{"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/binary-text-classification","name":"Binary text classification","slug":"binary-text-classification","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":20,"papers_with_code":12,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":10,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/binary-text-classification-on-ghostbuster-all","slug":"binary-text-classification-on-ghostbuster-all","dataset":"Ghostbuster (All Domains)","dataset_url":"/dataset/ghostbuster","rows_in_archive":2,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-mage-arbitrary","slug":"binary-text-classification-on-mage-arbitrary","dataset":"MAGE (Arbitrary-domains & Arbitrary-models)","dataset_url":"/dataset/mage","rows_in_archive":2,"metrics":["Average Recall"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-mixset-binary","slug":"binary-text-classification-on-mixset-binary","dataset":"MixSet (Binary)","dataset_url":"/dataset/mixset","rows_in_archive":2,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-turingbench","slug":"binary-text-classification-on-turingbench","dataset":"TURINGBENCH (Turing Test, GPT-3)","dataset_url":"/dataset/turingbench","rows_in_archive":2,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-turingbench-1","slug":"binary-text-classification-on-turingbench-1","dataset":"TURINGBENCH (Turing Test, FAIR_wmt20)","dataset_url":"/dataset/turingbench","rows_in_archive":2,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-tweepfake","slug":"binary-text-classification-on-tweepfake","dataset":"TweepFake","dataset_url":"/dataset/tweepfake","rows_in_archive":2,"metrics":["F1 score","Accuracy (%)"],"first_row_in_archive_order":{"model":"GigaCheck (Mistral-7B)","paper_title":"GigaCheck: Detecting LLM-generated Content","paper_url":"/paper/gigacheck-detecting-llm-generated-content","paper_date":"2024-10-31","arxiv_id":"2410.23728","code_links":[],"syntology":null}},{"leaderboard":"/sota/binary-text-classification-on-echr-non","slug":"binary-text-classification-on-echr-non","dataset":"ECHR Non-Anonymized","dataset_url":"/dataset/echr","rows_in_archive":1,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"HIER-BERT","paper_title":"Neural Legal Judgment Prediction in English","paper_url":"/paper/neural-legal-judgment-prediction-in-english","paper_date":"2019-06-05","arxiv_id":"1906.02059","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/echr","name":"ECHR","full_name":"","num_papers_in_archive":47},{"url":"/dataset/turingbench","name":"TURINGBENCH","full_name":"","num_papers_in_archive":18},{"url":"/dataset/tweepfake","name":"TweepFake","full_name":"","num_papers_in_archive":16},{"url":"/dataset/ghostbuster","name":"Ghostbuster","full_name":"","num_papers_in_archive":13},{"url":"/dataset/outfox","name":"OUTFOX","full_name":"","num_papers_in_archive":13},{"url":"/dataset/mage","name":"MAGE","full_name":"","num_papers_in_archive":11},{"url":"/dataset/mixset","name":"MixSet","full_name":"Mixcase Dataset","num_papers_in_archive":4},{"url":"/dataset/daccord","name":"DACCORD","full_name":"","num_papers_in_archive":2},{"url":"/dataset/bfrd","name":"BFRD","full_name":"Bengali Fake Review Dataset","num_papers_in_archive":1},{"url":"/dataset/this-is-not-a-dataset","name":"This is not a Dataset","full_name":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","num_papers_in_archive":1}],"subtasks":[{"url":"/task/detection-of-potentially-void-clauses","name":"Detection of potentially void clauses"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":20,"of":20,"of_with_code":12,"tagged_in_all":20,"counts":{"archive_papers_tagged":20,"with_a_code_link":12,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":20,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/turingbench-a-benchmark-environment-for","slug":"turingbench-a-benchmark-environment-for","title":"TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation","date":"2021-09-27","arxiv_id":"2109.13296","repositories_listed":3,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/turingbench-a-benchmark-environment-for#ran","syntology_url":"https://syntology.ai/paper/2109.13296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.13296"}},"official":null}},{"url":"/paper/llm-as-a-coauthor-the-challenges-of-detecting","slug":"llm-as-a-coauthor-the-challenges-of-detecting","title":"LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected?","date":"2024-01-11","arxiv_id":"2401.05952","repositories_listed":2,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":16,"phrase":"8 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; 5 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/llm-as-a-coauthor-the-challenges-of-detecting#ran","syntology_url":"https://syntology.ai/paper/2401.05952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05952"}},"official":{"repos":["dongping-chen/mixset"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/daccord-un-jeu-de-donnees-pour-la-detection","slug":"daccord-un-jeu-de-donnees-pour-la-detection","title":"DACCORD : un jeu de données pour la Détection Automatique d'énonCés COntRaDictoires en français","date":"2023-06-08","arxiv_id":null,"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/deepfake-text-detection-in-the-wild","slug":"deepfake-text-detection-in-the-wild","title":"MAGE: Machine-generated Text Detection in the Wild","date":"2023-05-22","arxiv_id":"2305.13242","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deepfake-text-detection-in-the-wild#ran","syntology_url":"https://syntology.ai/paper/2305.13242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13242"}},"official":{"repos":["yafuly/deepfaketextdetect","yafuly/mage"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-representations-for-soft-skill","slug":"learning-representations-for-soft-skill","title":"Learning Representations for Soft Skill Matching","date":"2018-07-20","arxiv_id":"1807.07741","repositories_listed":2,"syntology":null},{"url":"/paper/expectation-backpropagation-parameter-free","slug":"expectation-backpropagation-parameter-free","title":"Expectation Backpropagation: Parameter-Free Training of Multilayer Neural Networks with Continuous or Discrete Weights","date":"2014-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/hoaxpedia-a-unified-wikipedia-hoax-articles","slug":"hoaxpedia-a-unified-wikipedia-hoax-articles","title":"Hoaxpedia: A Unified Wikipedia Hoax Articles Dataset","date":"2024-05-03","arxiv_id":"2405.02175","repositories_listed":1,"syntology":null},{"url":"/paper/identification-of-the-relevance-of-comments","slug":"identification-of-the-relevance-of-comments","title":"Identification of the Relevance of Comments in Codes Using Bag of Words and Transformer Based Models","date":"2023-08-11","arxiv_id":"2308.06144","repositories_listed":1,"syntology":null},{"url":"/paper/active-learning-for-bert-an-empirical-study","slug":"active-learning-for-bert-an-empirical-study","title":"Active Learning for BERT: An Empirical Study","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tweepfake-about-detecting-deepfake-tweets","slug":"tweepfake-about-detecting-deepfake-tweets","title":"TweepFake: about Detecting Deepfake Tweets","date":"2020-07-31","arxiv_id":"2008.00036","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-shallow-and-deep-learning","slug":"evaluating-shallow-and-deep-learning","title":"Evaluating shallow and deep learning strategies for the 2018 n2c2 shared task on clinical text classification","date":"2019-09-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"reliable-decision-support-with-llms-a","title":"Reliable Decision Support with LLMs: A Framework for Evaluating Consistency in Binary Text Classification Applications","date":"2025-05-20","arxiv_id":"2505.14918","repositories_listed":0,"syntology":null},{"url":"/paper/gigacheck-detecting-llm-generated-content","slug":"gigacheck-detecting-llm-generated-content","title":"GigaCheck: Detecting LLM-generated Content","date":"2024-10-31","arxiv_id":"2410.23728","repositories_listed":0,"syntology":null},{"url":null,"slug":"calibrated-large-language-models-for-binary","title":"Calibrated Large Language Models for Binary Question Answering","date":"2024-07-01","arxiv_id":"2407.01122","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-the-generalizability-of-deep","title":"Analyzing the Generalizability of Deep Contextualized Language Representations For Text Classification","date":"2023-03-22","arxiv_id":"2303.12936","repositories_listed":0,"syntology":null},{"url":null,"slug":"argumentative-explanations-for-pattern-based","title":"Argumentative Explanations for Pattern-Based Text Classifiers","date":"2022-05-22","arxiv_id":"2205.10932","repositories_listed":0,"syntology":null},{"url":null,"slug":"cia-nitt-at-wnut-2020-task-2-classification","title":"CIA_NITT at WNUT-2020 Task 2: Classification of COVID-19 Tweets Using Pre-trained Language Models","date":"2020-09-12","arxiv_id":"2009.05782","repositories_listed":0,"syntology":null},{"url":"/paper/neural-legal-judgment-prediction-in-english","slug":"neural-legal-judgment-prediction-in-english","title":"Neural Legal Judgment Prediction in English","date":"2019-06-05","arxiv_id":"1906.02059","repositories_listed":0,"syntology":null},{"url":null,"slug":"deception-detection-for-the-russian-language","title":"Deception Detection for the Russian Language: Lexical and Syntactic Parameters","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":3,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/task/binary-text-classification/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/binary-text-classification/papers/ran/1","json":"/task/binary-text-classification/papers/ran/1.json","rows":3}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"207a75ccbcc1c9e0949e757db30a3b7b7fbbca92783d8e69a7d383bd8b5f4ef9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}