{"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/articles","name":"Articles","slug":"articles","description_markdown":null,"categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Audio","url":"/area/audio"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Medical","url":"/area/medical"},{"name":"Methodology","url":"/area/methodology"},{"name":"Music","url":"/area/music"},{"name":"Playing Games","url":"/area/playing-games"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":4012,"papers_with_code":1123,"benchmarks":0,"benchmark_tables_in_archive":2,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":2,"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":0,"subtasks":0,"parent_tasks":2},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/2d-classification","name":"2D Classification"},{"url":"/task/2d-human-pose-estimation","name":"2D Human Pose Estimation"}],"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":41,"rows_per_page":100,"shown":100,"of":4012,"of_with_code":1123,"tagged_in_all":4012,"counts":{"archive_papers_tagged":4012,"with_a_code_link":1123,"where_syntology_ran_a_sample":126,"not_listed_spam_title":0,"listed":4012,"listed_where_code_ran":126,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":104,"every_run_a_failure_of_syntologys_instrument":22,"listed_with_a_run_with_no_instrument_failure":104,"listed_every_run_a_failure_of_syntologys_instrument":22,"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/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","repositories_listed":67,"syntology":{"n":65,"n_ran":45,"n_constructed":0,"n_ran_checked":37,"n_instrument":8,"n_unverified":20,"n_honours":3,"n_violates":2,"n_no_contract":32,"n_pointer_only":7,"phrase":"45 ran (of which 0 constructed an object rather than computing a result; 37 with no instrument failure: 3 honoured, 2 violated, 32 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified","sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}},"official":{"repos":["openai/gpt-3"],"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/transformer-xl-attentive-language-models","slug":"transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","arxiv_id":"1901.02860","repositories_listed":37,"syntology":{"n":143,"n_ran":67,"n_constructed":37,"n_ran_checked":49,"n_instrument":18,"n_unverified":76,"n_honours":4,"n_violates":1,"n_no_contract":44,"n_pointer_only":43,"phrase":"67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified","sample_list":"/paper/transformer-xl-attentive-language-models#ran","syntology_url":"https://syntology.ai/paper/1901.02860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.02860"}},"official":{"repos":["kimiyoung/transformer-xl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/squad-100000-questions-for-machine","slug":"squad-100000-questions-for-machine","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","date":"2016-06-16","arxiv_id":"1606.05250","repositories_listed":21,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/squad-100000-questions-for-machine#ran","syntology_url":"https://syntology.ai/paper/1606.05250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.05250"}},"official":{"repos":["worksheets.codalab.org/worksheets/0xd53d03a48ef64b329c16b9baf0f99b0c"],"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/a-contextual-bandit-approach-to-personalized","slug":"a-contextual-bandit-approach-to-personalized","title":"A Contextual-Bandit Approach to Personalized News Article Recommendation","date":"2010-02-28","arxiv_id":"1003.0146","repositories_listed":12,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/a-contextual-bandit-approach-to-personalized#ran","syntology_url":"https://syntology.ai/paper/1003.0146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1003.0146"}},"official":null}},{"url":"/paper/reading-wikipedia-to-answer-open-domain","slug":"reading-wikipedia-to-answer-open-domain","title":"Reading Wikipedia to Answer Open-Domain Questions","date":"2017-03-31","arxiv_id":"1704.00051","repositories_listed":10,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reading-wikipedia-to-answer-open-domain#ran","syntology_url":"https://syntology.ai/paper/1704.00051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.00051"}},"official":{"repos":["facebookresearch/DrQA"],"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/wikihow-a-large-scale-text-summarization","slug":"wikihow-a-large-scale-text-summarization","title":"WikiHow: A Large Scale Text Summarization Dataset","date":"2018-10-18","arxiv_id":"1810.09305","repositories_listed":9,"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/wikihow-a-large-scale-text-summarization#ran","syntology_url":"https://syntology.ai/paper/1810.09305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.09305"}},"official":null}},{"url":"/paper/man-is-to-computer-programmer-as-woman-is-to","slug":"man-is-to-computer-programmer-as-woman-is-to","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","date":"2016-07-21","arxiv_id":"1607.06520","repositories_listed":8,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/man-is-to-computer-programmer-as-woman-is-to#ran","syntology_url":"https://syntology.ai/paper/1607.06520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.06520"}},"official":null}},{"url":"/paper/knowledge-graphs-meet-multi-modal-learning-a","slug":"knowledge-graphs-meet-multi-modal-learning-a","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","date":"2024-02-08","arxiv_id":"2402.05391","repositories_listed":6,"syntology":{"n":18,"n_ran":15,"n_constructed":0,"n_ran_checked":10,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":8,"n_pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 2 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/knowledge-graphs-meet-multi-modal-learning-a#ran","syntology_url":"https://syntology.ai/paper/2402.05391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05391"}},"official":{"repos":["zjukg/kg-mm-survey"],"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/image-based-table-recognition-data-model-and","slug":"image-based-table-recognition-data-model-and","title":"Image-based table recognition: data, model, and evaluation","date":"2019-11-25","arxiv_id":"1911.10683","repositories_listed":6,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/image-based-table-recognition-data-model-and#ran","syntology_url":"https://syntology.ai/paper/1911.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.10683"}},"official":{"repos":["ibm-aur-nlp/PubTabNet"],"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/scientific-statement-classification-over","slug":"scientific-statement-classification-over","title":"Scientific Statement Classification over arXiv.org","date":"2019-08-29","arxiv_id":"1908.10993","repositories_listed":6,"syntology":null},{"url":"/paper/190807836","slug":"190807836","title":"PubLayNet: largest dataset ever for document layout analysis","date":"2019-08-16","arxiv_id":"1908.07836","repositories_listed":6,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/190807836#ran","syntology_url":"https://syntology.ai/paper/1908.07836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07836"}},"official":{"repos":["ibm-aur-nlp/PubLayNet"],"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":["listed","official"]}}},{"url":"/paper/wikimatrix-mining-135m-parallel-sentences-in","slug":"wikimatrix-mining-135m-parallel-sentences-in","title":"WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia","date":"2019-07-10","arxiv_id":"1907.05791","repositories_listed":6,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/wikimatrix-mining-135m-parallel-sentences-in#ran","syntology_url":"https://syntology.ai/paper/1907.05791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.05791"}},"official":{"repos":["facebookresearch/LASER"],"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/newsroom-a-dataset-of-13-million-summaries","slug":"newsroom-a-dataset-of-13-million-summaries","title":"Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies","date":"2018-04-30","arxiv_id":"1804.11283","repositories_listed":6,"syntology":null},{"url":"/paper/large-scale-domain-specific-pretraining-for","slug":"large-scale-domain-specific-pretraining-for","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","date":"2023-03-02","arxiv_id":"2303.00915","repositories_listed":5,"syntology":null},{"url":"/paper/multi-task-identification-of-entities","slug":"multi-task-identification-of-entities","title":"Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction","date":"2018-08-29","arxiv_id":"1808.09602","repositories_listed":5,"syntology":null},{"url":"/paper/the-matrix-calculus-you-need-for-deep","slug":"the-matrix-calculus-you-need-for-deep","title":"The Matrix Calculus You Need For Deep Learning","date":"2018-02-05","arxiv_id":"1802.01528","repositories_listed":5,"syntology":null},{"url":"/paper/nsina-a-news-corpus-for-sinhala","slug":"nsina-a-news-corpus-for-sinhala","title":"NSINA: A News Corpus for Sinhala","date":"2024-03-25","arxiv_id":"2403.16571","repositories_listed":4,"syntology":null},{"url":"/paper/detectgpt-zero-shot-machine-generated-text","slug":"detectgpt-zero-shot-machine-generated-text","title":"DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature","date":"2023-01-26","arxiv_id":"2301.11305","repositories_listed":4,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/detectgpt-zero-shot-machine-generated-text#ran","syntology_url":"https://syntology.ai/paper/2301.11305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11305"}},"official":{"repos":["eric-mitchell/detect-gpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/pairwise-multi-class-document-classification","slug":"pairwise-multi-class-document-classification","title":"Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles","date":"2020-03-22","arxiv_id":"2003.09881","repositories_listed":4,"syntology":null},{"url":"/paper/dp-lstm-differential-privacy-inspired-lstm","slug":"dp-lstm-differential-privacy-inspired-lstm","title":"DP-LSTM: Differential Privacy-inspired LSTM for Stock Prediction Using Financial News","date":"2019-12-20","arxiv_id":"1912.10806","repositories_listed":4,"syntology":null},{"url":"/paper/mlqa-evaluating-cross-lingual-extractive","slug":"mlqa-evaluating-cross-lingual-extractive","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","date":"2019-10-16","arxiv_id":"1910.07475","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mlqa-evaluating-cross-lingual-extractive#ran","syntology_url":"https://syntology.ai/paper/1910.07475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.07475"}},"official":{"repos":["facebookresearch/MLQA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-zero-shot-text-classification","slug":"benchmarking-zero-shot-text-classification","title":"Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach","date":"2019-08-31","arxiv_id":"1909.00161","repositories_listed":4,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/benchmarking-zero-shot-text-classification#ran","syntology_url":"https://syntology.ai/paper/1909.00161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.00161"}},"official":{"repos":["yinwenpeng/BenchmarkingZeroShot"],"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":["listed","official","unlocated"]}}},{"url":"/paper/gan-qp-a-novel-gan-framework-without-gradient","slug":"gan-qp-a-novel-gan-framework-without-gradient","title":"GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint","date":"2018-11-18","arxiv_id":"1811.07296","repositories_listed":4,"syntology":null},{"url":"/paper/biosentvec-creating-sentence-embeddings-for","slug":"biosentvec-creating-sentence-embeddings-for","title":"BioSentVec: creating sentence embeddings for biomedical texts","date":"2018-10-22","arxiv_id":"1810.09302","repositories_listed":4,"syntology":null},{"url":"/paper/clinical-concept-embeddings-learned-from","slug":"clinical-concept-embeddings-learned-from","title":"Clinical Concept Embeddings Learned from Massive Sources of Multimodal Medical Data","date":"2018-04-04","arxiv_id":"1804.01486","repositories_listed":4,"syntology":null},{"url":"/paper/generating-wikipedia-by-summarizing-long","slug":"generating-wikipedia-by-summarizing-long","title":"Generating Wikipedia by Summarizing Long Sequences","date":"2018-01-30","arxiv_id":"1801.10198","repositories_listed":4,"syntology":null},{"url":"/paper/generating-news-headlines-with-recurrent","slug":"generating-news-headlines-with-recurrent","title":"Generating News Headlines with Recurrent Neural Networks","date":"2015-12-05","arxiv_id":"1512.01712","repositories_listed":4,"syntology":null},{"url":"/paper/fast-rhetorical-structure-theory-discourse","slug":"fast-rhetorical-structure-theory-discourse","title":"Fast Rhetorical Structure Theory Discourse Parsing","date":"2015-05-10","arxiv_id":"1505.02425","repositories_listed":4,"syntology":null},{"url":"/paper/scrambled-text-training-language-models-to","slug":"scrambled-text-training-language-models-to","title":"Scrambled text: training Language Models to correct OCR errors using synthetic data","date":"2024-09-29","arxiv_id":"2409.19735","repositories_listed":3,"syntology":null},{"url":"/paper/muse-machine-unlearning-six-way-evaluation","slug":"muse-machine-unlearning-six-way-evaluation","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","date":"2024-07-08","arxiv_id":"2407.06460","repositories_listed":3,"syntology":null},{"url":"/paper/internlm-xcomposer-a-vision-language-large","slug":"internlm-xcomposer-a-vision-language-large","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","date":"2023-09-26","arxiv_id":"2309.15112","repositories_listed":3,"syntology":null},{"url":"/paper/dapr-a-benchmark-on-document-aware-passage","slug":"dapr-a-benchmark-on-document-aware-passage","title":"DAPR: A Benchmark on Document-Aware Passage Retrieval","date":"2023-05-23","arxiv_id":"2305.13915","repositories_listed":3,"syntology":null},{"url":"/paper/reveal-the-unknown-out-of-knowledge-base","slug":"reveal-the-unknown-out-of-knowledge-base","title":"Reveal the Unknown: Out-of-Knowledge-Base Mention Discovery with Entity Linking","date":"2023-02-14","arxiv_id":"2302.07189","repositories_listed":3,"syntology":null},{"url":"/paper/ocr-vqgan-taming-text-within-image-generation","slug":"ocr-vqgan-taming-text-within-image-generation","title":"OCR-VQGAN: Taming Text-within-Image Generation","date":"2022-10-19","arxiv_id":"2210.11248","repositories_listed":3,"syntology":null},{"url":"/paper/how-large-language-models-are-transforming","slug":"how-large-language-models-are-transforming","title":"How Large Language Models are Transforming Machine-Paraphrased Plagiarism","date":"2022-10-07","arxiv_id":"2210.03568","repositories_listed":3,"syntology":null},{"url":"/paper/contextual-attention-network-transformer","slug":"contextual-attention-network-transformer","title":"Contextual Attention Network: Transformer Meets U-Net","date":"2022-03-02","arxiv_id":"2203.01932","repositories_listed":3,"syntology":null},{"url":"/paper/mumin-a-large-scale-multilingual-multimodal","slug":"mumin-a-large-scale-multilingual-multimodal","title":"MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset","date":"2022-02-23","arxiv_id":"2202.11684","repositories_listed":3,"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":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/mumin-a-large-scale-multilingual-multimodal#ran","syntology_url":"https://syntology.ai/paper/2202.11684","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.11684"}},"official":{"repos":["MuMiN-dataset/mumin-build"],"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/multilingual-open-text-1-0-public-domain-news","slug":"multilingual-open-text-1-0-public-domain-news","title":"Multilingual Open Text Release 1: Public Domain News in 44 Languages","date":"2022-01-14","arxiv_id":"2201.05609","repositories_listed":3,"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/multilingual-open-text-1-0-public-domain-news#ran","syntology_url":"https://syntology.ai/paper/2201.05609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05609"}},"official":{"repos":["VietHoang1710/khmer-nltk","bltlab/mot"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cliff-contrastive-learning-for-improving","slug":"cliff-contrastive-learning-for-improving","title":"CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization","date":"2021-09-19","arxiv_id":"2109.09209","repositories_listed":3,"syntology":null},{"url":"/paper/ethics-sheet-for-automatic-emotion","slug":"ethics-sheet-for-automatic-emotion","title":"Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis","date":"2021-09-17","arxiv_id":"2109.08256","repositories_listed":3,"syntology":null},{"url":"/paper/ethics-sheets-for-ai-tasks","slug":"ethics-sheets-for-ai-tasks","title":"Ethics Sheets for AI Tasks","date":"2021-07-02","arxiv_id":"2107.01183","repositories_listed":3,"syntology":null},{"url":"/paper/xor-qa-cross-lingual-open-retrieval-question","slug":"xor-qa-cross-lingual-open-retrieval-question","title":"XOR QA: Cross-lingual Open-Retrieval Question Answering","date":"2020-10-22","arxiv_id":"2010.11856","repositories_listed":3,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/xor-qa-cross-lingual-open-retrieval-question#ran","syntology_url":"https://syntology.ai/paper/2010.11856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11856"}},"official":{"repos":["AkariAsai/XORQA"],"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/let-s-stop-incorrect-comparisons-in-end-to","slug":"let-s-stop-incorrect-comparisons-in-end-to","title":"Let's Stop Incorrect Comparisons in End-to-end Relation Extraction!","date":"2020-09-22","arxiv_id":"2009.10684","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-summarize-from-human-feedback","slug":"learning-to-summarize-from-human-feedback","title":"Learning to summarize from human feedback","date":"2020-09-02","arxiv_id":"2009.01325","repositories_listed":3,"syntology":null},{"url":"/paper/end-to-end-abstractive-summarization-for","slug":"end-to-end-abstractive-summarization-for","title":"A Hierarchical Network for Abstractive Meeting Summarization with Cross-Domain Pretraining","date":"2020-04-04","arxiv_id":"2004.02016","repositories_listed":3,"syntology":null},{"url":"/paper/automatic-fact-guided-sentence-modification","slug":"automatic-fact-guided-sentence-modification","title":"Automatic Fact-guided Sentence Modification","date":"2019-09-30","arxiv_id":"1909.13838","repositories_listed":3,"syntology":null},{"url":"/paper/language-model-embeddings-improve-sentiment","slug":"language-model-embeddings-improve-sentiment","title":"LANGUAGE MODEL EMBEDDINGS IMPROVE SENTIMENT ANALYSIS IN RUSSIAN","date":"2019-05-29","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-interpret-satellite-images-in","slug":"learning-to-interpret-satellite-images-in","title":"Learning to Interpret Satellite Images in Global Scale Using Wikipedia","date":"2019-05-07","arxiv_id":"1905.02506","repositories_listed":3,"syntology":null},{"url":"/paper/a-dataset-for-document-grounded-conversations","slug":"a-dataset-for-document-grounded-conversations","title":"A Dataset for Document Grounded Conversations","date":"2018-09-19","arxiv_id":"1809.07358","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-dataset-for-document-grounded-conversations#ran","syntology_url":"https://syntology.ai/paper/1809.07358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.07358"}},"official":{"repos":["festvox/datasets-CMU_DoG"],"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/dont-give-me-the-details-just-the-summary","slug":"dont-give-me-the-details-just-the-summary","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","date":"2018-08-27","arxiv_id":"1808.08745","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dont-give-me-the-details-just-the-summary#ran","syntology_url":"https://syntology.ai/paper/1808.08745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.08745"}},"official":{"repos":["shashiongithub/XSum"],"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":["listed","official"]}}},{"url":"/paper/fundamentals-of-recurrent-neural-network-rnn","slug":"fundamentals-of-recurrent-neural-network-rnn","title":"Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network","date":"2018-08-09","arxiv_id":"1808.03314","repositories_listed":3,"syntology":null},{"url":"/paper/news-session-based-recommendations-using-deep","slug":"news-session-based-recommendations-using-deep","title":"News Session-Based Recommendations using Deep Neural Networks","date":"2018-07-31","arxiv_id":"1808.00076","repositories_listed":3,"syntology":null},{"url":"/paper/cail2018-a-large-scale-legal-dataset-for","slug":"cail2018-a-large-scale-legal-dataset-for","title":"CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction","date":"2018-07-04","arxiv_id":"1807.02478","repositories_listed":3,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/cail2018-a-large-scale-legal-dataset-for#ran","syntology_url":"https://syntology.ai/paper/1807.02478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.02478"}},"official":null}},{"url":"/paper/data-driven-summarization-of-scientific","slug":"data-driven-summarization-of-scientific","title":"Data-driven Summarization of Scientific Articles","date":"2018-04-24","arxiv_id":"1804.08875","repositories_listed":3,"syntology":null},{"url":"/paper/neural-models-for-documents-with-metadata","slug":"neural-models-for-documents-with-metadata","title":"Neural Models for Documents with Metadata","date":"2017-05-25","arxiv_id":"1705.09296","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-models-for-documents-with-metadata#ran","syntology_url":"https://syntology.ai/paper/1705.09296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.09296"}},"official":{"repos":["dallascard/neural_topic_models","dallascard/scholar"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/3d-object-reconstruction-from-hand-object","slug":"3d-object-reconstruction-from-hand-object","title":"3D Object Reconstruction from Hand-Object Interactions","date":"2017-04-03","arxiv_id":"1704.00529","repositories_listed":3,"syntology":null},{"url":"/paper/a-novel-framework-to-expedite-systematic","slug":"a-novel-framework-to-expedite-systematic","title":"A Novel Framework to Expedite Systematic Reviews by Automatically Building Information Extraction Training Corpora","date":"2016-06-21","arxiv_id":"1606.06424","repositories_listed":3,"syntology":null},{"url":"/paper/a-thorough-examination-of-the-cnndaily-mail","slug":"a-thorough-examination-of-the-cnndaily-mail","title":"A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task","date":"2016-06-09","arxiv_id":"1606.02858","repositories_listed":3,"syntology":null},{"url":"/paper/the-goldilocks-principle-reading-childrens","slug":"the-goldilocks-principle-reading-childrens","title":"The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations","date":"2015-11-07","arxiv_id":"1511.02301","repositories_listed":3,"syntology":null},{"url":"/paper/content-based-recommendations-with-poisson","slug":"content-based-recommendations-with-poisson","title":"Content-based recommendations with Poisson factorization","date":"2014-12-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/biomedica-an-open-biomedical-image-caption","slug":"biomedica-an-open-biomedical-image-caption","title":"BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature","date":"2025-01-13","arxiv_id":"2501.07171","repositories_listed":2,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/biomedica-an-open-biomedical-image-caption#ran","syntology_url":"https://syntology.ai/paper/2501.07171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07171"}},"official":{"repos":["ale9806/open_clip_with_biomedica","minwoosun/biomedica-etl"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/2409-13740","slug":"2409-13740","title":"Language agents achieve superhuman synthesis of scientific knowledge","date":"2024-09-10","arxiv_id":"2409.13740","repositories_listed":2,"syntology":null},{"url":"/paper/stard-a-chinese-statute-retrieval-dataset","slug":"stard-a-chinese-statute-retrieval-dataset","title":"STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionals","date":"2024-06-21","arxiv_id":"2406.15313","repositories_listed":2,"syntology":null},{"url":"/paper/large-language-models-in-targeted-sentiment","slug":"large-language-models-in-targeted-sentiment","title":"Large Language Models in Targeted Sentiment Analysis","date":"2024-04-18","arxiv_id":"2404.12342","repositories_listed":2,"syntology":null},{"url":"/paper/llm-attributor-interactive-visual-attribution","slug":"llm-attributor-interactive-visual-attribution","title":"LLM Attributor: Interactive Visual Attribution for LLM Generation","date":"2024-04-01","arxiv_id":"2404.01361","repositories_listed":2,"syntology":null},{"url":"/paper/leveraging-corpus-metadata-to-detect-template","slug":"leveraging-corpus-metadata-to-detect-template","title":"Leveraging Corpus Metadata to Detect Template-based Translation: An Exploratory Case Study of the Egyptian Arabic Wikipedia Edition","date":"2024-03-31","arxiv_id":"2404.00565","repositories_listed":2,"syntology":null},{"url":"/paper/a-dataset-for-pharmacovigilance-in-german","slug":"a-dataset-for-pharmacovigilance-in-german","title":"A Dataset for Pharmacovigilance in German, French, and Japanese: Annotating Adverse Drug Reactions across Languages","date":"2024-03-27","arxiv_id":"2403.18336","repositories_listed":2,"syntology":null},{"url":"/paper/fundus-a-simple-to-use-news-scraper-optimized","slug":"fundus-a-simple-to-use-news-scraper-optimized","title":"Fundus: A Simple-to-Use News Scraper Optimized for High Quality Extractions","date":"2024-03-22","arxiv_id":"2403.15279","repositories_listed":2,"syntology":null},{"url":"/paper/assisting-in-writing-wikipedia-like-articles","slug":"assisting-in-writing-wikipedia-like-articles","title":"Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models","date":"2024-02-22","arxiv_id":"2402.14207","repositories_listed":2,"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":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/assisting-in-writing-wikipedia-like-articles#ran","syntology_url":"https://syntology.ai/paper/2402.14207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14207"}},"official":{"repos":["stanford-oval/storm"],"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/extracting-definienda-in-mathematical","slug":"extracting-definienda-in-mathematical","title":"Extracting Definienda in Mathematical Scholarly Articles with Transformers","date":"2023-11-21","arxiv_id":"2311.12448","repositories_listed":2,"syntology":null},{"url":"/paper/famus-frames-across-multiple-sources","slug":"famus-frames-across-multiple-sources","title":"FAMuS: Frames Across Multiple Sources","date":"2023-11-09","arxiv_id":"2311.05601","repositories_listed":2,"syntology":null},{"url":"/paper/large-language-models-for-propaganda","slug":"large-language-models-for-propaganda","title":"Large Language Models for Propaganda Detection","date":"2023-10-10","arxiv_id":"2310.06422","repositories_listed":2,"syntology":null},{"url":"/paper/compressing-context-to-enhance-inference","slug":"compressing-context-to-enhance-inference","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","date":"2023-10-09","arxiv_id":"2310.06201","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/compressing-context-to-enhance-inference#ran","syntology_url":"https://syntology.ai/paper/2310.06201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06201"}},"official":{"repos":["liyucheng09/selective_context"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/jcola-japanese-corpus-of-linguistic","slug":"jcola-japanese-corpus-of-linguistic","title":"JCoLA: Japanese Corpus of Linguistic Acceptability","date":"2023-09-22","arxiv_id":"2309.12676","repositories_listed":2,"syntology":null},{"url":"/paper/speaker-attribution-in-german-parliamentary","slug":"speaker-attribution-in-german-parliamentary","title":"Speaker attribution in German parliamentary debates with QLoRA-adapted large language models","date":"2023-09-18","arxiv_id":"2309.09902","repositories_listed":2,"syntology":null},{"url":"/paper/j-guard-journalism-guided-adversarially","slug":"j-guard-journalism-guided-adversarially","title":"J-Guard: Journalism Guided Adversarially Robust Detection of AI-generated News","date":"2023-09-06","arxiv_id":"2309.03164","repositories_listed":2,"syntology":null},{"url":"/paper/multimodal-machine-learning-for-extraction-of","slug":"multimodal-machine-learning-for-extraction-of","title":"Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)","date":"2023-07-18","arxiv_id":"2307.09047","repositories_listed":2,"syntology":null},{"url":"/paper/a-corpus-for-sentence-level-subjectivity","slug":"a-corpus-for-sentence-level-subjectivity","title":"A Corpus for Sentence-level Subjectivity Detection on English News Articles","date":"2023-05-29","arxiv_id":"2305.18034","repositories_listed":2,"syntology":null},{"url":"/paper/ghostbuster-detecting-text-ghostwritten-by","slug":"ghostbuster-detecting-text-ghostwritten-by","title":"Ghostbuster: Detecting Text Ghostwritten by Large Language Models","date":"2023-05-24","arxiv_id":"2305.15047","repositories_listed":2,"syntology":null},{"url":"/paper/machine-made-media-monitoring-the","slug":"machine-made-media-monitoring-the","title":"Machine-Made Media: Monitoring the Mobilization of Machine-Generated Articles on Misinformation and Mainstream News Websites","date":"2023-05-16","arxiv_id":"2305.09820","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/machine-made-media-monitoring-the#ran","syntology_url":"https://syntology.ai/paper/2305.09820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.09820"}},"official":{"repos":["hanshanley/machine-made-media"],"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/wikiweb2m-a-page-level-multimodal-wikipedia","slug":"wikiweb2m-a-page-level-multimodal-wikipedia","title":"WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset","date":"2023-05-09","arxiv_id":"2305.05432","repositories_listed":2,"syntology":null},{"url":"/paper/tiefake-title-text-similarity-and-emotion","slug":"tiefake-title-text-similarity-and-emotion","title":"TieFake: Title-Text Similarity and Emotion-Aware Fake News Detection","date":"2023-04-19","arxiv_id":"2304.09421","repositories_listed":2,"syntology":null},{"url":"/paper/topic-modelling-of-swedish-newspaper-articles","slug":"topic-modelling-of-swedish-newspaper-articles","title":"Topic Modelling of Swedish Newspaper Articles about Coronavirus: a Case Study using Latent Dirichlet Allocation Method","date":"2023-01-08","arxiv_id":"2301.03029","repositories_listed":2,"syntology":null},{"url":"/paper/an-extractive-abstractive-approach-for-multi","slug":"an-extractive-abstractive-approach-for-multi","title":"An Extractive-Abstractive Approach for Multi-document Summarization of Scientific Articles for Literature Review","date":"2022-10-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/generating-extended-and-multilingual","slug":"generating-extended-and-multilingual","title":"Generating Extended and Multilingual Summaries with Pre-trained Transformers","date":"2022-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/streamingqa-a-benchmark-for-adaptation-to-new","slug":"streamingqa-a-benchmark-for-adaptation-to-new","title":"StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models","date":"2022-05-23","arxiv_id":"2205.11388","repositories_listed":2,"syntology":null},{"url":"/paper/politics-pretraining-with-same-story-article-1","slug":"politics-pretraining-with-same-story-article-1","title":"POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection","date":"2022-05-02","arxiv_id":"2205.00619","repositories_listed":2,"syntology":null},{"url":"/paper/detecting-stance-in-scientific-papers-did-we","slug":"detecting-stance-in-scientific-papers-did-we","title":"Did AI get more negative recently?","date":"2022-02-28","arxiv_id":"2202.13610","repositories_listed":2,"syntology":null},{"url":"/paper/pmc-patients-a-large-scale-dataset-of-patient","slug":"pmc-patients-a-large-scale-dataset-of-patient","title":"PMC-Patients: A Large-scale Dataset of Patient Summaries and Relations for Benchmarking Retrieval-based Clinical Decision Support Systems","date":"2022-02-28","arxiv_id":"2202.13876","repositories_listed":2,"syntology":null},{"url":"/paper/mumuqa-multimedia-multi-hop-news-question","slug":"mumuqa-multimedia-multi-hop-news-question","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","date":"2021-12-20","arxiv_id":"2112.10728","repositories_listed":2,"syntology":null},{"url":"/paper/newsclaims-a-new-benchmark-for-claim","slug":"newsclaims-a-new-benchmark-for-claim","title":"NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge","date":"2021-12-16","arxiv_id":"2112.08544","repositories_listed":2,"syntology":null},{"url":"/paper/rollinglda-an-update-algorithm-of-latent","slug":"rollinglda-an-update-algorithm-of-latent","title":"RollingLDA: An Update Algorithm of Latent Dirichlet Allocation to Construct Consistent Time Series from Textual Data","date":"2021-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/sportssum2-0-generating-high-quality-sports","slug":"sportssum2-0-generating-high-quality-sports","title":"SportsSum2.0: Generating High-Quality Sports News from Live Text Commentary","date":"2021-10-12","arxiv_id":"2110.05750","repositories_listed":2,"syntology":null},{"url":"/paper/scientific-evidence-extraction","slug":"scientific-evidence-extraction","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","date":"2021-09-30","arxiv_id":"2110.00061","repositories_listed":2,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scientific-evidence-extraction#ran","syntology_url":"https://syntology.ai/paper/2110.00061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00061"}},"official":{"repos":["microsoft/table-transformer"],"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":["listed","official"]}}},{"url":"/paper/mind-mainstream-and-independent-news","slug":"mind-mainstream-and-independent-news","title":"MINT -- Mainstream and Independent News Text Corpus","date":"2021-08-13","arxiv_id":"2108.06249","repositories_listed":2,"syntology":null},{"url":"/paper/combining-optimization-methods-using-an","slug":"combining-optimization-methods-using-an","title":"Combining Optimization Methods Using an Adaptive Meta Optimizer","date":"2021-06-19","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/bringing-structure-into-summaries-a-faceted","slug":"bringing-structure-into-summaries-a-faceted","title":"Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents","date":"2021-05-31","arxiv_id":"2106.00130","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-reason-for-text-generation-from","slug":"learning-to-reason-for-text-generation-from","title":"Learning to Reason for Text Generation from Scientific Tables","date":"2021-04-16","arxiv_id":"2104.08296","repositories_listed":2,"syntology":null},{"url":"/paper/identifying-machine-paraphrased-plagiarism","slug":"identifying-machine-paraphrased-plagiarism","title":"Identifying Machine-Paraphrased Plagiarism","date":"2021-03-22","arxiv_id":"2103.11909","repositories_listed":2,"syntology":null},{"url":"/paper/using-transformer-based-ensemble-learning-to","slug":"using-transformer-based-ensemble-learning-to","title":"Using Transformer based Ensemble Learning to classify Scientific Articles","date":"2021-02-19","arxiv_id":"2102.09991","repositories_listed":2,"syntology":null}],"syntology_records":26,"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":126,"papers_where_code_ran_first_page":"/task/articles/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":41,"url":"/task/articles/papers/2","json":"/task/articles/papers/2.json","rows":100},{"order":"archive","page":3,"of":41,"url":"/task/articles/papers/3","json":"/task/articles/papers/3.json","rows":100},{"order":"archive","page":4,"of":41,"url":"/task/articles/papers/4","json":"/task/articles/papers/4.json","rows":100},{"order":"archive","page":5,"of":41,"url":"/task/articles/papers/5","json":"/task/articles/papers/5.json","rows":100},{"order":"archive","page":6,"of":41,"url":"/task/articles/papers/6","json":"/task/articles/papers/6.json","rows":100},{"order":"archive","page":7,"of":41,"url":"/task/articles/papers/7","json":"/task/articles/papers/7.json","rows":100},{"order":"archive","page":8,"of":41,"url":"/task/articles/papers/8","json":"/task/articles/papers/8.json","rows":100},{"order":"archive","page":9,"of":41,"url":"/task/articles/papers/9","json":"/task/articles/papers/9.json","rows":100},{"order":"archive","page":10,"of":41,"url":"/task/articles/papers/10","json":"/task/articles/papers/10.json","rows":100},{"order":"archive","page":11,"of":41,"url":"/task/articles/papers/11","json":"/task/articles/papers/11.json","rows":100},{"order":"archive","page":12,"of":41,"url":"/task/articles/papers/12","json":"/task/articles/papers/12.json","rows":100},{"order":"archive","page":13,"of":41,"url":"/task/articles/papers/13","json":"/task/articles/papers/13.json","rows":100},{"order":"archive","page":14,"of":41,"url":"/task/articles/papers/14","json":"/task/articles/papers/14.json","rows":100},{"order":"archive","page":15,"of":41,"url":"/task/articles/papers/15","json":"/task/articles/papers/15.json","rows":100},{"order":"archive","page":16,"of":41,"url":"/task/articles/papers/16","json":"/task/articles/papers/16.json","rows":100},{"order":"archive","page":17,"of":41,"url":"/task/articles/papers/17","json":"/task/articles/papers/17.json","rows":100},{"order":"archive","page":18,"of":41,"url":"/task/articles/papers/18","json":"/task/articles/papers/18.json","rows":100},{"order":"archive","page":19,"of":41,"url":"/task/articles/papers/19","json":"/task/articles/papers/19.json","rows":100},{"order":"archive","page":20,"of":41,"url":"/task/articles/papers/20","json":"/task/articles/papers/20.json","rows":100},{"order":"archive","page":21,"of":41,"url":"/task/articles/papers/21","json":"/task/articles/papers/21.json","rows":100},{"order":"archive","page":22,"of":41,"url":"/task/articles/papers/22","json":"/task/articles/papers/22.json","rows":100},{"order":"archive","page":23,"of":41,"url":"/task/articles/papers/23","json":"/task/articles/papers/23.json","rows":100},{"order":"archive","page":24,"of":41,"url":"/task/articles/papers/24","json":"/task/articles/papers/24.json","rows":100},{"order":"archive","page":25,"of":41,"url":"/task/articles/papers/25","json":"/task/articles/papers/25.json","rows":100},{"order":"archive","page":26,"of":41,"url":"/task/articles/papers/26","json":"/task/articles/papers/26.json","rows":100},{"order":"archive","page":27,"of":41,"url":"/task/articles/papers/27","json":"/task/articles/papers/27.json","rows":100},{"order":"archive","page":28,"of":41,"url":"/task/articles/papers/28","json":"/task/articles/papers/28.json","rows":100},{"order":"archive","page":29,"of":41,"url":"/task/articles/papers/29","json":"/task/articles/papers/29.json","rows":100},{"order":"archive","page":30,"of":41,"url":"/task/articles/papers/30","json":"/task/articles/papers/30.json","rows":100},{"order":"archive","page":31,"of":41,"url":"/task/articles/papers/31","json":"/task/articles/papers/31.json","rows":100},{"order":"archive","page":32,"of":41,"url":"/task/articles/papers/32","json":"/task/articles/papers/32.json","rows":100},{"order":"archive","page":33,"of":41,"url":"/task/articles/papers/33","json":"/task/articles/papers/33.json","rows":100},{"order":"archive","page":34,"of":41,"url":"/task/articles/papers/34","json":"/task/articles/papers/34.json","rows":100},{"order":"archive","page":35,"of":41,"url":"/task/articles/papers/35","json":"/task/articles/papers/35.json","rows":100},{"order":"archive","page":36,"of":41,"url":"/task/articles/papers/36","json":"/task/articles/papers/36.json","rows":100},{"order":"archive","page":37,"of":41,"url":"/task/articles/papers/37","json":"/task/articles/papers/37.json","rows":100},{"order":"archive","page":38,"of":41,"url":"/task/articles/papers/38","json":"/task/articles/papers/38.json","rows":100},{"order":"archive","page":39,"of":41,"url":"/task/articles/papers/39","json":"/task/articles/papers/39.json","rows":100},{"order":"archive","page":40,"of":41,"url":"/task/articles/papers/40","json":"/task/articles/papers/40.json","rows":100},{"order":"archive","page":41,"of":41,"url":"/task/articles/papers/41","json":"/task/articles/papers/41.json","rows":12},{"order":"ran","page":1,"of":2,"url":"/task/articles/papers/ran/1","json":"/task/articles/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/articles/papers/ran/2","json":"/task/articles/papers/ran/2.json","rows":26}],"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":"4ecfcb89e8b238b344d4df08fbd6daf30ba66f9131ed45073a9aeee8773183c2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}