{"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/overall-test","name":"Overall - Test","slug":"overall-test","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":34,"papers_with_code":11,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/jeebench","name":"JEEBench","full_name":"","num_papers_in_archive":15},{"url":"/dataset/feedbackqa","name":"FeedbackQA","full_name":"","num_papers_in_archive":2}],"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":34,"of":34,"of_with_code":11,"tagged_in_all":34,"counts":{"archive_papers_tagged":34,"with_a_code_link":11,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":34,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"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/comparative-study-of-deep-learning-methods","slug":"comparative-study-of-deep-learning-methods","title":"Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients","date":"2020-07-29","arxiv_id":"2007.15546","repositories_listed":3,"syntology":null},{"url":"/paper/freelb-enhanced-adversarial-training-for","slug":"freelb-enhanced-adversarial-training-for","title":"FreeLB: Enhanced Adversarial Training for Natural Language Understanding","date":"2019-09-25","arxiv_id":"1909.11764","repositories_listed":2,"syntology":null},{"url":"/paper/deep-modeling-and-optimization-of-medical","slug":"deep-modeling-and-optimization-of-medical","title":"Deep Modeling and Optimization of Medical Image Classification","date":"2025-05-29","arxiv_id":"2505.23040","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-training-of-deep-neural-operator","slug":"efficient-training-of-deep-neural-operator","title":"Efficient Training of Deep Neural Operator Networks via Randomized Sampling","date":"2024-09-20","arxiv_id":"2409.13280","repositories_listed":1,"syntology":null},{"url":"/paper/watt-weight-average-test-time-adaption-of","slug":"watt-weight-average-test-time-adaption-of","title":"WATT: Weight Average Test-Time Adaptation of CLIP","date":"2024-06-19","arxiv_id":"2406.13875","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 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; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/watt-weight-average-test-time-adaption-of#ran","syntology_url":"https://syntology.ai/paper/2406.13875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13875"}},"official":{"repos":["mehrdad-noori/watt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/small-language-models-fine-tuned-to","slug":"small-language-models-fine-tuned-to","title":"Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning","date":"2023-10-21","arxiv_id":"2310.18338","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/small-language-models-fine-tuned-to#ran","syntology_url":"https://syntology.ai/paper/2310.18338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18338"}},"official":{"repos":["lcs2-iiitd/daslam"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/transferable-availability-poisoning-attacks","slug":"transferable-availability-poisoning-attacks","title":"Transferable Availability Poisoning Attacks","date":"2023-10-08","arxiv_id":"2310.05141","repositories_listed":1,"syntology":null},{"url":"/paper/have-llms-advanced-enough-a-challenging","slug":"have-llms-advanced-enough-a-challenging","title":"Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models","date":"2023-05-24","arxiv_id":"2305.15074","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/have-llms-advanced-enough-a-challenging#ran","syntology_url":"https://syntology.ai/paper/2305.15074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.15074"}},"official":{"repos":["hgaurav2k/jeebench"],"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":["found_in_text"]}}},{"url":"/paper/amplifying-membership-exposure-via-data","slug":"amplifying-membership-exposure-via-data","title":"Amplifying Membership Exposure via Data Poisoning","date":"2022-11-01","arxiv_id":"2211.00463","repositories_listed":1,"syntology":null},{"url":"/paper/using-interactive-feedback-to-improve-the-1","slug":"using-interactive-feedback-to-improve-the-1","title":"Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment","date":"2022-04-06","arxiv_id":"2204.03025","repositories_listed":1,"syntology":null},{"url":"/paper/localizing-open-ontology-qa-semantic-parsers","slug":"localizing-open-ontology-qa-semantic-parsers","title":"Localizing Open-Ontology QA Semantic Parsers in a Day Using Machine Translation","date":"2020-10-10","arxiv_id":"2010.05106","repositories_listed":1,"syntology":null},{"url":null,"slug":"underage-detection-through-a-multi-task-and","title":"Underage Detection through a Multi-Task and MultiAge Approach for Screening Minors in Unconstrained Imagery","date":"2025-06-12","arxiv_id":"2506.10689","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-10111","title":"AI5GTest: AI-Driven Specification-Aware Automated Testing and Validation of 5G O-RAN Components","date":"2025-06-11","arxiv_id":"2506.10111","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-speech-emotion-with-label-variance","title":"Modeling speech emotion with label variance and analyzing performance across speakers and unseen acoustic conditions","date":"2025-03-24","arxiv_id":"2503.22711","repositories_listed":0,"syntology":null},{"url":null,"slug":"unify-and-triumph-polyglot-diverse-and-self","title":"Unify and Triumph: Polyglot, Diverse, and Self-Consistent Generation of Unit Tests with LLMs","date":"2025-03-20","arxiv_id":"2503.16144","repositories_listed":0,"syntology":null},{"url":null,"slug":"cost-saving-llm-cascades-with-early","title":"Cost-Saving LLM Cascades with Early Abstention","date":"2025-02-13","arxiv_id":"2502.09054","repositories_listed":0,"syntology":null},{"url":null,"slug":"classifier-enhanced-deep-learning-model-for","title":"Classifier Enhanced Deep Learning Model for Erythroblast Differentiation with Limited Data","date":"2024-11-23","arxiv_id":"2411.15592","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradual-learning-optimizing-fine-tuning-with","title":"Gradual Learning: Optimizing Fine-Tuning with Partially Mastered Knowledge in Large Language Models","date":"2024-10-08","arxiv_id":"2410.05802","repositories_listed":0,"syntology":null},{"url":null,"slug":"artificial-data-point-generation-in-clustered","title":"Artificial Data Point Generation in Clustered Latent Space for Small Medical Datasets","date":"2024-09-26","arxiv_id":"2409.17685","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-future-of-software-testing-ai-powered","title":"The Future of Software Testing: AI-Powered Test Case Generation and Validation","date":"2024-09-09","arxiv_id":"2409.05808","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-layer-selection-for-latent-data","title":"Optimal Layer Selection for Latent Data Augmentation","date":"2024-08-24","arxiv_id":"2408.13426","repositories_listed":0,"syntology":null},{"url":null,"slug":"network-two-sample-test-for-block-models","title":"Network two-sample test for block models","date":"2024-06-10","arxiv_id":"2406.06014","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmid-high-resolution-mmwave-imaging-for-human","title":"mmID: High-Resolution mmWave Imaging for Human Identification","date":"2024-02-01","arxiv_id":"2402.00996","repositories_listed":0,"syntology":null},{"url":null,"slug":"contraction-properties-of-the-global","title":"Contraction Properties of the Global Workspace Primitive","date":"2023-10-02","arxiv_id":"2310.01571","repositories_listed":0,"syntology":null},{"url":null,"slug":"targeted-data-generation-finding-and-fixing","title":"Targeted Data Generation: Finding and Fixing Model Weaknesses","date":"2023-05-28","arxiv_id":"2305.17804","repositories_listed":0,"syntology":null},{"url":null,"slug":"constructing-open-cloze-tests-using","title":"Constructing Open Cloze Tests Using Generation and Discrimination Capabilities of Transformers","date":"2022-04-14","arxiv_id":"2204.07237","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-human-cell-classification-in-sparse","title":"Automated Human Cell Classification in Sparse Datasets using Few-Shot Learning","date":"2021-07-27","arxiv_id":"2107.13093","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-the-same-different-task-with","title":"Solving the Same-Different Task with Convolutional Neural Networks","date":"2021-01-22","arxiv_id":"2101.09129","repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-the-outcome-of-judicial-decisions","title":"Predicting the Outcome of Judicial Decisions made by the European Court of Human Rights","date":"2019-12-16","arxiv_id":"1912.10819","repositories_listed":0,"syntology":null},{"url":null,"slug":"fault-sneaking-attack-a-stealthy-framework","title":"Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks","date":"2019-05-28","arxiv_id":"1905.12032","repositories_listed":0,"syntology":null},{"url":null,"slug":"application-of-densenet-in-camera-model","title":"Application of DenseNet in Camera Model Identification and Post-processing Detection","date":"2019-05-27","arxiv_id":"1809.00576","repositories_listed":0,"syntology":null},{"url":null,"slug":"gandef-a-gan-based-adversarial-training","title":"GanDef: A GAN based Adversarial Training Defense for Neural Network Classifier","date":"2019-03-06","arxiv_id":"1903.02585","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-and-accurate-classification-of","title":"Fast and accurate classification of echocardiograms using deep learning","date":"2017-06-27","arxiv_id":"1706.08658","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-tree-learning-hierarchies-of-visual","title":"Attention Tree: Learning Hierarchies of Visual Features for Large-Scale Image Recognition","date":"2016-08-01","arxiv_id":"1608.00611","repositories_listed":0,"syntology":null}],"syntology_records":3,"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":3,"papers_where_code_ran_first_page":"/task/overall-test/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/overall-test/papers/ran/1","json":"/task/overall-test/papers/ran/1.json","rows":3}],"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":"edd69f3e3085ad7cd534333a51f180d9466c2891f7eb3b612f21d2ee6deec02e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}