{"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/wikiqa","name":"WikiQA","full_name":"Wikipedia open-domain Question Answering","description_markdown":"The **WikiQA** corpus is a publicly available set of question and sentence pairs, collected and annotated for research on open-domain question answering. In order to reflect the true information need of general users, Bing query logs were used as the question source. Each question is linked to a Wikipedia page that potentially has the answer. Because the summary section of a Wikipedia page provides the basic and usually most important information about the topic, sentences in this section were used as the candidate answers. The corpus includes 3,047 questions and 29,258 sentences, where 1,473 sentences were labeled as answer sentences to their corresponding questions.\r\n\r\nSource: [http://aka.ms/WikiQA](http://aka.ms/WikiQA)\r\nImage Source: [Yang et al](https://www.aclweb.org/anthology/D15-1237)","description_withheld":null,"homepage":"http://aka.ms/WikiQA","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/wikiqa-a-challenge-dataset-for-open-domain","title":"WikiQA: A Challenge Dataset for Open-Domain Question Answering","first_author":"Yi Yang","url":null},"license":{"name":"Custom","url":"https://www.microsoft.com/en-us/download/details.aspx?id=52419"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Answer Selection","url":"/task/answer-selection","datasets_with_task":"/datasets/task/answer-selection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WikiQA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/microsoft/wiki_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wiki_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#wikiqa","frameworks":["pytorch"]}],"num_papers_in_archive":196,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-wikiqa","task":"Question Answering","dataset_variant":"WikiQA","rows":25,"metrics":["MAP","MRR"],"first_row_in_archive_order":{"model":"TANDA-DeBERTa-V3-Large + ALL","paper":"/paper/structural-self-supervised-objectives-for","metrics":{"MAP":"0.927","MRR":"0.939"},"code_links":[{"title":"lucadiliello/transformers-framework","url":"https://github.com/lucadiliello/transformers-framework"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/answer-selection-on-wikiqa-1","task":"Answer Selection","dataset_variant":"WikiQA","rows":1,"metrics":["MAP "],"first_row_in_archive_order":{"model":"RLAS-BIABC","paper":"/paper/rlas-biabc-a-reinforcement-learning-based","metrics":{"MAP ":"0.888"},"code_links":[]},"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":19,"of":19,"counts":{"papers_with_a_benchmark_row":19,"with_a_code_link":13,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":19,"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 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/structural-self-supervised-objectives-for","slug":"structural-self-supervised-objectives-for","title":"Structural Self-Supervised Objectives for Transformers","date":"2023-09-15","arxiv_id":"2309.08272","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rlas-biabc-a-reinforcement-learning-based","slug":"rlas-biabc-a-reinforcement-learning-based","title":"RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm","date":"2023-01-07","arxiv_id":"2301.02807","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/pre-training-transformer-models-with-sentence","slug":"pre-training-transformer-models-with-sentence","title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","date":"2022-05-20","arxiv_id":"2205.10455","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/paragraph-based-transformer-pre-training-for","slug":"paragraph-based-transformer-pre-training-for","title":"Paragraph-based Transformer Pre-training for Multi-Sentence Inference","date":"2022-05-02","arxiv_id":"2205.01228","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tanda-transfer-and-adapt-pre-trained","slug":"tanda-transfer-and-adapt-pre-trained","title":"TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection","date":"2019-11-11","arxiv_id":"1911.04118","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/simple-and-effective-text-matching-with-1","slug":"simple-and-effective-text-matching-with-1","title":"Simple and Effective Text Matching with Richer Alignment Features","date":"2019-08-01","arxiv_id":"1908.00300","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["hitvoice/RE2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simple-and-effective-text-matching-with-1#ran","syntology_url":"https://syntology.ai/paper/1908.00300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.00300"}}}},{"paper":"/paper/a-compare-aggregate-model-with-latent","slug":"a-compare-aggregate-model-with-latent","title":"A Compare-Aggregate Model with Latent Clustering for Answer Selection","date":"2019-05-30","arxiv_id":"1905.12897","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/noise-contrastive-estimation-and-negative","slug":"noise-contrastive-estimation-and-negative","title":"Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency","date":"2018-09-06","arxiv_id":"1809.01812","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/baseline-needs-more-love-on-simple-word","slug":"baseline-needs-more-love-on-simple-word","title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","date":"2018-05-24","arxiv_id":"1805.09843","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/hyperbolic-representation-learning-for-fast","slug":"hyperbolic-representation-learning-for-fast","title":"Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering","date":"2017-07-25","arxiv_id":"1707.07847","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/neural-semantic-encoders","slug":"neural-semantic-encoders","title":"Neural Semantic Encoders","date":"2016-07-14","arxiv_id":"1607.04315","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/key-value-memory-networks-for-directly","slug":"key-value-memory-networks-for-directly","title":"Key-Value Memory Networks for Directly Reading Documents","date":"2016-06-09","arxiv_id":"1606.03126","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/pairwise-word-interaction-modeling-with-deep","slug":"pairwise-word-interaction-modeling-with-deep","title":"Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement","date":"2016-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sentence-similarity-learning-by-lexical","slug":"sentence-similarity-learning-by-lexical","title":"Sentence Similarity Learning by Lexical Decomposition and Composition","date":"2016-02-23","arxiv_id":"1602.07019","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/attentive-pooling-networks","slug":"attentive-pooling-networks","title":"Attentive Pooling Networks","date":"2016-02-11","arxiv_id":"1602.03609","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/neural-variational-inference-for-text","slug":"neural-variational-inference-for-text","title":"Neural Variational Inference for Text Processing","date":"2015-11-19","arxiv_id":"1511.06038","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/neural-variational-inference-for-text#ran","syntology_url":"https://syntology.ai/paper/1511.06038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06038"}}}},{"paper":"/paper/wikiqa-a-challenge-dataset-for-open-domain","slug":"wikiqa-a-challenge-dataset-for-open-domain","title":"WikiQA: A Challenge Dataset for Open-Domain Question Answering","date":"2015-09-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-learning-for-answer-sentence-selection","slug":"deep-learning-for-answer-sentence-selection","title":"Deep Learning for Answer Sentence Selection","date":"2014-12-04","arxiv_id":"1412.1632","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/distributed-representations-of-sentences-and","slug":"distributed-representations-of-sentences-and","title":"Distributed Representations of Sentences and Documents","date":"2014-05-16","arxiv_id":"1405.4053","rows_on_this_dataset":2,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distributed-representations-of-sentences-and#ran","syntology_url":"https://syntology.ai/paper/1405.4053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1405.4053"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/structural-self-supervised-objectives-for","slug":"structural-self-supervised-objectives-for","title":"Structural Self-Supervised Objectives for Transformers","date":"2023-09-15","arxiv_id":"2309.08272","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rlas-biabc-a-reinforcement-learning-based","slug":"rlas-biabc-a-reinforcement-learning-based","title":"RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm","date":"2023-01-07","arxiv_id":"2301.02807","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/pre-training-transformer-models-with-sentence","slug":"pre-training-transformer-models-with-sentence","title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","date":"2022-05-20","arxiv_id":"2205.10455","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/paragraph-based-transformer-pre-training-for","slug":"paragraph-based-transformer-pre-training-for","title":"Paragraph-based Transformer Pre-training for Multi-Sentence Inference","date":"2022-05-02","arxiv_id":"2205.01228","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tanda-transfer-and-adapt-pre-trained","slug":"tanda-transfer-and-adapt-pre-trained","title":"TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection","date":"2019-11-11","arxiv_id":"1911.04118","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/simple-and-effective-text-matching-with-1","slug":"simple-and-effective-text-matching-with-1","title":"Simple and Effective Text Matching with Richer Alignment Features","date":"2019-08-01","arxiv_id":"1908.00300","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["hitvoice/RE2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simple-and-effective-text-matching-with-1#ran","syntology_url":"https://syntology.ai/paper/1908.00300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.00300"}}}},{"paper":"/paper/a-compare-aggregate-model-with-latent","slug":"a-compare-aggregate-model-with-latent","title":"A Compare-Aggregate Model with Latent Clustering for Answer Selection","date":"2019-05-30","arxiv_id":"1905.12897","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/noise-contrastive-estimation-and-negative","slug":"noise-contrastive-estimation-and-negative","title":"Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency","date":"2018-09-06","arxiv_id":"1809.01812","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/baseline-needs-more-love-on-simple-word","slug":"baseline-needs-more-love-on-simple-word","title":"Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms","date":"2018-05-24","arxiv_id":"1805.09843","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/hyperbolic-representation-learning-for-fast","slug":"hyperbolic-representation-learning-for-fast","title":"Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering","date":"2017-07-25","arxiv_id":"1707.07847","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/neural-semantic-encoders","slug":"neural-semantic-encoders","title":"Neural Semantic Encoders","date":"2016-07-14","arxiv_id":"1607.04315","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/key-value-memory-networks-for-directly","slug":"key-value-memory-networks-for-directly","title":"Key-Value Memory Networks for Directly Reading Documents","date":"2016-06-09","arxiv_id":"1606.03126","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/pairwise-word-interaction-modeling-with-deep","slug":"pairwise-word-interaction-modeling-with-deep","title":"Pairwise Word Interaction Modeling with Deep Neural Networks for Semantic Similarity Measurement","date":"2016-06-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sentence-similarity-learning-by-lexical","slug":"sentence-similarity-learning-by-lexical","title":"Sentence Similarity Learning by Lexical Decomposition and Composition","date":"2016-02-23","arxiv_id":"1602.07019","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/attentive-pooling-networks","slug":"attentive-pooling-networks","title":"Attentive Pooling Networks","date":"2016-02-11","arxiv_id":"1602.03609","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/neural-variational-inference-for-text","slug":"neural-variational-inference-for-text","title":"Neural Variational Inference for Text Processing","date":"2015-11-19","arxiv_id":"1511.06038","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/neural-variational-inference-for-text#ran","syntology_url":"https://syntology.ai/paper/1511.06038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.06038"}}}},{"paper":"/paper/wikiqa-a-challenge-dataset-for-open-domain","slug":"wikiqa-a-challenge-dataset-for-open-domain","title":"WikiQA: A Challenge Dataset for Open-Domain Question Answering","date":"2015-09-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-learning-for-answer-sentence-selection","slug":"deep-learning-for-answer-sentence-selection","title":"Deep Learning for Answer Sentence Selection","date":"2014-12-04","arxiv_id":"1412.1632","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/distributed-representations-of-sentences-and","slug":"distributed-representations-of-sentences-and","title":"Distributed Representations of Sentences and Documents","date":"2014-05-16","arxiv_id":"1405.4053","rows_on_this_dataset":2,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distributed-representations-of-sentences-and#ran","syntology_url":"https://syntology.ai/paper/1405.4053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1405.4053"}}}}],"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/dataset/wikiqa/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/wikiqa/papers/ran/1","json":"/dataset/wikiqa/papers/ran/1.json","rows":3}],"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":3,"samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":3,"papers_with_a_run_with_no_instrument_failure":3,"papers_where_every_run_was_an_instrument_failure":0,"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":"744bce8b831096dcf16f194bc92179bf027e9af1954bb1f024442273ec22219f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}