-high-dimensional-motor","title":"Classification of High-Dimensional Motor Imagery Tasks based on An End-to-end role assigned convolutional neural network","date":"2020-02-01","arxiv_id":"2002.00210","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-model-for-image-classification-with","slug":"efficient-model-for-image-classification-with","title":"Efficient Model for Image Classification With Regularization Tricks","date":"2020-02-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/improving-domain-adapted-sentiment","slug":"improving-domain-adapted-sentiment","title":"Improving Domain-Adapted Sentiment Classification by Deep Adversarial Mutual Learning","date":"2020-02-01","arxiv_id":"2002.00119","repositories_listed":1,"syntology":null},{"url":"/paper/molecule-property-prediction-and-1","slug":"molecule-property-prediction-and-1","title":"Molecule Property Prediction and Classification with Graph Hypernetworks","date":"2020-02-01","arxiv_id":"2002.00240","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/molecule-property-prediction-and-1#ran","syntology_url":"https://syntology.ai/paper/2002.00240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.00240"}},"official":null}},{"url":"/paper/benchmarking-popular-classification-models","slug":"benchmarking-popular-classification-models","title":"Benchmarking Popular Classification Models' Robustness to Random and Targeted Corruptions","date":"2020-01-31","arxiv_id":"2002.00754","repositories_listed":1,"syntology":null},{"url":"/paper/classifying-images-with-few-spikes-per-neuron","slug":"classifying-images-with-few-spikes-per-neuron","title":"Optimized spiking neurons classify images with high accuracy through temporal coding with two spikes","date":"2020-01-31","arxiv_id":"2002.00860","repositories_listed":1,"syntology":null},{"url":"/paper/enhancement-of-short-text-clustering-by","slug":"enhancement-of-short-text-clustering-by","title":"Enhancement of Short Text Clustering by Iterative Classification","date":"2020-01-31","arxiv_id":"2001.11631","repositories_listed":1,"syntology":null},{"url":"/paper/an-implicit-attention-mechanism-for-deep","slug":"an-implicit-attention-mechanism-for-deep","title":"Person Re-identification: Implicitly Defining the Receptive Fields of Deep Learning Classification Frameworks","date":"2020-01-30","arxiv_id":"2001.11267","repositories_listed":1,"syntology":null},{"url":"/paper/data-mining-in-clinical-trial-text","slug":"data-mining-in-clinical-trial-text","title":"Data Mining in Clinical Trial Text: Transformers for Classification and Question Answering Tasks","date":"2020-01-30","arxiv_id":"2001.11268","repositories_listed":1,"syntology":null},{"url":"/paper/going-beyond-accuracy-estimating-homophily-in","slug":"going-beyond-accuracy-estimating-homophily-in","title":"Going beyond accuracy: estimating homophily in social networks using predictions","date":"2020-01-30","arxiv_id":"2001.11171","repositories_listed":1,"syntology":null},{"url":"/paper/which-way-direction-aware-attributed-graph","slug":"which-way-direction-aware-attributed-graph","title":"Which way? Direction-Aware Attributed Graph Embedding","date":"2020-01-30","arxiv_id":"2001.11297","repositories_listed":1,"syntology":null},{"url":"/paper/stream-learn-open-source-python-library-for","slug":"stream-learn-open-source-python-library-for","title":"stream-learn -- open-source Python library for difficult data stream batch analysis","date":"2020-01-29","arxiv_id":"2001.11077","repositories_listed":1,"syntology":null},{"url":"/paper/margin-maximization-as-lossless-maximal","slug":"margin-maximization-as-lossless-maximal","title":"Margin Maximization as Lossless Maximal Compression","date":"2020-01-28","arxiv_id":"2001.10318","repositories_listed":1,"syntology":null},{"url":"/paper/mse-optimal-neural-network-initialization-via","slug":"mse-optimal-neural-network-initialization-via","title":"MSE-Optimal Neural Network Initialization via Layer Fusion","date":"2020-01-28","arxiv_id":"2001.10509","repositories_listed":1,"syntology":null},{"url":"/paper/multi-class-gaussian-process-classification-1","slug":"multi-class-gaussian-process-classification-1","title":"Multi-class Gaussian Process Classification with Noisy Inputs","date":"2020-01-28","arxiv_id":"2001.10523","repositories_listed":1,"syntology":null},{"url":"/paper/opfython-a-python-inspired-optimum-path","slug":"opfython-a-python-inspired-optimum-path","title":"OPFython: A Python-Inspired Optimum-Path Forest Classifier","date":"2020-01-28","arxiv_id":"2001.10420","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-unsupervised-inputs-for-accurate","slug":"exploiting-unsupervised-inputs-for-accurate","title":"Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification","date":"2020-01-27","arxiv_id":"2001.09849","repositories_listed":1,"syntology":null},{"url":"/paper/libtwinsvm-a-library-for-twin-support-vector","slug":"libtwinsvm-a-library-for-twin-support-vector","title":"LIBTwinSVM: A Library for Twin Support Vector Machines","date":"2020-01-27","arxiv_id":"2001.10073","repositories_listed":1,"syntology":null},{"url":"/paper/cor-gan-correlation-capturing-convolutional","slug":"cor-gan-correlation-capturing-convolutional","title":"CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Records","date":"2020-01-25","arxiv_id":"2001.09346","repositories_listed":1,"syntology":null},{"url":"/paper/intent-classification-in-question-answering","slug":"intent-classification-in-question-answering","title":"Intent Classification in Question-Answering Using LSTM Architectures","date":"2020-01-25","arxiv_id":"2001.09330","repositories_listed":1,"syntology":null},{"url":"/paper/power-bert-accelerating-bert-inference-for","slug":"power-bert-accelerating-bert-inference-for","title":"PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination","date":"2020-01-24","arxiv_id":"2001.08950","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 2 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) · 0 unverified","sample_list":"/paper/power-bert-accelerating-bert-inference-for#ran","syntology_url":"https://syntology.ai/paper/2001.08950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.08950"}},"official":{"repos":["IBM/PoWER-BERT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cnn-cass-cnn-for-classification-of-coronary","slug":"cnn-cass-cnn-for-classification-of-coronary","title":"CNN-CASS: CNN for Classification of Coronary Artery Stenosis Score in MPR Images","date":"2020-01-23","arxiv_id":"2001.08593","repositories_listed":1,"syntology":null},{"url":"/paper/cross-domain-few-shot-classification-via-1","slug":"cross-domain-few-shot-classification-via-1","title":"Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation","date":"2020-01-23","arxiv_id":"2001.08735","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cross-domain-few-shot-classification-via-1#ran","syntology_url":"https://syntology.ai/paper/2001.08735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.08735"}},"official":{"repos":["hytseng0509/CrossDomainFewShot"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gl2vec-graph-embedding-enriched-by-line","slug":"gl2vec-graph-embedding-enriched-by-line","title":"GL2vec: Graph Embedding Enriched by Line Graphs with Edge Features","date":"2020-01-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/localization-of-critical-findings-in-chest-x","slug":"localization-of-critical-findings-in-chest-x","title":"Localization of Critical Findings in Chest X-Ray without Local Annotations Using Multi-Instance Learning","date":"2020-01-23","arxiv_id":"2001.08817","repositories_listed":1,"syntology":null},{"url":"/paper/on-last-layer-algorithms-for-classification","slug":"on-last-layer-algorithms-for-classification","title":"On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation","date":"2020-01-22","arxiv_id":"2001.08049","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/on-last-layer-algorithms-for-classification#ran","syntology_url":"https://syntology.ai/paper/2001.08049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.08049"}},"official":{"repos":["nbrosse/uncertainties"],"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/partially-shared-variational-auto-encoders","slug":"partially-shared-variational-auto-encoders","title":"Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift","date":"2020-01-22","arxiv_id":"2001.07895","repositories_listed":1,"syntology":null},{"url":"/paper/representation-learning-for-medical-data","slug":"representation-learning-for-medical-data","title":"Representation Learning for Medical Data","date":"2020-01-22","arxiv_id":"2001.08269","repositories_listed":1,"syntology":null},{"url":"/paper/ghostimage-perception-domain-attacks-against","slug":"ghostimage-perception-domain-attacks-against","title":"GhostImage: Remote Perception Attacks against Camera-based Image Classification Systems","date":"2020-01-21","arxiv_id":"2001.07792","repositories_listed":1,"syntology":null},{"url":"/paper/cnn-based-insar-coherence-classification","slug":"cnn-based-insar-coherence-classification","title":"CNN-based InSAR Coherence Classification","date":"2020-01-20","arxiv_id":"2001.06956","repositories_listed":1,"syntology":null},{"url":"/paper/multiplication-fusion-of-sparse-and","slug":"multiplication-fusion-of-sparse-and","title":"Multiplication fusion of sparse and collaborative-competitive representation for image classification","date":"2020-01-20","arxiv_id":"2001.07090","repositories_listed":1,"syntology":null},{"url":"/paper/compounding-the-performance-improvements-of","slug":"compounding-the-performance-improvements-of","title":"Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network","date":"2020-01-17","arxiv_id":"2001.06268","repositories_listed":1,"syntology":{"n":11,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/compounding-the-performance-improvements-of#ran","syntology_url":"https://syntology.ai/paper/2001.06268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.06268"}},"official":{"repos":["clovaai/assembled-cnn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/epileptic-seizure-classification-with","slug":"epileptic-seizure-classification-with","title":"Epileptic Seizure Classification with Symmetric and Hybrid Bilinear Models","date":"2020-01-15","arxiv_id":"2001.06282","repositories_listed":1,"syntology":null},{"url":"/paper/two-cycle-learning-clustering-based","slug":"two-cycle-learning-clustering-based","title":"CycleCluster: Modernising Clustering Regularisation for Deep Semi-Supervised Classification","date":"2020-01-15","arxiv_id":"2001.05317","repositories_listed":1,"syntology":null},{"url":"/paper/an-adversarial-approach-for-the-robust","slug":"an-adversarial-approach-for-the-robust","title":"An Adversarial Approach for the Robust Classification of Pneumonia from Chest Radiographs","date":"2020-01-13","arxiv_id":"2001.04051","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-occluded-image-classification-via","slug":"boosting-occluded-image-classification-via","title":"Boosting Occluded Image Classification via Subspace Decomposition Based Estimation of Deep Features","date":"2020-01-13","arxiv_id":"2001.04066","repositories_listed":1,"syntology":null},{"url":"/paper/aggregated-learning-a-vector-quantization","slug":"aggregated-learning-a-vector-quantization","title":"Aggregated Learning: A Vector-Quantization Approach to Learning Neural Network Classifiers","date":"2020-01-12","arxiv_id":"2001.03955","repositories_listed":1,"syntology":null},{"url":"/paper/bag-of-tricks-for-retail-product-image","slug":"bag-of-tricks-for-retail-product-image","title":"Bag of Tricks for Retail Product Image Classification","date":"2020-01-12","arxiv_id":"2001.03992","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-graph-isomorphism-network-for","slug":"understanding-graph-isomorphism-network-for","title":"Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysis","date":"2020-01-10","arxiv_id":"2001.03690","repositories_listed":1,"syntology":null}],"record_sha256":"7d5f658e9dbda978f659abacde5c9d225d0b3e49d79c618cd97b79fba6123733","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}