{"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":"/dataset/imagenet/papers/ran/4","list_of":"/dataset/imagenet","dataset":"ImageNet","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","key_notes":{"samples_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'","samples_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)"},"order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":4,"pages_in_order":4,"rows_per_page":100,"rows":[301,361],"of":361,"counts":{"papers_with_a_benchmark_row":630,"with_a_code_link":588,"where_syntology_ran_a_sample":361,"not_listed_spam_title":0,"listed":630,"listed_where_code_ran":361,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":312,"every_run_a_failure_of_syntologys_instrument":49,"listed_with_a_run_with_no_instrument_failure":312,"listed_every_run_a_failure_of_syntologys_instrument":49,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/dataset/imagenet/papers/ran/1","prev":"/dataset/imagenet/papers/ran/3","next":null,"papers":[{"paper":"/paper/dicenet-dimension-wise-convolutions-for","slug":"dicenet-dimension-wise-convolutions-for","title":"DiCENet: Dimension-wise Convolutions for Efficient Networks","date":"2019-06-08","arxiv_id":"1906.03516","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["sacmehta/EdgeNets"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dicenet-dimension-wise-convolutions-for#ran","syntology_url":"https://syntology.ai/paper/1906.03516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03516"}}}},{"paper":"/paper/190600910","slug":"190600910","title":"Learning Representations by Maximizing Mutual Information Across Views","date":"2019-06-03","arxiv_id":"1906.00910","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":8,"samples_constructed":5,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190600910#ran","syntology_url":"https://syntology.ai/paper/1906.00910","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00910"}}}},{"paper":"/paper/efficientnet-rethinking-model-scaling-for","slug":"efficientnet-rethinking-model-scaling-for","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","date":"2019-05-28","arxiv_id":"1905.11946","rows_on_this_dataset":8,"code_links":144,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":302,"samples_ran":198,"samples_constructed":73,"samples_ran_checked":157,"samples_ran_instrument_failed":41,"samples_unverified":104,"pointer_only_for_licence":113,"official":{"repos":["tensorflow/tpu"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/efficientnet-rethinking-model-scaling-for#ran","syntology_url":"https://syntology.ai/paper/1905.11946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11946"}}}},{"paper":"/paper/spatial-group-wise-enhance-improving-semantic","slug":"spatial-group-wise-enhance-improving-semantic","title":"Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks","date":"2019-05-23","arxiv_id":"1905.09646","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["implus/PytorchInsight"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spatial-group-wise-enhance-improving-semantic#ran","syntology_url":"https://syntology.ai/paper/1905.09646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09646"}}}},{"paper":"/paper/data-efficient-image-recognition-with","slug":"data-efficient-image-recognition-with","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","date":"2019-05-22","arxiv_id":"1905.09272","rows_on_this_dataset":6,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/data-efficient-image-recognition-with#ran","syntology_url":"https://syntology.ai/paper/1905.09272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09272"}}}},{"paper":"/paper/cutmix-regularization-strategy-to-train","slug":"cutmix-regularization-strategy-to-train","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","date":"2019-05-13","arxiv_id":"1905.04899","rows_on_this_dataset":2,"code_links":30,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":24,"samples_ran":17,"samples_constructed":6,"samples_ran_checked":11,"samples_ran_instrument_failed":6,"samples_unverified":7,"pointer_only_for_licence":5,"official":{"repos":["clovaai/CutMix-PyTorch"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cutmix-regularization-strategy-to-train#ran","syntology_url":"https://syntology.ai/paper/1905.04899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04899"}}}},{"paper":"/paper/190503670","slug":"190503670","title":"S4L: Self-Supervised Semi-Supervised Learning","date":"2019-05-09","arxiv_id":"1905.03670","rows_on_this_dataset":22,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":19,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":19,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190503670#ran","syntology_url":"https://syntology.ai/paper/1905.03670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.03670"}}}},{"paper":"/paper/searching-for-mobilenetv3","slug":"searching-for-mobilenetv3","title":"Searching for MobileNetV3","date":"2019-05-06","arxiv_id":"1905.02244","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":105,"samples_ran":86,"samples_constructed":22,"samples_ran_checked":75,"samples_ran_instrument_failed":11,"samples_unverified":19,"pointer_only_for_licence":46,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/searching-for-mobilenetv3#ran","syntology_url":"https://syntology.ai/paper/1905.02244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.02244"}}}},{"paper":"/paper/fast-autoaugment","slug":"fast-autoaugment","title":"Fast AutoAugment","date":"2019-05-01","arxiv_id":"1905.00397","rows_on_this_dataset":4,"code_links":11,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":40,"samples_ran":37,"samples_constructed":2,"samples_ran_checked":21,"samples_ran_instrument_failed":16,"samples_unverified":3,"pointer_only_for_licence":7,"official":{"repos":["kakaobrain/fast-autoaugment"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fast-autoaugment#ran","syntology_url":"https://syntology.ai/paper/1905.00397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.00397"}}}},{"paper":"/paper/unsupervised-data-augmentation-1","slug":"unsupervised-data-augmentation-1","title":"Unsupervised Data Augmentation for Consistency Training","date":"2019-04-29","arxiv_id":"1904.12848","rows_on_this_dataset":2,"code_links":20,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":52,"samples_ran":30,"samples_constructed":3,"samples_ran_checked":22,"samples_ran_instrument_failed":8,"samples_unverified":22,"pointer_only_for_licence":17,"official":{"repos":["google-research/uda"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":14,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-data-augmentation-1#ran","syntology_url":"https://syntology.ai/paper/1904.12848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12848"}}}},{"paper":"/paper/190411491","slug":"190411491","title":"Local Relation Networks for Image Recognition","date":"2019-04-25","arxiv_id":"1904.11491","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190411491#ran","syntology_url":"https://syntology.ai/paper/1904.11491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11491"}}}},{"paper":"/paper/190409925","slug":"190409925","title":"Attention Augmented Convolutional Networks","date":"2019-04-22","arxiv_id":"1904.09925","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/190409925#ran","syntology_url":"https://syntology.ai/paper/1904.09925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09925"}}}},{"paper":"/paper/drop-an-octave-reducing-spatial-redundancy-in","slug":"drop-an-octave-reducing-spatial-redundancy-in","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","date":"2019-04-10","arxiv_id":"1904.05049","rows_on_this_dataset":1,"code_links":28,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":34,"samples_ran":24,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":13,"samples_unverified":10,"pointer_only_for_licence":9,"official":{"repos":["facebookresearch/OctConv"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/drop-an-octave-reducing-spatial-redundancy-in#ran","syntology_url":"https://syntology.ai/paper/1904.05049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05049"}}}},{"paper":"/paper/single-path-nas-designing-hardware-efficient","slug":"single-path-nas-designing-hardware-efficient","title":"Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours","date":"2019-04-05","arxiv_id":"1904.02877","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":16,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":12,"pointer_only_for_licence":1,"official":{"repos":["dstamoulis/single-path-nas"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":12,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/single-path-nas-designing-hardware-efficient#ran","syntology_url":"https://syntology.ai/paper/1904.02877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02877"}}}},{"paper":"/paper/a-comprehensive-overhaul-of-feature","slug":"a-comprehensive-overhaul-of-feature","title":"A Comprehensive Overhaul of Feature Distillation","date":"2019-04-03","arxiv_id":"1904.01866","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["clovaai/overhaul-distillation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-comprehensive-overhaul-of-feature#ran","syntology_url":"https://syntology.ai/paper/1904.01866","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01866"}}}},{"paper":"/paper/res2net-a-new-multi-scale-backbone","slug":"res2net-a-new-multi-scale-backbone","title":"Res2Net: A New Multi-scale Backbone Architecture","date":"2019-04-02","arxiv_id":"1904.01169","rows_on_this_dataset":2,"code_links":34,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":4,"pointer_only_for_licence":9,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/res2net-a-new-multi-scale-backbone#ran","syntology_url":"https://syntology.ai/paper/1904.01169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01169"}}}},{"paper":"/paper/exploring-randomly-wired-neural-networks-for","slug":"exploring-randomly-wired-neural-networks-for","title":"Exploring Randomly Wired Neural Networks for Image Recognition","date":"2019-04-02","arxiv_id":"1904.01569","rows_on_this_dataset":3,"code_links":9,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":31,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":21,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-randomly-wired-neural-networks-for#ran","syntology_url":"https://syntology.ai/paper/1904.01569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01569"}}}},{"paper":"/paper/single-path-one-shot-neural-architecture","slug":"single-path-one-shot-neural-architecture","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","date":"2019-03-31","arxiv_id":"1904.00420","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/single-path-one-shot-neural-architecture#ran","syntology_url":"https://syntology.ai/paper/1904.00420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00420"}}}},{"paper":"/paper/srm-a-style-based-recalibration-module-for","slug":"srm-a-style-based-recalibration-module-for","title":"SRM : A Style-based Recalibration Module for Convolutional Neural Networks","date":"2019-03-26","arxiv_id":"1903.10829","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/srm-a-style-based-recalibration-module-for#ran","syntology_url":"https://syntology.ai/paper/1903.10829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.10829"}}}},{"paper":"/paper/sharpdarts-faster-and-more-accurate","slug":"sharpdarts-faster-and-more-accurate","title":"sharpDARTS: Faster and More Accurate Differentiable Architecture Search","date":"2019-03-23","arxiv_id":"1903.09900","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ahundt/sharpDARTS"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sharpdarts-faster-and-more-accurate#ran","syntology_url":"https://syntology.ai/paper/1903.09900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.09900"}}}},{"paper":"/paper/selective-kernel-networks","slug":"selective-kernel-networks","title":"Selective Kernel Networks","date":"2019-03-15","arxiv_id":"1903.06586","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["implus/SKNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/selective-kernel-networks#ran","syntology_url":"https://syntology.ai/paper/1903.06586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.06586"}}}},{"paper":"/paper/learned-step-size-quantization","slug":"learned-step-size-quantization","title":"Learned Step Size Quantization","date":"2019-02-21","arxiv_id":"1902.08153","rows_on_this_dataset":5,"code_links":9,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":23,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":3,"samples_unverified":9,"pointer_only_for_licence":6,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learned-step-size-quantization#ran","syntology_url":"https://syntology.ai/paper/1902.08153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.08153"}}}},{"paper":"/paper/multigrain-a-unified-image-embedding-for","slug":"multigrain-a-unified-image-embedding-for","title":"MultiGrain: a unified image embedding for classes and instances","date":"2019-02-14","arxiv_id":"1902.05509","rows_on_this_dataset":10,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["facebookresearch/multigrain"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multigrain-a-unified-image-embedding-for#ran","syntology_url":"https://syntology.ai/paper/1902.05509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.05509"}}}},{"paper":"/paper/revisiting-self-supervised-visual","slug":"revisiting-self-supervised-visual","title":"Revisiting Self-Supervised Visual Representation Learning","date":"2019-01-25","arxiv_id":"1901.09005","rows_on_this_dataset":4,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":7,"official":{"repos":["google/revisiting-self-supervised"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/revisiting-self-supervised-visual#ran","syntology_url":"https://syntology.ai/paper/1901.09005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.09005"}}}},{"paper":"/paper/fbnet-hardware-aware-efficient-convnet-design","slug":"fbnet-hardware-aware-efficient-convnet-design","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","date":"2018-12-09","arxiv_id":"1812.03443","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["facebookresearch/mobile-vision"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fbnet-hardware-aware-efficient-convnet-design#ran","syntology_url":"https://syntology.ai/paper/1812.03443","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03443"}}}},{"paper":"/paper/bag-of-tricks-for-image-classification-with","slug":"bag-of-tricks-for-image-classification-with","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","date":"2018-12-04","arxiv_id":"1812.01187","rows_on_this_dataset":1,"code_links":28,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":15,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":2,"samples_unverified":4,"pointer_only_for_licence":5,"official":{"repos":["dmlc/gluon-cv"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bag-of-tricks-for-image-classification-with#ran","syntology_url":"https://syntology.ai/paper/1812.01187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.01187"}}}},{"paper":"/paper/proxylessnas-direct-neural-architecture","slug":"proxylessnas-direct-neural-architecture","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","date":"2018-12-02","arxiv_id":"1812.00332","rows_on_this_dataset":2,"code_links":23,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":27,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":4,"official":{"repos":["MIT-HAN-LAB/ProxylessNAS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/proxylessnas-direct-neural-architecture#ran","syntology_url":"https://syntology.ai/paper/1812.00332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00332"}}}},{"paper":"/paper/espnetv2-a-light-weight-power-efficient-and","slug":"espnetv2-a-light-weight-power-efficient-and","title":"ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network","date":"2018-11-28","arxiv_id":"1811.11431","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["sacmehta/EdgeNets"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/espnetv2-a-light-weight-power-efficient-and#ran","syntology_url":"https://syntology.ai/paper/1811.11431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11431"}}}},{"paper":"/paper/gpipe-efficient-training-of-giant-neural","slug":"gpipe-efficient-training-of-giant-neural","title":"GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism","date":"2018-11-16","arxiv_id":"1811.06965","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":25,"samples_ran":20,"samples_constructed":0,"samples_ran_checked":19,"samples_ran_instrument_failed":1,"samples_unverified":5,"pointer_only_for_licence":16,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpipe-efficient-training-of-giant-neural#ran","syntology_url":"https://syntology.ai/paper/1811.06965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.06965"}}}},{"paper":"/paper/mnasnet-platform-aware-neural-architecture","slug":"mnasnet-platform-aware-neural-architecture","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","date":"2018-07-31","arxiv_id":"1807.11626","rows_on_this_dataset":3,"code_links":29,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["tensorflow/tpu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mnasnet-platform-aware-neural-architecture#ran","syntology_url":"https://syntology.ai/paper/1807.11626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.11626"}}}},{"paper":"/paper/shufflenet-v2-practical-guidelines-for","slug":"shufflenet-v2-practical-guidelines-for","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","date":"2018-07-30","arxiv_id":"1807.11164","rows_on_this_dataset":1,"code_links":35,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":30,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":1,"samples_unverified":16,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/shufflenet-v2-practical-guidelines-for#ran","syntology_url":"https://syntology.ai/paper/1807.11164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.11164"}}}},{"paper":"/paper/deep-clustering-for-unsupervised-learning-of","slug":"deep-clustering-for-unsupervised-learning-of","title":"Deep Clustering for Unsupervised Learning of Visual Features","date":"2018-07-15","arxiv_id":"1807.05520","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":2,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/deepcluster"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-clustering-for-unsupervised-learning-of#ran","syntology_url":"https://syntology.ai/paper/1807.05520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.05520"}}}},{"paper":"/paper/representation-learning-with-contrastive","slug":"representation-learning-with-contrastive","title":"Representation Learning with Contrastive Predictive Coding","date":"2018-07-10","arxiv_id":"1807.03748","rows_on_this_dataset":3,"code_links":28,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":45,"samples_ran":35,"samples_constructed":21,"samples_ran_checked":30,"samples_ran_instrument_failed":5,"samples_unverified":10,"pointer_only_for_licence":22,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/representation-learning-with-contrastive#ran","syntology_url":"https://syntology.ai/paper/1807.03748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03748"}}}},{"paper":"/paper/an-intriguing-failing-of-convolutional-neural","slug":"an-intriguing-failing-of-convolutional-neural","title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","date":"2018-07-09","arxiv_id":"1807.03247","rows_on_this_dataset":1,"code_links":24,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["uber-research/coordconv"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-intriguing-failing-of-convolutional-neural#ran","syntology_url":"https://syntology.ai/paper/1807.03247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03247"}}}},{"paper":"/paper/pcl-proposal-cluster-learning-for-weakly","slug":"pcl-proposal-cluster-learning-for-weakly","title":"PCL: Proposal Cluster Learning for Weakly Supervised Object Detection","date":"2018-07-09","arxiv_id":"1807.03342","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["ppengtang/oicr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pcl-proposal-cluster-learning-for-weakly#ran","syntology_url":"https://syntology.ai/paper/1807.03342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03342"}}}},{"paper":"/paper/darts-differentiable-architecture-search","slug":"darts-differentiable-architecture-search","title":"DARTS: Differentiable Architecture Search","date":"2018-06-24","arxiv_id":"1806.09055","rows_on_this_dataset":1,"code_links":59,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":156,"samples_ran":74,"samples_constructed":30,"samples_ran_checked":60,"samples_ran_instrument_failed":14,"samples_unverified":82,"pointer_only_for_licence":54,"official":{"repos":["quark0/darts"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/darts-differentiable-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1806.09055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.09055"}}}},{"paper":"/paper/autoaugment-learning-augmentation-policies","slug":"autoaugment-learning-augmentation-policies","title":"AutoAugment: Learning Augmentation Policies from Data","date":"2018-05-24","arxiv_id":"1805.09501","rows_on_this_dataset":2,"code_links":33,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":43,"samples_ran":25,"samples_constructed":0,"samples_ran_checked":22,"samples_ran_instrument_failed":3,"samples_unverified":18,"pointer_only_for_licence":4,"official":{"repos":["tensorflow/models"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/autoaugment-learning-augmentation-policies#ran","syntology_url":"https://syntology.ai/paper/1805.09501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09501"}}}},{"paper":"/paper/unsupervised-feature-learning-via-non","slug":"unsupervised-feature-learning-via-non","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","date":"2018-05-05","arxiv_id":"1805.01978","rows_on_this_dataset":1,"code_links":15,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":23,"samples_ran":19,"samples_constructed":14,"samples_ran_checked":17,"samples_ran_instrument_failed":2,"samples_unverified":4,"pointer_only_for_licence":16,"official":{"repos":["zhirongw/lemniscate.pytorch"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-feature-learning-via-non#ran","syntology_url":"https://syntology.ai/paper/1805.01978","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.01978"}}}},{"paper":"/paper/unsupervised-representation-learning-by-1","slug":"unsupervised-representation-learning-by-1","title":"Unsupervised Representation Learning by Predicting Image Rotations","date":"2018-03-21","arxiv_id":"1803.07728","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":22,"samples_ran":16,"samples_constructed":7,"samples_ran_checked":14,"samples_ran_instrument_failed":2,"samples_unverified":6,"pointer_only_for_licence":18,"official":{"repos":["gidariss/FeatureLearningRotNet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unsupervised-representation-learning-by-1#ran","syntology_url":"https://syntology.ai/paper/1803.07728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.07728"}}}},{"paper":"/paper/averaging-weights-leads-to-wider-optima-and","slug":"averaging-weights-leads-to-wider-optima-and","title":"Averaging Weights Leads to Wider Optima and Better Generalization","date":"2018-03-14","arxiv_id":"1803.05407","rows_on_this_dataset":2,"code_links":17,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["timgaripov/swa"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/averaging-weights-leads-to-wider-optima-and#ran","syntology_url":"https://syntology.ai/paper/1803.05407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.05407"}}}},{"paper":"/paper/mobilenetv2-inverted-residuals-and-linear","slug":"mobilenetv2-inverted-residuals-and-linear","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","date":"2018-01-13","arxiv_id":"1801.04381","rows_on_this_dataset":2,"code_links":159,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":111,"samples_ran":85,"samples_constructed":40,"samples_ran_checked":65,"samples_ran_instrument_failed":20,"samples_unverified":26,"pointer_only_for_licence":64,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mobilenetv2-inverted-residuals-and-linear#ran","syntology_url":"https://syntology.ai/paper/1801.04381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.04381"}}}},{"paper":"/paper/sparse-learning-of-stochastic-dynamic","slug":"sparse-learning-of-stochastic-dynamic","title":"Sparse learning of stochastic dynamic equations","date":"2017-12-06","arxiv_id":"1712.02432","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":3,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sparse-learning-of-stochastic-dynamic#ran","syntology_url":"https://syntology.ai/paper/1712.02432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.02432"}}}},{"paper":"/paper/progressive-neural-architecture-search","slug":"progressive-neural-architecture-search","title":"Progressive Neural Architecture Search","date":"2017-12-02","arxiv_id":"1712.00559","rows_on_this_dataset":2,"code_links":18,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["chenxi116/PNASNet.TF","tensorflow/models","chenxi116/PNASNet.pytorch"],"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":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/progressive-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1712.00559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.00559"}}}},{"paper":"/paper/representation-learning-by-learning-to-count","slug":"representation-learning-by-learning-to-count","title":"Representation Learning by Learning to Count","date":"2017-08-22","arxiv_id":"1708.06734","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/representation-learning-by-learning-to-count#ran","syntology_url":"https://syntology.ai/paper/1708.06734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.06734"}}}},{"paper":"/paper/residual-attention-network-for-image","slug":"residual-attention-network-for-image","title":"Residual Attention Network for Image Classification","date":"2017-04-23","arxiv_id":"1704.06904","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/residual-attention-network-for-image#ran","syntology_url":"https://syntology.ai/paper/1704.06904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.06904"}}}},{"paper":"/paper/mobilenets-efficient-convolutional-neural","slug":"mobilenets-efficient-convolutional-neural","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","date":"2017-04-17","arxiv_id":"1704.04861","rows_on_this_dataset":1,"code_links":159,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":83,"samples_ran":53,"samples_constructed":28,"samples_ran_checked":44,"samples_ran_instrument_failed":9,"samples_unverified":30,"pointer_only_for_licence":48,"official":{"repos":["tensorflow/tensorflow"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mobilenets-efficient-convolutional-neural#ran","syntology_url":"https://syntology.ai/paper/1704.04861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.04861"}}}},{"paper":"/paper/mean-teachers-are-better-role-models-weight","slug":"mean-teachers-are-better-role-models-weight","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","date":"2017-03-06","arxiv_id":"1703.01780","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["CuriousAI/mean-teacher"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mean-teachers-are-better-role-models-weight#ran","syntology_url":"https://syntology.ai/paper/1703.01780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.01780"}}}},{"paper":"/paper/paying-more-attention-to-attention-improving","slug":"paying-more-attention-to-attention-improving","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","date":"2016-12-12","arxiv_id":"1612.03928","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["szagoruyko/attention-transfer"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/paying-more-attention-to-attention-improving#ran","syntology_url":"https://syntology.ai/paper/1612.03928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.03928"}}}},{"paper":"/paper/aggregated-residual-transformations-for-deep","slug":"aggregated-residual-transformations-for-deep","title":"Aggregated Residual Transformations for Deep Neural Networks","date":"2016-11-16","arxiv_id":"1611.05431","rows_on_this_dataset":1,"code_links":61,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":80,"samples_ran":51,"samples_constructed":7,"samples_ran_checked":31,"samples_ran_instrument_failed":20,"samples_unverified":29,"pointer_only_for_licence":13,"official":{"repos":["facebookresearch/ResNeXt"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/aggregated-residual-transformations-for-deep#ran","syntology_url":"https://syntology.ai/paper/1611.05431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.05431"}}}},{"paper":"/paper/xception-deep-learning-with-depthwise","slug":"xception-deep-learning-with-depthwise","title":"Xception: Deep Learning with Depthwise Separable Convolutions","date":"2016-10-07","arxiv_id":"1610.02357","rows_on_this_dataset":1,"code_links":41,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":15,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":8,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xception-deep-learning-with-depthwise#ran","syntology_url":"https://syntology.ai/paper/1610.02357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.02357"}}}},{"paper":"/paper/pruning-filters-for-efficient-convnets","slug":"pruning-filters-for-efficient-convnets","title":"Pruning Filters for Efficient ConvNets","date":"2016-08-31","arxiv_id":"1608.08710","rows_on_this_dataset":3,"code_links":21,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":36,"samples_ran":23,"samples_constructed":4,"samples_ran_checked":9,"samples_ran_instrument_failed":14,"samples_unverified":13,"pointer_only_for_licence":22,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pruning-filters-for-efficient-convnets#ran","syntology_url":"https://syntology.ai/paper/1608.08710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.08710"}}}},{"paper":"/paper/densely-connected-convolutional-networks","slug":"densely-connected-convolutional-networks","title":"Densely Connected Convolutional Networks","date":"2016-08-25","arxiv_id":"1608.06993","rows_on_this_dataset":4,"code_links":146,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":71,"samples_ran":48,"samples_constructed":0,"samples_ran_checked":32,"samples_ran_instrument_failed":16,"samples_unverified":23,"pointer_only_for_licence":8,"official":{"repos":["liuzhuang13/DenseNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/densely-connected-convolutional-networks#ran","syntology_url":"https://syntology.ai/paper/1608.06993","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.06993"}}}},{"paper":"/paper/lets-keep-it-simple-using-simple","slug":"lets-keep-it-simple-using-simple","title":"Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures","date":"2016-08-22","arxiv_id":"1608.06037","rows_on_this_dataset":8,"code_links":9,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["Coderx7/SimpleNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lets-keep-it-simple-using-simple#ran","syntology_url":"https://syntology.ai/paper/1608.06037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.06037"}}}},{"paper":"/paper/fractalnet-ultra-deep-neural-networks-without","slug":"fractalnet-ultra-deep-neural-networks-without","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","date":"2016-05-24","arxiv_id":"1605.07648","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/fractalnet-ultra-deep-neural-networks-without#ran","syntology_url":"https://syntology.ai/paper/1605.07648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.07648"}}}},{"paper":"/paper/wide-residual-networks","slug":"wide-residual-networks","title":"Wide Residual Networks","date":"2016-05-23","arxiv_id":"1605.07146","rows_on_this_dataset":1,"code_links":72,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":96,"samples_ran":66,"samples_constructed":31,"samples_ran_checked":48,"samples_ran_instrument_failed":18,"samples_unverified":30,"pointer_only_for_licence":50,"official":{"repos":["szagoruyko/wide-residual-networks"],"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":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/wide-residual-networks#ran","syntology_url":"https://syntology.ai/paper/1605.07146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.07146"}}}},{"paper":"/paper/colorful-image-colorization","slug":"colorful-image-colorization","title":"Colorful Image Colorization","date":"2016-03-28","arxiv_id":"1603.08511","rows_on_this_dataset":1,"code_links":39,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":73,"samples_ran":47,"samples_constructed":10,"samples_ran_checked":30,"samples_ran_instrument_failed":17,"samples_unverified":26,"pointer_only_for_licence":41,"official":{"repos":["richzhang/colorization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/colorful-image-colorization#ran","syntology_url":"https://syntology.ai/paper/1603.08511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.08511"}}}},{"paper":"/paper/identity-mappings-in-deep-residual-networks","slug":"identity-mappings-in-deep-residual-networks","title":"Identity Mappings in Deep Residual Networks","date":"2016-03-16","arxiv_id":"1603.05027","rows_on_this_dataset":1,"code_links":54,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":25,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":2,"samples_unverified":11,"pointer_only_for_licence":2,"official":{"repos":["KaimingHe/resnet-1k-layers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/identity-mappings-in-deep-residual-networks#ran","syntology_url":"https://syntology.ai/paper/1603.05027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.05027"}}}},{"paper":"/paper/squeezenet-alexnet-level-accuracy-with-50x","slug":"squeezenet-alexnet-level-accuracy-with-50x","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","date":"2016-02-24","arxiv_id":"1602.07360","rows_on_this_dataset":1,"code_links":59,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["DT42/squeezenet_demo","DeepScale/SqueezeNet","Element-Research/dpnn","ejlb/squeezenet-chainer","haria/SqueezeNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/squeezenet-alexnet-level-accuracy-with-50x#ran","syntology_url":"https://syntology.ai/paper/1602.07360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.07360"}}}},{"paper":"/paper/inception-v4-inception-resnet-and-the-impact","slug":"inception-v4-inception-resnet-and-the-impact","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","date":"2016-02-23","arxiv_id":"1602.07261","rows_on_this_dataset":1,"code_links":87,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/inception-v4-inception-resnet-and-the-impact#ran","syntology_url":"https://syntology.ai/paper/1602.07261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.07261"}}}},{"paper":"/paper/deep-residual-learning-for-image-recognition","slug":"deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","arxiv_id":"1512.03385","rows_on_this_dataset":3,"code_links":484,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":377,"samples_ran":254,"samples_constructed":108,"samples_ran_checked":166,"samples_ran_instrument_failed":88,"samples_unverified":123,"pointer_only_for_licence":193,"official":{"repos":["KaimingHe/resnet-1k-layers"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-residual-learning-for-image-recognition#ran","syntology_url":"https://syntology.ai/paper/1512.03385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.03385"}}}},{"paper":"/paper/distilling-the-knowledge-in-a-neural-network","slug":"distilling-the-knowledge-in-a-neural-network","title":"Distilling the Knowledge in a Neural Network","date":"2015-03-09","arxiv_id":"1503.02531","rows_on_this_dataset":2,"code_links":64,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":37,"samples_ran":23,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":9,"samples_unverified":14,"pointer_only_for_licence":11,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distilling-the-knowledge-in-a-neural-network#ran","syntology_url":"https://syntology.ai/paper/1503.02531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1503.02531"}}}}],"record_sha256":"95c43237c5219ea243f45f368dff3bea112447cb899663bcf55ca558b92088f9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}