{"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/open-question","name":"Open-Ended Question Answering","slug":"open-question","description_markdown":"Open-ended questions are defined as those that simply pose the question, without imposing any constraints on the format of the response. This distinguishes them from questions with a predetermined answer format.","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"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":796,"papers_with_code":228,"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":1},"benchmarks":[],"datasets":[{"url":"/dataset/sfd","name":"SF20K","full_name":"Short-Films 20K","num_papers_in_archive":1},{"url":"/dataset/worldcuisines","name":"WorldCuisines","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/question-answering","name":"Question Answering"}],"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":8,"rows_per_page":100,"shown":100,"of":796,"of_with_code":228,"tagged_in_all":796,"counts":{"archive_papers_tagged":796,"with_a_code_link":228,"where_syntology_ran_a_sample":70,"not_listed_spam_title":0,"listed":796,"listed_where_code_ran":70,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":59,"every_run_a_failure_of_syntologys_instrument":11,"listed_with_a_run_with_no_instrument_failure":59,"listed_every_run_a_failure_of_syntologys_instrument":11,"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/chestx-ray8-hospital-scale-chest-x-ray","slug":"chestx-ray8-hospital-scale-chest-x-ray","title":"ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases","date":"2017-05-05","arxiv_id":"1705.02315","repositories_listed":26,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chestx-ray8-hospital-scale-chest-x-ray#ran","syntology_url":"https://syntology.ai/paper/1705.02315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.02315"}},"official":null}},{"url":"/paper/pre-training-graph-neural-networks","slug":"pre-training-graph-neural-networks","title":"Strategies for Pre-training Graph Neural Networks","date":"2019-05-29","arxiv_id":"1905.12265","repositories_listed":11,"syntology":{"n":14,"n_ran":13,"n_constructed":1,"n_ran_checked":9,"n_instrument":4,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":5,"phrase":"13 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pre-training-graph-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1905.12265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12265"}},"official":{"repos":["snap-stanford/pretrain-gnns"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/would-mega-scale-datasets-further-enhance","slug":"would-mega-scale-datasets-further-enhance","title":"Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?","date":"2020-04-10","arxiv_id":"2004.04968","repositories_listed":10,"syntology":{"n":22,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/would-mega-scale-datasets-further-enhance#ran","syntology_url":"https://syntology.ai/paper/2004.04968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04968"}},"official":{"repos":["kenshohara/3D-ResNets-PyTorch"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hybrid-task-cascade-for-instance-segmentation","slug":"hybrid-task-cascade-for-instance-segmentation","title":"Hybrid Task Cascade for Instance Segmentation","date":"2019-01-22","arxiv_id":"1901.07518","repositories_listed":5,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hybrid-task-cascade-for-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/1901.07518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07518"}},"official":{"repos":["open-mmlab/mmdetection"],"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/stable-sample-compression-schemes-new","slug":"stable-sample-compression-schemes-new","title":"Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound","date":"2020-11-09","arxiv_id":"2011.04586","repositories_listed":4,"syntology":null},{"url":"/paper/data-sketching-for-faster-training-of-machine","slug":"data-sketching-for-faster-training-of-machine","title":"Coresets for Data-efficient Training of Machine Learning Models","date":"2019-06-05","arxiv_id":"1906.01827","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/data-sketching-for-faster-training-of-machine#ran","syntology_url":"https://syntology.ai/paper/1906.01827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.01827"}},"official":{"repos":["baharanm/craig"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/point-m2ae-multi-scale-masked-autoencoders","slug":"point-m2ae-multi-scale-masked-autoencoders","title":"Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training","date":"2022-05-28","arxiv_id":"2205.14401","repositories_listed":3,"syntology":null},{"url":"/paper/hear-2021-holistic-evaluation-of-audio","slug":"hear-2021-holistic-evaluation-of-audio","title":"HEAR: Holistic Evaluation of Audio Representations","date":"2022-03-06","arxiv_id":"2203.03022","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hear-2021-holistic-evaluation-of-audio#ran","syntology_url":"https://syntology.ai/paper/2203.03022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03022"}},"official":{"repos":["neuralaudio/hear-eval-kit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/flag-adversarial-data-augmentation-for-graph-1","slug":"flag-adversarial-data-augmentation-for-graph-1","title":"Robust Optimization as Data Augmentation for Large-scale Graphs","date":"2020-10-19","arxiv_id":"2010.09891","repositories_listed":3,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/flag-adversarial-data-augmentation-for-graph-1#ran","syntology_url":"https://syntology.ai/paper/2010.09891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09891"}},"official":{"repos":["devnkong/FLAG"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-shapley-value-experience-replay","slug":"adversarial-shapley-value-experience-replay","title":"Online Class-Incremental Continual Learning with Adversarial Shapley Value","date":"2020-08-31","arxiv_id":"2009.00093","repositories_listed":3,"syntology":null},{"url":"/paper/opiec-an-open-information-extraction-corpus","slug":"opiec-an-open-information-extraction-corpus","title":"OPIEC: An Open Information Extraction Corpus","date":"2019-04-28","arxiv_id":"1904.12324","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-cluster-faces-on-an-affinity","slug":"learning-to-cluster-faces-on-an-affinity","title":"Learning to Cluster Faces on an Affinity Graph","date":"2019-04-04","arxiv_id":"1904.02749","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-to-cluster-faces-on-an-affinity#ran","syntology_url":"https://syntology.ai/paper/1904.02749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02749"}},"official":{"repos":["yl-1993/learn-to-cluster"],"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/convolutional-analysis-operator-learning","slug":"convolutional-analysis-operator-learning","title":"Convolutional Analysis Operator Learning: Dependence on Training Data","date":"2019-02-21","arxiv_id":"1902.08267","repositories_listed":3,"syntology":null},{"url":"/paper/deep-learning-based-electroencephalography","slug":"deep-learning-based-electroencephalography","title":"Deep learning-based electroencephalography analysis: a systematic review","date":"2019-01-16","arxiv_id":"1901.05498","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/deep-learning-based-electroencephalography#ran","syntology_url":"https://syntology.ai/paper/1901.05498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.05498"}},"official":null}},{"url":"/paper/on-the-dimensionality-of-word-embedding","slug":"on-the-dimensionality-of-word-embedding","title":"On the Dimensionality of Word Embedding","date":"2018-12-11","arxiv_id":"1812.04224","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-the-dimensionality-of-word-embedding#ran","syntology_url":"https://syntology.ai/paper/1812.04224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.04224"}},"official":{"repos":["ziyin-dl/word-embedding-dimensionality-selection","aaaasssddf/PIP-experiments"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/chain-of-discussion-a-multi-model-framework","slug":"chain-of-discussion-a-multi-model-framework","title":"Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering","date":"2024-02-26","arxiv_id":"2402.16313","repositories_listed":2,"syntology":null},{"url":"/paper/when-does-aggregating-multiple-skills-with","slug":"when-does-aggregating-multiple-skills-with","title":"When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP","date":"2023-05-23","arxiv_id":"2305.14007","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/when-does-aggregating-multiple-skills-with#ran","syntology_url":"https://syntology.ai/paper/2305.14007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14007"}},"official":{"repos":["edisonni-hku/mtl4finance","EdisonNi-hku/when-does-mtl-work"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/last-layer-fairness-fine-tuning-is-simple-and","slug":"last-layer-fairness-fine-tuning-is-simple-and","title":"Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks","date":"2023-04-08","arxiv_id":"2304.03935","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/last-layer-fairness-fine-tuning-is-simple-and#ran","syntology_url":"https://syntology.ai/paper/2304.03935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03935"}},"official":{"repos":["yuzhenmao/fairness-finetuning"],"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/slca-slow-learner-with-classifier-alignment","slug":"slca-slow-learner-with-classifier-alignment","title":"SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model","date":"2023-03-09","arxiv_id":"2303.05118","repositories_listed":2,"syntology":null},{"url":"/paper/data-efficient-contrastive-self-supervised","slug":"data-efficient-contrastive-self-supervised","title":"Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least","date":"2023-02-18","arxiv_id":"2302.09195","repositories_listed":2,"syntology":null},{"url":"/paper/analyzing-the-effectiveness-of-the-underlying","slug":"analyzing-the-effectiveness-of-the-underlying","title":"Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering","date":"2023-02-12","arxiv_id":"2302.05963","repositories_listed":2,"syntology":null},{"url":"/paper/training-language-models-for-deeper","slug":"training-language-models-for-deeper","title":"Training language models to summarize narratives improves brain alignment","date":"2022-12-21","arxiv_id":"2212.10898","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/training-language-models-for-deeper#ran","syntology_url":"https://syntology.ai/paper/2212.10898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10898"}},"official":{"repos":["awwkl/brain_language_narratives","awwkl/brain_language_summarization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/when-less-is-more-on-the-value-of-co-training","slug":"when-less-is-more-on-the-value-of-co-training","title":"When Less is More: On the Value of \"Co-training\" for Semi-Supervised Software Defect Predictors","date":"2022-11-10","arxiv_id":"2211.05920","repositories_listed":2,"syntology":null},{"url":"/paper/linearly-mapping-from-image-to-text-space","slug":"linearly-mapping-from-image-to-text-space","title":"Linearly Mapping from Image to Text Space","date":"2022-09-30","arxiv_id":"2209.15162","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/linearly-mapping-from-image-to-text-space#ran","syntology_url":"https://syntology.ai/paper/2209.15162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.15162"}},"official":{"repos":["jmerullo/limber"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/coscl-cooperation-of-small-continual-learners","slug":"coscl-cooperation-of-small-continual-learners","title":"CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One","date":"2022-07-13","arxiv_id":"2207.06543","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/coscl-cooperation-of-small-continual-learners#ran","syntology_url":"https://syntology.ai/paper/2207.06543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06543"}},"official":{"repos":["lywang3081/coscl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/testing-the-ability-of-language-models-to-1","slug":"testing-the-ability-of-language-models-to-1","title":"Testing the Ability of Language Models to Interpret Figurative Language","date":"2022-04-26","arxiv_id":"2204.12632","repositories_listed":2,"syntology":{"n":14,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/testing-the-ability-of-language-models-to-1#ran","syntology_url":"https://syntology.ai/paper/2204.12632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.12632"}},"official":{"repos":["nightingal3/fig-qa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/bamboo-building-mega-scale-vision-dataset","slug":"bamboo-building-mega-scale-vision-dataset","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","date":"2022-03-15","arxiv_id":"2203.07845","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bamboo-building-mega-scale-vision-dataset#ran","syntology_url":"https://syntology.ai/paper/2203.07845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07845"}},"official":{"repos":["davidzhangyuanhan/bamboo","zhangyuanhan-ai/bamboo"],"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":["official"]}}},{"url":"/paper/parameter-differentiation-based-multilingual","slug":"parameter-differentiation-based-multilingual","title":"Parameter Differentiation based Multilingual Neural Machine Translation","date":"2021-12-27","arxiv_id":"2112.13619","repositories_listed":2,"syntology":null},{"url":"/paper/likelihood-free-frequentist-inference","slug":"likelihood-free-frequentist-inference","title":"Likelihood-Free Frequentist Inference: Bridging Classical Statistics and Machine Learning for Reliable Simulator-Based Inference","date":"2021-07-08","arxiv_id":"2107.03920","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/likelihood-free-frequentist-inference#ran","syntology_url":"https://syntology.ai/paper/2107.03920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.03920"}},"official":{"repos":["lee-group-cmu/lf2i","Mr8ND/ACORE-LFI"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/small-in-distribution-changes-in-3d","slug":"small-in-distribution-changes-in-3d","title":"In-distribution adversarial attacks on object recognition models using gradient-free search","date":"2021-06-30","arxiv_id":"2106.16198","repositories_listed":2,"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/small-in-distribution-changes-in-3d#ran","syntology_url":"https://syntology.ai/paper/2106.16198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.16198"}},"official":{"repos":["spandan-madan/in_distribution_adversarial_examples","in-dist-adversarials/in_distribution_adversarial_examples"],"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/argument-mining-driven-analysis-of-peer","slug":"argument-mining-driven-analysis-of-peer","title":"Argument Mining Driven Analysis of Peer-Reviews","date":"2020-12-10","arxiv_id":"2012.07743","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/argument-mining-driven-analysis-of-peer#ran","syntology_url":"https://syntology.ai/paper/2012.07743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.07743"}},"official":{"repos":["fromm-m/aaai2021-am-peer-reviews"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/identifying-learning-rules-from-neural","slug":"identifying-learning-rules-from-neural","title":"Identifying Learning Rules From Neural Network Observables","date":"2020-10-22","arxiv_id":"2010.11765","repositories_listed":2,"syntology":null},{"url":"/paper/discovering-reinforcement-learning-algorithms","slug":"discovering-reinforcement-learning-algorithms","title":"Discovering Reinforcement Learning Algorithms","date":"2020-07-17","arxiv_id":"2007.08794","repositories_listed":2,"syntology":null},{"url":"/paper/attack-of-the-tails-yes-you-really-can","slug":"attack-of-the-tails-yes-you-really-can","title":"Attack of the Tails: Yes, You Really Can Backdoor Federated Learning","date":"2020-07-09","arxiv_id":"2007.05084","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/attack-of-the-tails-yes-you-really-can#ran","syntology_url":"https://syntology.ai/paper/2007.05084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.05084"}},"official":{"repos":["ksreenivasan/OOD_Federated_Learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/graph-neural-network-based-coarse-grained","slug":"graph-neural-network-based-coarse-grained","title":"Graph Neural Network Based Coarse-Grained Mapping Prediction","date":"2020-06-24","arxiv_id":"2007.04921","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/graph-neural-network-based-coarse-grained#ran","syntology_url":"https://syntology.ai/paper/2007.04921","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.04921"}},"official":{"repos":["rochesterxugroup/DSGPM","rochesterxugroup/HAM_dataset"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/attention-guided-context-feature-pyramid","slug":"attention-guided-context-feature-pyramid","title":"Attention-guided Context Feature Pyramid Network for Object Detection","date":"2020-05-23","arxiv_id":"2005.11475","repositories_listed":2,"syntology":null},{"url":"/paper/langevin-dqn","slug":"langevin-dqn","title":"Langevin DQN","date":"2020-02-17","arxiv_id":"2002.07282","repositories_listed":2,"syntology":null},{"url":"/paper/learning-deformable-registration-of-medical","slug":"learning-deformable-registration-of-medical","title":"Learning Deformable Registration of Medical Images with Anatomical Constraints","date":"2020-01-20","arxiv_id":"2001.07183","repositories_listed":2,"syntology":null},{"url":"/paper/learning-representations-for-time-series","slug":"learning-representations-for-time-series","title":"Learning Representations for Time Series Clustering","date":"2019-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/distilling-the-knowledge-of-bert-for-text-1","slug":"distilling-the-knowledge-of-bert-for-text-1","title":"Distilling Knowledge Learned in BERT for Text Generation","date":"2019-11-10","arxiv_id":"1911.03829","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/distilling-the-knowledge-of-bert-for-text-1#ran","syntology_url":"https://syntology.ai/paper/1911.03829","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03829"}},"official":{"repos":["ChenRocks/Distill-BERT-Textgen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/trb-a-novel-triplet-representation-for-1","slug":"trb-a-novel-triplet-representation-for-1","title":"TRB: A Novel Triplet Representation for Understanding 2D Human Body","date":"2019-10-25","arxiv_id":"1910.11535","repositories_listed":2,"syntology":null},{"url":"/paper/rapid-learning-or-feature-reuse-towards","slug":"rapid-learning-or-feature-reuse-towards","title":"Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML","date":"2019-09-19","arxiv_id":"1909.09157","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-model-based-reinforcement","slug":"benchmarking-model-based-reinforcement","title":"Benchmarking Model-Based Reinforcement Learning","date":"2019-07-03","arxiv_id":"1907.02057","repositories_listed":2,"syntology":null},{"url":"/paper/dont-paint-it-black-white-box-explanations","slug":"dont-paint-it-black-white-box-explanations","title":"Evaluating Explanation Methods for Deep Learning in Security","date":"2019-06-05","arxiv_id":"1906.02108","repositories_listed":2,"syntology":null},{"url":"/paper/generating-contrastive-explanations-with","slug":"generating-contrastive-explanations-with","title":"Leveraging Latent Features for Local Explanations","date":"2019-05-29","arxiv_id":"1905.12698","repositories_listed":2,"syntology":null},{"url":"/paper/colonel-blotto-games-and-hide-and-seek-games","slug":"colonel-blotto-games-and-hide-and-seek-games","title":"Path Planning Problems with Side Observations-When Colonels Play Hide-and-Seek","date":"2019-05-27","arxiv_id":"1905.11151","repositories_listed":2,"syntology":null},{"url":"/paper/structured-variational-learning-of-bayesian","slug":"structured-variational-learning-of-bayesian","title":"Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors","date":"2018-06-13","arxiv_id":"1806.05975","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/structured-variational-learning-of-bayesian#ran","syntology_url":"https://syntology.ai/paper/1806.05975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05975"}},"official":null}},{"url":"/paper/stochastic-subgradient-method-converges-at","slug":"stochastic-subgradient-method-converges-at","title":"Stochastic subgradient method converges at the rate $O(k^{-1/4})$ on weakly convex functions","date":"2018-02-08","arxiv_id":"1802.02988","repositories_listed":2,"syntology":null},{"url":"/paper/how-intelligence-can-change-the-course-of","slug":"how-intelligence-can-change-the-course-of","title":"How intelligence can change the course of evolution","date":"2017-10-01","arxiv_id":"1710.00352","repositories_listed":2,"syntology":null},{"url":"/paper/full-capacity-unitary-recurrent-neural","slug":"full-capacity-unitary-recurrent-neural","title":"Full-Capacity Unitary Recurrent Neural Networks","date":"2016-10-31","arxiv_id":"1611.00035","repositories_listed":2,"syntology":null},{"url":"/paper/a-monte-carlo-aixi-approximation","slug":"a-monte-carlo-aixi-approximation","title":"A Monte Carlo AIXI Approximation","date":"2009-09-04","arxiv_id":"0909.0801","repositories_listed":2,"syntology":null},{"url":"/paper/culfit-a-fine-grained-cultural-aware-llm","slug":"culfit-a-fine-grained-cultural-aware-llm","title":"CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis","date":"2025-05-26","arxiv_id":"2505.19484","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/culfit-a-fine-grained-cultural-aware-llm#ran","syntology_url":"https://syntology.ai/paper/2505.19484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19484"}},"official":{"repos":["mmadmax/culfit"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/o-2-searcher-a-searching-based-agent-model","slug":"o-2-searcher-a-searching-based-agent-model","title":"O$^2$-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering","date":"2025-05-22","arxiv_id":"2505.16582","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/o-2-searcher-a-searching-based-agent-model#ran","syntology_url":"https://syntology.ai/paper/2505.16582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16582"}},"official":{"repos":["acade-mate/o2-searcher"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/2505-10772","slug":"2505-10772","title":"Ranked Voting based Self-Consistency of Large Language Models","date":"2025-05-16","arxiv_id":"2505.10772","repositories_listed":1,"syntology":null},{"url":"/paper/fspo-few-shot-preference-optimization-of","slug":"fspo-few-shot-preference-optimization-of","title":"FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users","date":"2025-02-26","arxiv_id":"2502.19312","repositories_listed":1,"syntology":null},{"url":"/paper/neptune-the-long-orbit-to-benchmarking-long","slug":"neptune-the-long-orbit-to-benchmarking-long","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","date":"2024-12-12","arxiv_id":"2412.09582","repositories_listed":1,"syntology":null},{"url":"/paper/utilize-the-flow-before-stepping-into-the","slug":"utilize-the-flow-before-stepping-into-the","title":"Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning","date":"2024-10-09","arxiv_id":"2410.06913","repositories_listed":1,"syntology":null},{"url":"/paper/ranking-generated-answers-on-the-agreement-of","slug":"ranking-generated-answers-on-the-agreement-of","title":"Ranking Generated Answers: On the Agreement of Retrieval Models with Humans on Consumer Health Questions","date":"2024-08-19","arxiv_id":"2408.09831","repositories_listed":1,"syntology":null},{"url":"/paper/llasa-large-multimodal-agent-for-human","slug":"llasa-large-multimodal-agent-for-human","title":"LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors","date":"2024-06-20","arxiv_id":"2406.14498","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llasa-large-multimodal-agent-for-human#ran","syntology_url":"https://syntology.ai/paper/2406.14498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14498"}},"official":{"repos":["bashlab/llasa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/extrinsic-evaluation-of-cultural-competence","slug":"extrinsic-evaluation-of-cultural-competence","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","date":"2024-06-17","arxiv_id":"2406.11565","repositories_listed":1,"syntology":null},{"url":"/paper/scar-efficient-instruction-tuning-for-large","slug":"scar-efficient-instruction-tuning-for-large","title":"SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking","date":"2024-06-16","arxiv_id":"2406.10882","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/scar-efficient-instruction-tuning-for-large#ran","syntology_url":"https://syntology.ai/paper/2406.10882","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10882"}},"official":{"repos":["zhuang-li/scar"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/automated-evaluation-of-retrieval-augmented","slug":"automated-evaluation-of-retrieval-augmented","title":"Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation","date":"2024-05-22","arxiv_id":"2405.13622","repositories_listed":1,"syntology":null},{"url":"/paper/sciqag-a-framework-for-auto-generated","slug":"sciqag-a-framework-for-auto-generated","title":"SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-grained Evaluation","date":"2024-05-16","arxiv_id":"2405.09939","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-elementary-multilingual","slug":"evaluating-the-elementary-multilingual","title":"Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ","date":"2024-03-06","arxiv_id":"2403.03814","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/evaluating-the-elementary-multilingual#ran","syntology_url":"https://syntology.ai/paper/2403.03814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03814"}},"official":{"repos":["paul-rottger/multiq"],"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/bimedix-bilingual-medical-mixture-of-experts","slug":"bimedix-bilingual-medical-mixture-of-experts","title":"BiMediX: Bilingual Medical Mixture of Experts LLM","date":"2024-02-20","arxiv_id":"2402.13253","repositories_listed":1,"syntology":null},{"url":"/paper/on-early-detection-of-hallucinations-in","slug":"on-early-detection-of-hallucinations-in","title":"On Early Detection of Hallucinations in Factual Question Answering","date":"2023-12-19","arxiv_id":"2312.14183","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/on-early-detection-of-hallucinations-in#ran","syntology_url":"https://syntology.ai/paper/2312.14183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14183"}},"official":{"repos":["amazon-science/llm-hallucinations-factual-qa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/performance-trade-offs-of-watermarking-large","slug":"performance-trade-offs-of-watermarking-large","title":"Downstream Trade-offs of a Family of Text Watermarks","date":"2023-11-16","arxiv_id":"2311.09816","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/performance-trade-offs-of-watermarking-large#ran","syntology_url":"https://syntology.ai/paper/2311.09816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09816"}},"official":{"repos":["flair-iisc/watermark_tradeoffs"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/monolingual-or-multilingual-instruction","slug":"monolingual-or-multilingual-instruction","title":"Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca","date":"2023-09-16","arxiv_id":"2309.08958","repositories_listed":1,"syntology":null},{"url":"/paper/prd-peer-rank-and-discussion-improve-large","slug":"prd-peer-rank-and-discussion-improve-large","title":"PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations","date":"2023-07-06","arxiv_id":"2307.02762","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/prd-peer-rank-and-discussion-improve-large#ran","syntology_url":"https://syntology.ai/paper/2307.02762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.02762"}},"official":{"repos":["bcdnlp/prd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/2d-shapley-a-framework-for-fragmented-data","slug":"2d-shapley-a-framework-for-fragmented-data","title":"2D-Shapley: A Framework for Fragmented Data Valuation","date":"2023-06-18","arxiv_id":"2306.10473","repositories_listed":1,"syntology":null},{"url":"/paper/adversaries-with-limited-information-in-the","slug":"adversaries-with-limited-information-in-the","title":"Adversaries with Limited Information in the Friedkin--Johnsen Model","date":"2023-06-17","arxiv_id":"2306.10313","repositories_listed":1,"syntology":null},{"url":"/paper/mol-instructions-a-large-scale-biomolecular","slug":"mol-instructions-a-large-scale-biomolecular","title":"Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models","date":"2023-06-13","arxiv_id":"2306.08018","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mol-instructions-a-large-scale-biomolecular#ran","syntology_url":"https://syntology.ai/paper/2306.08018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08018"}},"official":{"repos":["zjunlp/mol-instructions"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-do-or-learning-while-doing","slug":"learning-to-do-or-learning-while-doing","title":"Learning to Do or Learning While Doing: Reinforcement Learning and Bayesian Optimisation for Online Continuous Tuning","date":"2023-06-06","arxiv_id":"2306.03739","repositories_listed":1,"syntology":null},{"url":"/paper/tight-regret-bounds-for-single-pass-streaming","slug":"tight-regret-bounds-for-single-pass-streaming","title":"Tight Regret Bounds for Single-pass Streaming Multi-armed Bandits","date":"2023-06-03","arxiv_id":"2306.02208","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tight-regret-bounds-for-single-pass-streaming#ran","syntology_url":"https://syntology.ai/paper/2306.02208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02208"}},"official":{"repos":["jhwjhw0123/streaming-regret-minimization-mabs"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/speaking-the-language-of-your-listener","slug":"speaking-the-language-of-your-listener","title":"Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind","date":"2023-05-31","arxiv_id":"2305.19933","repositories_listed":1,"syntology":null},{"url":"/paper/2305-14550","slug":"2305-14550","title":"When should we prefer Decision Transformers for Offline Reinforcement Learning?","date":"2023-05-23","arxiv_id":"2305.14550","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2305-14550#ran","syntology_url":"https://syntology.ai/paper/2305.14550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14550"}},"official":{"repos":["prajjwal1/rl_paradigm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/knowledge-of-knowledge-exploring-known","slug":"knowledge-of-knowledge-exploring-known","title":"Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models","date":"2023-05-23","arxiv_id":"2305.13712","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/knowledge-of-knowledge-exploring-known#ran","syntology_url":"https://syntology.ai/paper/2305.13712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13712"}},"official":{"repos":["amayuelas/knowledge-of-knowledge"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mplm-sim-unveiling-better-cross-lingual","slug":"mplm-sim-unveiling-better-cross-lingual","title":"mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models","date":"2023-05-23","arxiv_id":"2305.13684","repositories_listed":1,"syntology":null},{"url":"/paper/improving-implicit-feedback-based","slug":"improving-implicit-feedback-based","title":"Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment","date":"2023-05-09","arxiv_id":"2305.05585","repositories_listed":1,"syntology":null},{"url":"/paper/the-role-of-relevance-in-fair-ranking","slug":"the-role-of-relevance-in-fair-ranking","title":"The Role of Relevance in Fair Ranking","date":"2023-05-09","arxiv_id":"2305.05608","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/the-role-of-relevance-in-fair-ranking#ran","syntology_url":"https://syntology.ai/paper/2305.05608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05608"}},"official":{"repos":["aparna-b/fairrankingrelevance"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/2x-faster-language-model-pre-training-via","slug":"2x-faster-language-model-pre-training-via","title":"Masked Structural Growth for 2x Faster Language Model Pre-training","date":"2023-05-04","arxiv_id":"2305.02869","repositories_listed":1,"syntology":{"n":34,"n_ran":16,"n_constructed":6,"n_ran_checked":10,"n_instrument":6,"n_unverified":18,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/2x-faster-language-model-pre-training-via#ran","syntology_url":"https://syntology.ai/paper/2305.02869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02869"}},"official":{"repos":["cofe-ai/msg"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":6,"n_ran_no_instrument_failure":10,"n_unverified":18,"ran_from_kinds":["official"]}}},{"url":"/paper/shall-we-pretrain-autoregressive-language","slug":"shall-we-pretrain-autoregressive-language","title":"Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study","date":"2023-04-13","arxiv_id":"2304.06762","repositories_listed":1,"syntology":null},{"url":"/paper/autorl-hyperparameter-landscapes","slug":"autorl-hyperparameter-landscapes","title":"AutoRL Hyperparameter Landscapes","date":"2023-04-05","arxiv_id":"2304.02396","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/autorl-hyperparameter-landscapes#ran","syntology_url":"https://syntology.ai/paper/2304.02396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.02396"}},"official":{"repos":["automl/autorl-landscape"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/time-series-contrastive-learning-with","slug":"time-series-contrastive-learning-with","title":"Time Series Contrastive Learning with Information-Aware Augmentations","date":"2023-03-21","arxiv_id":"2303.11911","repositories_listed":1,"syntology":null},{"url":"/paper/data-efficient-training-of-cnns-and","slug":"data-efficient-training-of-cnns-and","title":"Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective","date":"2023-03-03","arxiv_id":"2303.02095","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-contrastive-learning-for-1","slug":"cross-modal-contrastive-learning-for-1","title":"Cross-modal Contrastive Learning for Multimodal Fake News Detection","date":"2023-02-25","arxiv_id":"2302.14057","repositories_listed":1,"syntology":null},{"url":"/paper/a-robust-optimisation-perspective-on","slug":"a-robust-optimisation-perspective-on","title":"A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks","date":"2023-01-26","arxiv_id":"2301.11342","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-robust-optimisation-perspective-on#ran","syntology_url":"https://syntology.ai/paper/2301.11342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11342"}},"official":{"repos":["sen-uni-kn/specrepair"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/predictive-world-models-from-real-world","slug":"predictive-world-models-from-real-world","title":"Predictive World Models from Real-World Partial Observations","date":"2023-01-12","arxiv_id":"2301.04783","repositories_listed":1,"syntology":null},{"url":"/paper/toward-building-general-foundation-models-for","slug":"toward-building-general-foundation-models-for","title":"Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks","date":"2023-01-12","arxiv_id":"2301.05065","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-theory-of-diversity-in-ensemble","slug":"a-unified-theory-of-diversity-in-ensemble","title":"A Unified Theory of Diversity in Ensemble Learning","date":"2023-01-10","arxiv_id":"2301.03962","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-unified-theory-of-diversity-in-ensemble#ran","syntology_url":"https://syntology.ai/paper/2301.03962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.03962"}},"official":{"repos":["echostatements/decompose"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/fgahoi-fine-grained-anchors-for-human-object","slug":"fgahoi-fine-grained-anchors-for-human-object","title":"FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection","date":"2023-01-08","arxiv_id":"2301.04019","repositories_listed":1,"syntology":null},{"url":"/paper/buffer-balancing-accuracy-efficiency-and","slug":"buffer-balancing-accuracy-efficiency-and","title":"BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-encode-clinical","slug":"large-language-models-encode-clinical","title":"Large Language Models Encode Clinical Knowledge","date":"2022-12-26","arxiv_id":"2212.13138","repositories_listed":1,"syntology":null},{"url":"/paper/does-clip-bind-concepts-probing","slug":"does-clip-bind-concepts-probing","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","date":"2022-12-20","arxiv_id":"2212.10537","repositories_listed":1,"syntology":null},{"url":"/paper/rangeaugment-efficient-online-augmentation","slug":"rangeaugment-efficient-online-augmentation","title":"RangeAugment: Efficient Online Augmentation with Range Learning","date":"2022-12-20","arxiv_id":"2212.10553","repositories_listed":1,"syntology":null},{"url":"/paper/why-can-gpt-learn-in-context-language-models","slug":"why-can-gpt-learn-in-context-language-models","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","date":"2022-12-20","arxiv_id":"2212.10559","repositories_listed":1,"syntology":null},{"url":"/paper/a-revenue-function-for-comparison-based","slug":"a-revenue-function-for-comparison-based","title":"A Revenue Function for Comparison-Based Hierarchical Clustering","date":"2022-11-29","arxiv_id":"2211.16459","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-impact-of-adversarial","slug":"understanding-the-impact-of-adversarial","title":"Understanding the Impact of Adversarial Robustness on Accuracy Disparity","date":"2022-11-28","arxiv_id":"2211.15762","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/understanding-the-impact-of-adversarial#ran","syntology_url":"https://syntology.ai/paper/2211.15762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.15762"}},"official":{"repos":["accuracy-disparity/at-on-ad"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/near-optimal-multiple-testing-in-bayesian","slug":"near-optimal-multiple-testing-in-bayesian","title":"Near-optimal multiple testing in Bayesian linear models with finite-sample FDR control","date":"2022-11-04","arxiv_id":"2211.02778","repositories_listed":1,"syntology":null},{"url":"/paper/instance-segmentation-for-chinese-character","slug":"instance-segmentation-for-chinese-character","title":"Instance Segmentation for Chinese Character Stroke Extraction, Datasets and Benchmarks","date":"2022-10-25","arxiv_id":"2210.13826","repositories_listed":1,"syntology":null}],"syntology_records":42,"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":70,"papers_where_code_ran_first_page":"/task/open-question/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":"archive","page":2,"of":8,"url":"/task/open-question/papers/2","json":"/task/open-question/papers/2.json","rows":100},{"order":"archive","page":3,"of":8,"url":"/task/open-question/papers/3","json":"/task/open-question/papers/3.json","rows":100},{"order":"archive","page":4,"of":8,"url":"/task/open-question/papers/4","json":"/task/open-question/papers/4.json","rows":100},{"order":"archive","page":5,"of":8,"url":"/task/open-question/papers/5","json":"/task/open-question/papers/5.json","rows":100},{"order":"archive","page":6,"of":8,"url":"/task/open-question/papers/6","json":"/task/open-question/papers/6.json","rows":100},{"order":"archive","page":7,"of":8,"url":"/task/open-question/papers/7","json":"/task/open-question/papers/7.json","rows":100},{"order":"archive","page":8,"of":8,"url":"/task/open-question/papers/8","json":"/task/open-question/papers/8.json","rows":96},{"order":"ran","page":1,"of":1,"url":"/task/open-question/papers/ran/1","json":"/task/open-question/papers/ran/1.json","rows":70}],"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":"efb1800f72c0dd3193395a61748b7a1916dbb10af783fccd73e4f070fe8eac89","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}