{"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/papers/2","list_of":"/task/articles","task":"Articles","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":41,"rows_per_page":100,"rows":[101,200],"of":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":107,"every_run_a_failure_of_syntologys_instrument":19,"listed_with_a_run_with_no_instrument_failure":107,"listed_every_run_a_failure_of_syntologys_instrument":19,"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"},"first_page":"/task/articles","prev":"/task/articles","next":"/task/articles/papers/3","papers":[{"url":"/paper/learning-to-match-mathematical-statements","slug":"learning-to-match-mathematical-statements","title":"Learning to Match Mathematical Statements with Proofs","date":"2021-02-03","arxiv_id":"2102.02110","repositories_listed":2,"syntology":null},{"url":"/paper/wangchanberta-pretraining-transformer-based","slug":"wangchanberta-pretraining-transformer-based","title":"WangchanBERTa: Pretraining transformer-based Thai Language Models","date":"2021-01-24","arxiv_id":"2101.09635","repositories_listed":2,"syntology":null},{"url":"/paper/transformer-based-automatic-covid-19-fake","slug":"transformer-based-automatic-covid-19-fake","title":"Transformer based Automatic COVID-19 Fake News Detection System","date":"2021-01-01","arxiv_id":"2101.00180","repositories_listed":2,"syntology":null},{"url":"/paper/fighting-an-infodemic-covid-19-fake-news","slug":"fighting-an-infodemic-covid-19-fake-news","title":"Fighting an Infodemic: COVID-19 Fake News Dataset","date":"2020-11-06","arxiv_id":"2011.03327","repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-for-text-attribute-transfer-a","slug":"deep-learning-for-text-attribute-transfer-a","title":"Deep Learning for Text Style Transfer: A Survey","date":"2020-11-01","arxiv_id":"2011.00416","repositories_listed":2,"syntology":null},{"url":"/paper/language-models-are-open-knowledge-graphs-1","slug":"language-models-are-open-knowledge-graphs-1","title":"Language Models are Open Knowledge Graphs","date":"2020-10-22","arxiv_id":"2010.11967","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-models-are-open-knowledge-graphs-1#ran","syntology_url":"https://syntology.ai/paper/2010.11967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11967"}},"official":null}},{"url":"/paper/where-are-the-facts-searching-for-fact","slug":"where-are-the-facts-searching-for-fact","title":"Where Are the Facts? Searching for Fact-checked Information to Alleviate the Spread of Fake News","date":"2020-10-07","arxiv_id":"2010.03159","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/where-are-the-facts-searching-for-fact#ran","syntology_url":"https://syntology.ai/paper/2010.03159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03159"}},"official":{"repos":["nguyenvo09/EMNLP2020"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/roft-a-tool-for-evaluating-human-detection-of","slug":"roft-a-tool-for-evaluating-human-detection-of","title":"RoFT: A Tool for Evaluating Human Detection of Machine-Generated Text","date":"2020-10-06","arxiv_id":"2010.03070","repositories_listed":2,"syntology":null},{"url":"/paper/abstractive-summarization-of-spoken","slug":"abstractive-summarization-of-spoken","title":"Abstractive Summarization of Spoken andWritten Instructions with BERT","date":"2020-08-21","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/align-then-summarize-automatic-alignment-1","slug":"align-then-summarize-automatic-alignment-1","title":"Align then Summarize: Automatic Alignment Methods for Summarization Corpus Creation","date":"2020-07-15","arxiv_id":"2007.07841","repositories_listed":2,"syntology":null},{"url":"/paper/mind-a-large-scale-dataset-for-news","slug":"mind-a-large-scale-dataset-for-news","title":"MIND: A Large-scale Dataset for News Recommendation","date":"2020-07-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/screenplay-summarization-using-latent","slug":"screenplay-summarization-using-latent","title":"Screenplay Summarization Using Latent Narrative Structure","date":"2020-04-27","arxiv_id":"2004.12727","repositories_listed":2,"syntology":null},{"url":"/paper/privacy-preserving-news-recommendation-model","slug":"privacy-preserving-news-recommendation-model","title":"Privacy-Preserving News Recommendation Model Learning","date":"2020-03-21","arxiv_id":"2003.09592","repositories_listed":2,"syntology":null},{"url":"/paper/resources-for-turkish-dependency-parsing","slug":"resources-for-turkish-dependency-parsing","title":"Resources for Turkish Dependency Parsing: Introducing the BOUN Treebank and the BoAT Annotation Tool","date":"2020-02-24","arxiv_id":"2002.10416","repositories_listed":2,"syntology":null},{"url":"/paper/generating-representative-headlines-for-news","slug":"generating-representative-headlines-for-news","title":"Generating Representative Headlines for News Stories","date":"2020-01-26","arxiv_id":"2001.09386","repositories_listed":2,"syntology":null},{"url":"/paper/samsum-corpus-a-human-annotated-dialogue-1","slug":"samsum-corpus-a-human-annotated-dialogue-1","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","date":"2019-11-27","arxiv_id":"1911.12237","repositories_listed":2,"syntology":null},{"url":"/paper/piqa-reasoning-about-physical-commonsense-in","slug":"piqa-reasoning-about-physical-commonsense-in","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","date":"2019-11-26","arxiv_id":"1911.11641","repositories_listed":2,"syntology":null},{"url":"/paper/a-context-sensitive-real-time-spell-checker","slug":"a-context-sensitive-real-time-spell-checker","title":"A context sensitive real-time Spell Checker with language adaptability","date":"2019-10-23","arxiv_id":"1910.11242","repositories_listed":2,"syntology":null},{"url":"/paper/billsum-a-corpus-for-automatic-summarization","slug":"billsum-a-corpus-for-automatic-summarization","title":"BillSum: A Corpus for Automatic Summarization of US Legislation","date":"2019-10-01","arxiv_id":"1910.00523","repositories_listed":2,"syntology":null},{"url":"/paper/addressing-semantic-drift-in-question","slug":"addressing-semantic-drift-in-question","title":"Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering","date":"2019-09-13","arxiv_id":"1909.06356","repositories_listed":2,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":6,"n_honours":2,"n_violates":1,"n_no_contract":8,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/addressing-semantic-drift-in-question#ran","syntology_url":"https://syntology.ai/paper/1909.06356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.06356"}},"official":{"repos":["ZhangShiyue/QGforQA"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/giveme5w1h-a-universal-system-for-extracting","slug":"giveme5w1h-a-universal-system-for-extracting","title":"Giveme5W1H: A Universal System for Extracting Main Events from News Articles","date":"2019-09-06","arxiv_id":"1909.02766","repositories_listed":2,"syntology":null},{"url":"/paper/a-finnish-news-corpus-for-named-entity","slug":"a-finnish-news-corpus-for-named-entity","title":"A Finnish News Corpus for Named Entity Recognition","date":"2019-08-12","arxiv_id":"1908.04212","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-importance-of-news-content","slug":"on-the-importance-of-news-content","title":"On the Importance of News Content Representation in Hybrid Neural Session-based Recommender Systems","date":"2019-07-12","arxiv_id":"1907.07629","repositories_listed":2,"syntology":{"n":26,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":10,"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) · 10 unverified","sample_list":"/paper/on-the-importance-of-news-content#ran","syntology_url":"https://syntology.ai/paper/1907.07629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.07629"}},"official":{"repos":["gabrielspmoreira/chameleon_recsys"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/a-topic-agnostic-approach-for-identifying","slug":"a-topic-agnostic-approach-for-identifying","title":"A Topic-Agnostic Approach for Identifying Fake News Pages","date":"2019-05-02","arxiv_id":"1905.00957","repositories_listed":2,"syntology":null},{"url":"/paper/inferring-which-medical-treatments-work-from","slug":"inferring-which-medical-treatments-work-from","title":"Inferring Which Medical Treatments Work from Reports of Clinical Trials","date":"2019-04-02","arxiv_id":"1904.01606","repositories_listed":2,"syntology":null},{"url":"/paper/discofuse-a-large-scale-dataset-for-discourse","slug":"discofuse-a-large-scale-dataset-for-discourse","title":"DiscoFuse: A Large-Scale Dataset for Discourse-Based Sentence Fusion","date":"2019-02-27","arxiv_id":"1902.10526","repositories_listed":2,"syntology":null},{"url":"/paper/learning-hierarchical-discourse-level","slug":"learning-hierarchical-discourse-level","title":"Learning Hierarchical Discourse-level Structure for Fake News Detection","date":"2019-02-27","arxiv_id":"1903.07389","repositories_listed":2,"syntology":null},{"url":"/paper/detecting-incongruity-between-news-headline","slug":"detecting-incongruity-between-news-headline","title":"Detecting Incongruity Between News Headline and Body Text via a Deep Hierarchical Encoder","date":"2018-11-17","arxiv_id":"1811.07066","repositories_listed":2,"syntology":null},{"url":"/paper/content-selection-in-deep-learning-models-of","slug":"content-selection-in-deep-learning-models-of","title":"Content Selection in Deep Learning Models of Summarization","date":"2018-10-29","arxiv_id":"1810.12343","repositories_listed":2,"syntology":null},{"url":"/paper/overview-of-cail2018-legal-judgment","slug":"overview-of-cail2018-legal-judgment","title":"Overview of CAIL2018: Legal Judgment Prediction Competition","date":"2018-10-13","arxiv_id":"1810.05851","repositories_listed":2,"syntology":null},{"url":"/paper/predicting-factuality-of-reporting-and-bias","slug":"predicting-factuality-of-reporting-and-bias","title":"Predicting Factuality of Reporting and Bias of News Media Sources","date":"2018-10-02","arxiv_id":"1810.01765","repositories_listed":2,"syntology":null},{"url":"/paper/declare-debunking-fake-news-and-false-claims","slug":"declare-debunking-fake-news-and-false-claims","title":"DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning","date":"2018-09-17","arxiv_id":"1809.06416","repositories_listed":2,"syntology":null},{"url":"/paper/multilingual-clustering-of-streaming-news","slug":"multilingual-clustering-of-streaming-news","title":"Multilingual Clustering of Streaming News","date":"2018-09-03","arxiv_id":"1809.00540","repositories_listed":2,"syntology":null},{"url":"/paper/disentangling-multiple-conditional-inputs-in","slug":"disentangling-multiple-conditional-inputs-in","title":"Disentangling Multiple Conditional Inputs in GANs","date":"2018-06-20","arxiv_id":"1806.07819","repositories_listed":2,"syntology":null},{"url":"/paper/jack-the-reader-a-machine-reading-framework","slug":"jack-the-reader-a-machine-reading-framework","title":"Jack the Reader - A Machine Reading Framework","date":"2018-06-20","arxiv_id":"1806.08727","repositories_listed":2,"syntology":null},{"url":"/paper/a-corpus-with-multi-level-annotations-of","slug":"a-corpus-with-multi-level-annotations-of","title":"A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature","date":"2018-06-11","arxiv_id":"1806.04185","repositories_listed":2,"syntology":null},{"url":"/paper/fake-news-detection-with-deep-diffusive","slug":"fake-news-detection-with-deep-diffusive","title":"FAKEDETECTOR: Effective Fake News Detection with Deep Diffusive Neural Network","date":"2018-05-22","arxiv_id":"1805.08751","repositories_listed":2,"syntology":null},{"url":"/paper/tap-dlnd-10-a-corpus-for-document-level","slug":"tap-dlnd-10-a-corpus-for-document-level","title":"TAP-DLND 1.0 : A Corpus for Document Level Novelty Detection","date":"2018-02-20","arxiv_id":"1802.06950","repositories_listed":2,"syntology":null},{"url":"/paper/a-discourse-level-named-entity-recognition","slug":"a-discourse-level-named-entity-recognition","title":"A Discourse-Level Named Entity Recognition and Relation Extraction Dataset for Chinese Literature Text","date":"2017-11-19","arxiv_id":"1711.07010","repositories_listed":2,"syntology":null},{"url":"/paper/the-dirha-english-corpus-and-related-tasks","slug":"the-dirha-english-corpus-and-related-tasks","title":"The DIRHA-English corpus and related tasks for distant-speech recognition in domestic environments","date":"2017-10-06","arxiv_id":"1710.02560","repositories_listed":2,"syntology":null},{"url":"/paper/the-conditional-analogy-gan-swapping-fashion","slug":"the-conditional-analogy-gan-swapping-fashion","title":"The Conditional Analogy GAN: Swapping Fashion Articles on People Images","date":"2017-09-14","arxiv_id":"1709.04695","repositories_listed":2,"syntology":null},{"url":"/paper/extractive-summarization-using-deep-learning","slug":"extractive-summarization-using-deep-learning","title":"Extractive Summarization using Deep Learning","date":"2017-08-15","arxiv_id":"1708.04439","repositories_listed":2,"syntology":null},{"url":"/paper/neural-extractive-summarization-with-side","slug":"neural-extractive-summarization-with-side","title":"Neural Extractive Summarization with Side Information","date":"2017-04-14","arxiv_id":"1704.04530","repositories_listed":2,"syntology":null},{"url":"/paper/this-just-in-fake-news-packs-a-lot-in-title","slug":"this-just-in-fake-news-packs-a-lot-in-title","title":"This Just In: Fake News Packs a Lot in Title, Uses Simpler, Repetitive Content in Text Body, More Similar to Satire than Real News","date":"2017-03-28","arxiv_id":"1703.09398","repositories_listed":2,"syntology":null},{"url":"/paper/csi-a-hybrid-deep-model-for-fake-news","slug":"csi-a-hybrid-deep-model-for-fake-news","title":"CSI: A Hybrid Deep Model for Fake News Detection","date":"2017-03-20","arxiv_id":"1703.06959","repositories_listed":2,"syntology":null},{"url":"/paper/we-used-neural-networks-to-detect-clickbaits","slug":"we-used-neural-networks-to-detect-clickbaits","title":"We used Neural Networks to Detect Clickbaits: You won't believe what happened Next!","date":"2016-12-05","arxiv_id":"1612.01340","repositories_listed":2,"syntology":null},{"url":"/paper/newsqa-a-machine-comprehension-dataset","slug":"newsqa-a-machine-comprehension-dataset","title":"NewsQA: A Machine Comprehension Dataset","date":"2016-11-29","arxiv_id":"1611.09830","repositories_listed":2,"syntology":null},{"url":"/paper/sentence-ordering-and-coherence-modeling","slug":"sentence-ordering-and-coherence-modeling","title":"Sentence Ordering and Coherence Modeling using Recurrent Neural Networks","date":"2016-11-08","arxiv_id":"1611.02654","repositories_listed":2,"syntology":null},{"url":"/paper/wikireading-a-novel-large-scale-language","slug":"wikireading-a-novel-large-scale-language","title":"WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia","date":"2016-08-11","arxiv_id":"1608.03542","repositories_listed":2,"syntology":null},{"url":"/paper/stock-trend-prediction-using-news-sentiment","slug":"stock-trend-prediction-using-news-sentiment","title":"Stock trend prediction using news sentiment analysis","date":"2016-07-07","arxiv_id":"1607.01958","repositories_listed":2,"syntology":null},{"url":"/paper/science-concierge-a-fast-content-based","slug":"science-concierge-a-fast-content-based","title":"Science Concierge: A fast content-based recommendation system for scientific publications","date":"2016-04-04","arxiv_id":"1604.01070","repositories_listed":2,"syntology":null},{"url":"/paper/towards-better-understanding-of-artifacts-in","slug":"towards-better-understanding-of-artifacts-in","title":"Towards Better Understanding of Artifacts in Variant Calling from High-Coverage Samples","date":"2014-04-03","arxiv_id":"1404.0929","repositories_listed":2,"syntology":null},{"url":"/paper/stochastic-variational-inference","slug":"stochastic-variational-inference","title":"Stochastic Variational Inference","date":"2012-06-29","arxiv_id":"1206.7051","repositories_listed":2,"syntology":null},{"url":"/paper/ai-wizards-at-checkthat-2025-enhancing","slug":"ai-wizards-at-checkthat-2025-enhancing","title":"AI Wizards at CheckThat! 2025: Enhancing Transformer-Based Embeddings with Sentiment for Subjectivity Detection in News Articles","date":"2025-07-15","arxiv_id":"2507.11764","repositories_listed":1,"syntology":null},{"url":"/paper/remember-past-anticipate-future-learning","slug":"remember-past-anticipate-future-learning","title":"Remember Past, Anticipate Future: Learning Continual Multimodal Misinformation Detectors","date":"2025-07-08","arxiv_id":"2507.05939","repositories_listed":1,"syntology":null},{"url":"/paper/narrative-shift-detection-a-hybrid-approach","slug":"narrative-shift-detection-a-hybrid-approach","title":"Narrative Shift Detection: A Hybrid Approach of Dynamic Topic Models and Large Language Models","date":"2025-06-25","arxiv_id":"2506.20269","repositories_listed":1,"syntology":null},{"url":"/paper/characterizing-linguistic-shifts-in-croatian","slug":"characterizing-linguistic-shifts-in-croatian","title":"Characterizing Linguistic Shifts in Croatian News via Diachronic Word Embeddings","date":"2025-06-16","arxiv_id":"2506.13569","repositories_listed":1,"syntology":null},{"url":"/paper/how-grounded-is-wikipedia-a-study-on","slug":"how-grounded-is-wikipedia-a-study-on","title":"How Grounded is Wikipedia? A Study on Structured Evidential Support","date":"2025-06-14","arxiv_id":"2506.12637","repositories_listed":1,"syntology":null},{"url":"/paper/intent-factored-generation-unleashing-the","slug":"intent-factored-generation-unleashing-the","title":"Intent Factored Generation: Unleashing the Diversity in Your Language Model","date":"2025-06-11","arxiv_id":"2506.09659","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/intent-factored-generation-unleashing-the#ran","syntology_url":"https://syntology.ai/paper/2506.09659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09659"}},"official":{"repos":["flairox/ifg"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-mismatched-benchmark-for-scientific-natural","slug":"a-mismatched-benchmark-for-scientific-natural","title":"A MISMATCHED Benchmark for Scientific Natural Language Inference","date":"2025-06-05","arxiv_id":"2506.04603","repositories_listed":1,"syntology":null},{"url":"/paper/towards-network-data-analytics-in-5g-systems","slug":"towards-network-data-analytics-in-5g-systems","title":"Towards Network Data Analytics in 5G Systems and Beyond","date":"2025-06-05","arxiv_id":"2506.04860","repositories_listed":1,"syntology":null},{"url":"/paper/matter-of-fact-a-benchmark-for-verifying-the","slug":"matter-of-fact-a-benchmark-for-verifying-the","title":"Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Science","date":"2025-06-04","arxiv_id":"2506.04410","repositories_listed":1,"syntology":null},{"url":"/paper/prism-a-framework-for-producing-interpretable","slug":"prism-a-framework-for-producing-interpretable","title":"PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder","date":"2025-05-30","arxiv_id":"2505.24646","repositories_listed":1,"syntology":null},{"url":"/paper/can-large-language-models-match-the","slug":"can-large-language-models-match-the","title":"Can Large Language Models Match the Conclusions of Systematic Reviews?","date":"2025-05-28","arxiv_id":"2505.22787","repositories_listed":1,"syntology":null},{"url":"/paper/gatenlp-at-semeval-2025-task-10-hierarchical","slug":"gatenlp-at-semeval-2025-task-10-hierarchical","title":"GateNLP at SemEval-2025 Task 10: Hierarchical Three-Step Prompting for Multilingual Narrative Classification","date":"2025-05-28","arxiv_id":"2505.22867","repositories_listed":1,"syntology":null},{"url":"/paper/response-to-comment-on-mutualism-weaken-the","slug":"response-to-comment-on-mutualism-weaken-the","title":"Response to comment on Mutualism weaken the latitudinal diversity gradient among oceanic islands","date":"2025-05-27","arxiv_id":"2505.21006","repositories_listed":1,"syntology":null},{"url":"/paper/mole-metadata-extraction-and-validation-in","slug":"mole-metadata-extraction-and-validation-in","title":"MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs","date":"2025-05-26","arxiv_id":"2505.19800","repositories_listed":1,"syntology":null},{"url":"/paper/delving-into-multilingual-ethical-bias-the","slug":"delving-into-multilingual-ethical-bias-the","title":"Delving into Multilingual Ethical Bias: The MSQAD with Statistical Hypothesis Tests for Large Language Models","date":"2025-05-25","arxiv_id":"2505.19121","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-keyphrase-extraction-from-academic-1","slug":"enhancing-keyphrase-extraction-from-academic-1","title":"Enhancing Keyphrase Extraction from Academic Articles Using Section Structure Information","date":"2025-05-20","arxiv_id":"2505.14149","repositories_listed":1,"syntology":null},{"url":"/paper/panorama-a-synthetic-pii-laced-dataset-for","slug":"panorama-a-synthetic-pii-laced-dataset-for","title":"PANORAMA: A synthetic PII-laced dataset for studying sensitive data memorization in LLMs","date":"2025-05-18","arxiv_id":"2505.12238","repositories_listed":1,"syntology":null},{"url":"/paper/cxmarena-unified-dataset-to-benchmark","slug":"cxmarena-unified-dataset-to-benchmark","title":"CXMArena: Unified Dataset to benchmark performance in realistic CXM Scenarios","date":"2025-05-14","arxiv_id":"2505.09436","repositories_listed":1,"syntology":null},{"url":"/paper/neoqa-evidence-based-question-answering-with","slug":"neoqa-evidence-based-question-answering-with","title":"NeoQA: Evidence-based Question Answering with Generated News Events","date":"2025-05-09","arxiv_id":"2505.05949","repositories_listed":1,"syntology":null},{"url":"/paper/towards-artificial-intelligence-research","slug":"towards-artificial-intelligence-research","title":"Towards Artificial Intelligence Research Assistant for Expert-Involved Learning","date":"2025-05-03","arxiv_id":"2505.04638","repositories_listed":1,"syntology":null},{"url":"/paper/20min-xd-a-comparable-corpus-of-swiss-news","slug":"20min-xd-a-comparable-corpus-of-swiss-news","title":"20min-XD: A Comparable Corpus of Swiss News Articles","date":"2025-04-30","arxiv_id":"2504.21677","repositories_listed":1,"syntology":null},{"url":"/paper/robust-misinformation-detection-by-visiting","slug":"robust-misinformation-detection-by-visiting","title":"Robust Misinformation Detection by Visiting Potential Commonsense Conflict","date":"2025-04-30","arxiv_id":"2504.21604","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/robust-misinformation-detection-by-visiting#ran","syntology_url":"https://syntology.ai/paper/2504.21604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21604"}},"official":{"repos":["wangbing1416/md-pcc"],"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/an-empirical-study-on-prompt-compression-for","slug":"an-empirical-study-on-prompt-compression-for","title":"An Empirical Study on Prompt Compression for Large Language Models","date":"2025-04-24","arxiv_id":"2505.00019","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":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) · 0 unverified","sample_list":"/paper/an-empirical-study-on-prompt-compression-for#ran","syntology_url":"https://syntology.ai/paper/2505.00019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.00019"}},"official":{"repos":["3DAgentWorld/Toolkit-for-Prompt-Compression"],"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/a-python-tool-for-reconstructing-full-news","slug":"a-python-tool-for-reconstructing-full-news","title":"A Python Tool for Reconstructing Full News Text from GDELT","date":"2025-04-22","arxiv_id":"2504.16063","repositories_listed":1,"syntology":null},{"url":"/paper/controlled-territory-and-conflict-tracking","slug":"controlled-territory-and-conflict-tracking","title":"Controlled Territory and Conflict Tracking (CONTACT): (Geo-)Mapping Occupied Territory from Open Source Intelligence","date":"2025-04-18","arxiv_id":"2504.13730","repositories_listed":1,"syntology":null},{"url":"/paper/stamp-your-content-proving-dataset-membership","slug":"stamp-your-content-proving-dataset-membership","title":"STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings","date":"2025-04-18","arxiv_id":"2504.13416","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/stamp-your-content-proving-dataset-membership#ran","syntology_url":"https://syntology.ai/paper/2504.13416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13416"}},"official":{"repos":["codeboy5/stamp"],"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/tongui-building-generalized-gui-agents-by","slug":"tongui-building-generalized-gui-agents-by","title":"TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials","date":"2025-04-17","arxiv_id":"2504.12679","repositories_listed":1,"syntology":null},{"url":"/paper/characterizing-knowledge-manipulation-in-a","slug":"characterizing-knowledge-manipulation-in-a","title":"Characterizing Knowledge Manipulation in a Russian Wikipedia Fork","date":"2025-04-14","arxiv_id":"2504.10663","repositories_listed":1,"syntology":null},{"url":"/paper/biocheminsight-an-open-source-toolkit-for","slug":"biocheminsight-an-open-source-toolkit-for","title":"BioChemInsight: An Open-Source Toolkit for Automated Identification and Recognition of Optical Chemical Structures and Activity Data in Scientific Publications","date":"2025-04-12","arxiv_id":"2504.10525","repositories_listed":1,"syntology":null},{"url":"/paper/ai-slop-to-ai-polish-aligning-language-models","slug":"ai-slop-to-ai-polish-aligning-language-models","title":"AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation","date":"2025-04-10","arxiv_id":"2504.07532","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ai-slop-to-ai-polish-aligning-language-models#ran","syntology_url":"https://syntology.ai/paper/2504.07532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07532"}},"official":{"repos":["salesforce/creativity_eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/talking-point-based-ideological-discourse","slug":"talking-point-based-ideological-discourse","title":"Talking Point based Ideological Discourse Analysis in News Events","date":"2025-04-10","arxiv_id":"2504.07400","repositories_listed":1,"syntology":null},{"url":"/paper/llm-times-mapreduce-v2-entropy-driven","slug":"llm-times-mapreduce-v2-entropy-driven","title":"LLM$\\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources","date":"2025-04-08","arxiv_id":"2504.05732","repositories_listed":1,"syntology":null},{"url":"/paper/arxivbench-can-llms-assist-researchers-in","slug":"arxivbench-can-llms-assist-researchers-in","title":"ArxivBench: Can LLMs Assist Researchers in Conducting Research?","date":"2025-04-06","arxiv_id":"2504.10496","repositories_listed":1,"syntology":null},{"url":"/paper/is-less-really-more-fake-news-detection-with","slug":"is-less-really-more-fake-news-detection-with","title":"Is Less Really More? Fake News Detection with Limited Information","date":"2025-04-02","arxiv_id":"2504.01922","repositories_listed":1,"syntology":null},{"url":"/paper/prophet-an-inferable-future-forecasting","slug":"prophet-an-inferable-future-forecasting","title":"PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation","date":"2025-04-02","arxiv_id":"2504.01509","repositories_listed":1,"syntology":null},{"url":"/paper/wikivideo-article-generation-from-multiple","slug":"wikivideo-article-generation-from-multiple","title":"WikiVideo: Article Generation from Multiple Videos","date":"2025-04-01","arxiv_id":"2504.00939","repositories_listed":1,"syntology":null},{"url":"/paper/citegeist-automated-generation-of-related","slug":"citegeist-automated-generation-of-related","title":"Citegeist: Automated Generation of Related Work Analysis on the arXiv Corpus","date":"2025-03-29","arxiv_id":"2503.23229","repositories_listed":1,"syntology":null},{"url":"/paper/meditools-medical-education-powered-by-llms","slug":"meditools-medical-education-powered-by-llms","title":"MediTools -- Medical Education Powered by LLMs","date":"2025-03-28","arxiv_id":"2503.22769","repositories_listed":1,"syntology":null},{"url":"/paper/wikiautogen-towards-multi-modal-wikipedia","slug":"wikiautogen-towards-multi-modal-wikipedia","title":"WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation","date":"2025-03-24","arxiv_id":"2503.19065","repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-survey-on-cross-domain","slug":"a-comprehensive-survey-on-cross-domain","title":"A Comprehensive Survey on Cross-Domain Recommendation: Taxonomy, Progress, and Prospects","date":"2025-03-18","arxiv_id":"2503.14110","repositories_listed":1,"syntology":null},{"url":"/paper/microvqa-a-multimodal-reasoning-benchmark-for","slug":"microvqa-a-multimodal-reasoning-benchmark-for","title":"MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research","date":"2025-03-17","arxiv_id":"2503.13399","repositories_listed":1,"syntology":null},{"url":"/paper/who-wrote-this-identifying-machine-vs-human","slug":"who-wrote-this-identifying-machine-vs-human","title":"Who Wrote This? Identifying Machine vs Human-Generated Text in Hausa","date":"2025-03-17","arxiv_id":"2503.13101","repositories_listed":1,"syntology":null},{"url":"/paper/roamify-designing-and-evaluating-an-llm-based","slug":"roamify-designing-and-evaluating-an-llm-based","title":"Roamify: Designing and Evaluating an LLM Based Google Chrome Extension for Personalised Itinerary Planning","date":"2025-03-10","arxiv_id":"2504.10489","repositories_listed":1,"syntology":null},{"url":"/paper/limtopic-llm-based-topic-modeling-and-text","slug":"limtopic-llm-based-topic-modeling-and-text","title":"LimTopic: LLM-based Topic Modeling and Text Summarization for Analyzing Scientific Articles limitations","date":"2025-03-08","arxiv_id":"2503.10658","repositories_listed":1,"syntology":null},{"url":"/paper/quantifying-the-relevance-of-youth-research","slug":"quantifying-the-relevance-of-youth-research","title":"Quantifying the Relevance of Youth Research Cited in the US Policy Documents","date":"2025-03-06","arxiv_id":"2503.04977","repositories_listed":1,"syntology":null},{"url":"/paper/surveyforge-on-the-outline-heuristics-memory","slug":"surveyforge-on-the-outline-heuristics-memory","title":"SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing","date":"2025-03-06","arxiv_id":"2503.04629","repositories_listed":1,"syntology":null},{"url":"/paper/wikipedia-in-the-era-of-llms-evolution-and","slug":"wikipedia-in-the-era-of-llms-evolution-and","title":"Wikipedia in the Era of LLMs: Evolution and Risks","date":"2025-03-04","arxiv_id":"2503.02879","repositories_listed":1,"syntology":null}],"record_sha256":"7ae3c5a0b228cdbed24a9c7f9c24949a2bb188df7e1be577960a34c1f9e008c0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}