{"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":"/dataset/indicglue","name":"IndicGLUE","full_name":"Indic General Language Understanding Evaluation Benchmark","description_markdown":"We now introduce IndicGLUE, the Indic General\r\nLanguage Understanding Evaluation Benchmark,\r\nwhich is a collection of various NLP tasks as de-\r\nscribed below. The goal is to provide an evaluation\r\nbenchmark for natural language understanding ca-\r\npabilities of NLP models on diverse tasks and mul-\r\ntiple Indian languages.","description_withheld":null,"homepage":"https://indicnlp.ai4bharat.org/indic-glue/","introduced_date":"2020-11-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/indicnlpsuite-monolingual-corpora-evaluation","title":"IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages","first_author":"Divyanshu Kakwani","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Sentiment Analysis","url":"/task/sentiment-analysis","datasets_with_task":"/datasets/task/sentiment-analysis"},{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Multiple Choice Question Answering (MCQA)","url":"/task/multiple-choice-qa","datasets_with_task":"/datasets/task/multiple-choice-qa"},{"name":"News Classification","url":"/task/news-classification","datasets_with_task":"/datasets/task/news-classification"}],"languages":[{"name":"Bengali","url":"/datasets/language/bengali"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Marathi","url":"/datasets/language/marathi"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Telugu","url":"/datasets/language/telugu"},{"name":"Assamese","url":"/datasets/language/assamese"},{"name":"Gujarati","url":"/datasets/language/gujarati"},{"name":"Kannada","url":"/datasets/language/kannada"},{"name":"Malayalam","url":"/datasets/language/malayalam"},{"name":"Oriya (macrolanguage)","url":"/datasets/language/oriya-macrolanguage"},{"name":"Punjabi","url":"/datasets/language/punjabi"}],"variants":["IITP Product Reviews Sentiment","IITP Movie Reviews Sentiment","IndicGLUE WSTP Pa","IndicGLUE"],"data_loaders":[],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sentiment-analysis-on-iitp-product-reviews","task":"Sentiment Analysis","dataset_variant":"IITP Product Reviews Sentiment","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CalBERT","paper":"/paper/calbert-code-mixed-adaptive-language-1","metrics":{"Accuracy":"79.4"},"code_links":[{"title":"aditeyabaral/calbert","url":"https://github.com/aditeyabaral/calbert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-qa-on-indicglue-wstp-pa","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"IndicGLUE WSTP Pa","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"xlmindic-base-uniscript","paper":"/paper/does-transliteration-help-multilingual","metrics":{"Accuracy":"77.55"},"code_links":[{"title":"ibraheem-moosa/xlm-indic","url":"https://github.com/ibraheem-moosa/xlm-indic"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/sentiment-analysis-on-iitp-movie-reviews","task":"Sentiment Analysis","dataset_variant":"IITP Movie Reviews Sentiment","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"xlmindic-base-uniscript","paper":"/paper/does-transliteration-help-multilingual","metrics":{"Accuracy":"66.34"},"code_links":[{"title":"ibraheem-moosa/xlm-indic","url":"https://github.com/ibraheem-moosa/xlm-indic"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-indicglue","task":"Text Generation","dataset_variant":"IndicGLUE","rows":0,"metrics":["Average Accuracy"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":3,"of":3,"counts":{"papers_with_a_benchmark_row":3,"with_a_code_link":3,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/calbert-code-mixed-adaptive-language-1","slug":"calbert-code-mixed-adaptive-language-1","title":"CalBERT - Code-mixed Adaptive Language representations using BERT","date":"2022-04-14","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/does-transliteration-help-multilingual","slug":"does-transliteration-help-multilingual","title":"Does Transliteration Help Multilingual Language Modeling?","date":"2022-01-29","arxiv_id":"2201.12501","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ibraheem-moosa/xlm-indic"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/does-transliteration-help-multilingual#ran","syntology_url":"https://syntology.ai/paper/2201.12501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12501"}}}},{"paper":"/paper/indicnlpsuite-monolingual-corpora-evaluation","slug":"indicnlpsuite-monolingual-corpora-evaluation","title":"IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages","date":"2020-11-08","arxiv_id":null,"rows_on_this_dataset":3,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/calbert-code-mixed-adaptive-language-1","slug":"calbert-code-mixed-adaptive-language-1","title":"CalBERT - Code-mixed Adaptive Language representations using BERT","date":"2022-04-14","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/does-transliteration-help-multilingual","slug":"does-transliteration-help-multilingual","title":"Does Transliteration Help Multilingual Language Modeling?","date":"2022-01-29","arxiv_id":"2201.12501","rows_on_this_dataset":6,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ibraheem-moosa/xlm-indic"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/does-transliteration-help-multilingual#ran","syntology_url":"https://syntology.ai/paper/2201.12501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12501"}}}},{"paper":"/paper/indicnlpsuite-monolingual-corpora-evaluation","slug":"indicnlpsuite-monolingual-corpora-evaluation","title":"IndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages","date":"2020-11-08","arxiv_id":null,"rows_on_this_dataset":3,"code_links":1,"syntology":null}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/indicglue/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/indicglue/papers/ran/1","json":"/dataset/indicglue/papers/ran/1.json","rows":1}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"9f128c792dc2f6887e83249772bf271a2611246090f982f55621274914e01343","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}