{"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/error-understanding","name":"Error Understanding","slug":"error-understanding","description_markdown":"Discover what causes the model’s prediction errors.","categories":[{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":9,"papers_with_code":5,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/error-understanding-on-cub-200-2011-1","slug":"error-understanding-on-cub-200-2011-1","dataset":"CUB-200-2011","dataset_url":"/dataset/cub-200-2011","rows_in_archive":4,"metrics":["Average highest confidence (ResNet-101)","Insertion AUC score (ResNet-101)","Average highest confidence (MobileNetV2)","Insertion AUC score (MobileNetV2)","Average highest confidence (EfficientNetV2-M)","Insertion AUC score (EfficientNetV2-M)"],"first_row_in_archive_order":{"model":"SMDL-Attribution (ICLR version)","paper_title":"Less is More: Fewer Interpretable Region via Submodular Subset Selection","paper_url":"/paper/less-is-more-fewer-interpretable-region-via","paper_date":"2024-02-14","arxiv_id":"2402.09164","code_links":[{"title":"ruoyuchen10/smdl-attribution","url":"https://github.com/ruoyuchen10/smdl-attribution"}],"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/less-is-more-fewer-interpretable-region-via#ran","syntology_url":"https://syntology.ai/paper/2402.09164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09164"}},"official":{"repos":["ruoyuchen10/smdl-attribution"],"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"]}}}},{"leaderboard":"/sota/error-understanding-on-cub-200-2011-resnet","slug":"error-understanding-on-cub-200-2011-resnet","dataset":"CUB-200-2011 (ResNet-101)","dataset_url":null,"rows_in_archive":3,"metrics":["Average highest confidence","Insertion AUC score"],"first_row_in_archive_order":{"model":"Grad-CAM++","paper_title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","paper_url":"/paper/grad-cam-improved-visual-explanations-for","paper_date":"2017-10-30","arxiv_id":"1710.11063","code_links":[{"title":"jacobgil/pytorch-grad-cam","url":"https://github.com/jacobgil/pytorch-grad-cam"},{"title":"frgfm/torch-cam","url":"https://github.com/frgfm/torch-cam"},{"title":"sicara/tf-explain","url":"https://github.com/sicara/tf-explain"},{"title":"adityac94/Grad_CAM_plus_plus","url":"https://github.com/adityac94/Grad_CAM_plus_plus"},{"title":"yunqing-me/attackvlm","url":"https://github.com/yunqing-me/attackvlm"},{"title":"yiskw713/SmoothGradCAMplusplus","url":"https://github.com/yiskw713/SmoothGradCAMplusplus"},{"title":"yiskw713/scorecam","url":"https://github.com/yiskw713/scorecam"},{"title":"samson6460/tf_keras_gradcamplusplus","url":"https://github.com/samson6460/tf_keras_gradcamplusplus"},{"title":"samson6460/tf.keras-gradcamplusplus","url":"https://github.com/samson6460/tf.keras-gradcamplusplus"},{"title":"samson6460/tf-keras-gradcamplusplus","url":"https://github.com/samson6460/tf-keras-gradcamplusplus"},{"title":"totti0223/gradcamplusplus","url":"https://github.com/totti0223/gradcamplusplus"},{"title":"tristangomez44/metrics-saliency-maps","url":"https://github.com/tristangomez44/metrics-saliency-maps"},{"title":"yiskw713/ClassActivationMapping","url":"https://github.com/yiskw713/ClassActivationMapping"},{"title":"vcowwy/paddle-grad-cam","url":"https://github.com/vcowwy/paddle-grad-cam"},{"title":"lisssse14/Grad_CAM_PLUS_PLUS","url":"https://github.com/lisssse14/Grad_CAM_PLUS_PLUS"},{"title":"Ecgbert/Grad_CAM_PLUS_PLUS","url":"https://github.com/Ecgbert/Grad_CAM_PLUS_PLUS"},{"title":"pasrichashivam/Convnets_Grad-CAM_Grad-CAM-PlusPlus_Keras_tensorflow-2","url":"https://github.com/pasrichashivam/Convnets_Grad-CAM_Grad-CAM-PlusPlus_Keras_tensorflow-2"},{"title":"FelixMQuintana/Deep-Vasp-E","url":"https://github.com/FelixMQuintana/Deep-Vasp-E"},{"title":"fcUalberta/UAlberta-Multimedia-Masters-Program-Interpretable-AI-Part_1_2","url":"https://github.com/fcUalberta/UAlberta-Multimedia-Masters-Program-Interpretable-AI-Part_1_2"},{"title":"ftorres11/saliencysense","url":"https://github.com/ftorres11/saliencysense"},{"title":"eknim/gradcamplusplus","url":"https://github.com/eknim/gradcamplusplus"},{"title":"shashidhar100/Comparison-of-gradcam-and-gradcam_plus_plus_keras","url":"https://github.com/shashidhar100/Comparison-of-gradcam-and-gradcam_plus_plus_keras"},{"title":"v1an1/gradcamplusplus-cats-v-dogs","url":"https://github.com/v1an1/gradcamplusplus-cats-v-dogs"},{"title":"HollrayChan/gradcam-plus-plus","url":"https://github.com/HollrayChan/gradcam-plus-plus"}],"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/grad-cam-improved-visual-explanations-for#ran","syntology_url":"https://syntology.ai/paper/1710.11063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11063"}},"official":{"repos":["adityac94/Grad_CAM_plus_plus"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}}],"datasets":[{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":9,"of":9,"of_with_code":5,"tagged_in_all":9,"counts":{"archive_papers_tagged":9,"with_a_code_link":5,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":9,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":1,"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"},"items":[{"url":"/paper/grad-cam-improved-visual-explanations-for","slug":"grad-cam-improved-visual-explanations-for","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","date":"2017-10-30","arxiv_id":"1710.11063","repositories_listed":24,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"6 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/grad-cam-improved-visual-explanations-for#ran","syntology_url":"https://syntology.ai/paper/1710.11063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11063"}},"official":{"repos":["adityac94/Grad_CAM_plus_plus"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/score-camimproved-visual-explanations-via","slug":"score-camimproved-visual-explanations-via","title":"Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks","date":"2019-10-03","arxiv_id":"1910.01279","repositories_listed":9,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/score-camimproved-visual-explanations-via#ran","syntology_url":"https://syntology.ai/paper/1910.01279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01279"}},"official":{"repos":["haofanwang/Score-CAM"],"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"]}}},{"url":"/paper/less-is-more-fewer-interpretable-region-via","slug":"less-is-more-fewer-interpretable-region-via","title":"Less is More: Fewer Interpretable Region via Submodular Subset Selection","date":"2024-02-14","arxiv_id":"2402.09164","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/less-is-more-fewer-interpretable-region-via#ran","syntology_url":"https://syntology.ai/paper/2402.09164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09164"}},"official":{"repos":["ruoyuchen10/smdl-attribution"],"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/making-sense-of-dependence-efficient-black","slug":"making-sense-of-dependence-efficient-black","title":"Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure","date":"2022-06-13","arxiv_id":"2206.06219","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/making-sense-of-dependence-efficient-black#ran","syntology_url":"https://syntology.ai/paper/2206.06219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06219"}},"official":{"repos":["paulnovello/hsic-attribution-method"],"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/isea-an-interactive-pipeline-for-semantic","slug":"isea-an-interactive-pipeline-for-semantic","title":"iSEA: An Interactive Pipeline for Semantic Error Analysis of NLP Models","date":"2022-03-08","arxiv_id":"2203.04408","repositories_listed":1,"syntology":null},{"url":null,"slug":"xtower-a-multilingual-llm-for-explaining-and","title":"xTower: A Multilingual LLM for Explaining and Correcting Translation Errors","date":"2024-06-27","arxiv_id":"2406.19482","repositories_listed":0,"syntology":null},{"url":null,"slug":"variable-importance-measure-for-spatial","title":"Variable importance measure for spatial machine learning models with application to air pollution exposure prediction","date":"2024-06-04","arxiv_id":"2406.01982","repositories_listed":0,"syntology":null},{"url":null,"slug":"error-detection-in-egocentric-procedural-task","title":"Error Detection in Egocentric Procedural Task Videos","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-humans-strategies-in-maze","title":"Understanding Humans' Strategies in Maze Solving","date":"2013-07-22","arxiv_id":"1307.5713","repositories_listed":0,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/task/error-understanding/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/error-understanding/papers/ran/1","json":"/task/error-understanding/papers/ran/1.json","rows":4}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"d50a6567be1bb56e1d8d01c812810e0ea5fb7f7271d3763ed7f7d5e18999f330","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}