{"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/question-selection","name":"Question Selection","slug":"question-selection","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":31,"papers_with_code":18,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/question-selection-on-big-bench","slug":"question-selection-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla-70B (few-shot, k=5)","paper_title":"Training Compute-Optimal Large Language Models","paper_url":"/paper/training-compute-optimal-large-language","paper_date":"2022-03-29","arxiv_id":"2203.15556","code_links":[{"title":"karpathy/llama2.c","url":"https://github.com/karpathy/llama2.c"},{"title":"nkluge-correa/teenytinyllama","url":"https://github.com/nkluge-correa/teenytinyllama"}],"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349}],"subtasks":[],"parent_tasks":[{"url":"/task/reading-comprehension","name":"Reading Comprehension"}],"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":31,"of":31,"of_with_code":18,"tagged_in_all":31,"counts":{"archive_papers_tagged":31,"with_a_code_link":18,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":31,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"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 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/scaling-language-models-methods-analysis-1","slug":"scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}},"official":null}},{"url":"/paper/bobcat-bilevel-optimization-based","slug":"bobcat-bilevel-optimization-based","title":"BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing","date":"2021-08-17","arxiv_id":"2108.07386","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":3,"n_ran_checked":5,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bobcat-bilevel-optimization-based#ran","syntology_url":"https://syntology.ai/paper/2108.07386","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07386"}},"official":{"repos":["arghosh/bobcat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/asking-clarifying-questions-in-open-domain","slug":"asking-clarifying-questions-in-open-domain","title":"Asking Clarifying Questions in Open-Domain Information-Seeking Conversations","date":"2019-07-15","arxiv_id":"1907.06554","repositories_listed":2,"syntology":null},{"url":"/paper/autojudger-an-agent-driven-framework-for","slug":"autojudger-an-agent-driven-framework-for","title":"AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs","date":"2025-05-27","arxiv_id":"2505.21389","repositories_listed":1,"syntology":null},{"url":"/paper/qa-prompting-improving-summarization-with","slug":"qa-prompting-improving-summarization-with","title":"QA-prompting: Improving Summarization with Large Language Models using Question-Answering","date":"2025-05-20","arxiv_id":"2505.14347","repositories_listed":1,"syntology":null},{"url":"/paper/decentralized-arena-towards-democratic-and","slug":"decentralized-arena-towards-democratic-and","title":"Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models","date":"2025-05-19","arxiv_id":"2505.12808","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-political-surveys-and-gpt-4-tackling","slug":"adaptive-political-surveys-and-gpt-4-tackling","title":"Adaptive political surveys and GPT-4: Tackling the cold start problem with simulated user interactions","date":"2025-03-12","arxiv_id":"2503.09311","repositories_listed":1,"syntology":null},{"url":"/paper/pscon-toward-conversational-product-search","slug":"pscon-toward-conversational-product-search","title":"PSCon: Product Search Through Conversations","date":"2025-02-19","arxiv_id":"2502.13881","repositories_listed":1,"syntology":null},{"url":"/paper/active-task-disambiguation-with-llms","slug":"active-task-disambiguation-with-llms","title":"Active Task Disambiguation with LLMs","date":"2025-02-06","arxiv_id":"2502.04485","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-inspired-cold-start-with-sufficient","slug":"diffusion-inspired-cold-start-with-sufficient","title":"Diffusion-Inspired Cold Start with Sufficient Prior in Computerized Adaptive Testing","date":"2024-11-19","arxiv_id":"2411.12182","repositories_listed":1,"syntology":null},{"url":"/paper/fast-and-adaptive-questionnaires-for-voting","slug":"fast-and-adaptive-questionnaires-for-voting","title":"Fast and Adaptive Questionnaires for Voting Advice Applications","date":"2024-04-02","arxiv_id":"2404.01872","repositories_listed":1,"syntology":null},{"url":"/paper/survey-of-computerized-adaptive-testing-a","slug":"survey-of-computerized-adaptive-testing-a","title":"Survey of Computerized Adaptive Testing: A Machine Learning Perspective","date":"2024-03-31","arxiv_id":"2404.00712","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/survey-of-computerized-adaptive-testing-a#ran","syntology_url":"https://syntology.ai/paper/2404.00712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00712"}},"official":{"repos":["bigdata-ustc/educat"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/balancing-test-accuracy-and-security-in","slug":"balancing-test-accuracy-and-security-in","title":"Balancing Test Accuracy and Security in Computerized Adaptive Testing","date":"2023-05-18","arxiv_id":"2305.18312","repositories_listed":1,"syntology":null},{"url":"/paper/what-makes-a-question-inquisitive-a-study-on-1","slug":"what-makes-a-question-inquisitive-a-study-on-1","title":"“What makes a question inquisitive?” A Study on Type-Controlled Inquisitive Question Generation","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/comqa-compositional-question-answering-via","slug":"comqa-compositional-question-answering-via","title":"ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks","date":"2021-01-16","arxiv_id":"2101.06400","repositories_listed":1,"syntology":null},{"url":"/paper/crowdsourced-collective-entity-resolution","slug":"crowdsourced-collective-entity-resolution","title":"Crowdsourced Collective Entity Resolution with Relational Match Propagation","date":"2020-02-21","arxiv_id":"2002.09361","repositories_listed":1,"syntology":null},{"url":"/paper/modelling-sentence-pairs-with-tree-structured","slug":"modelling-sentence-pairs-with-tree-structured","title":"Modelling Sentence Pairs with Tree-structured Attentive Encoder","date":"2016-10-10","arxiv_id":"1610.02806","repositories_listed":1,"syntology":null},{"url":null,"slug":"testagent-an-adaptive-and-intelligent-expert","title":"TestAgent: An Adaptive and Intelligent Expert for Human Assessment","date":"2025-06-03","arxiv_id":"2506.03032","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-incremental-preference-elicitation-based","title":"An incremental preference elicitation-based approach to learning potentially non-monotonic preferences in multi-criteria sorting","date":"2024-09-04","arxiv_id":"2409.02760","repositories_listed":0,"syntology":null},{"url":null,"slug":"asking-more-informative-questions-for","title":"Asking More Informative Questions for Grounded Retrieval","date":"2023-11-14","arxiv_id":"2311.08584","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-detect-interesting-anomalies","title":"Learning to Detect Interesting Anomalies","date":"2022-10-28","arxiv_id":"2210.16334","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-makes-a-question-inquisitive-a-study-on","title":"\"What makes a question inquisitive?\" A Study on Type-Controlled Inquisitive Question Generation","date":"2022-05-17","arxiv_id":"2205.08056","repositories_listed":0,"syntology":null},{"url":null,"slug":"asking-clarifying-questions-based-on-negative","title":"Asking Clarifying Questions Based on Negative Feedback in Conversational Search","date":"2021-07-12","arxiv_id":"2107.05760","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-clarifying-question-selection-system-from","title":"A Clarifying Question Selection System from NTES_ALONG in Convai3 Challenge","date":"2020-10-27","arxiv_id":"2010.14202","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-transformer-leveraging-multiple","title":"Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search","date":"2020-06-13","arxiv_id":"2006.07548","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-clustering-from-noisy-binary-feedback","title":"Optimal Clustering from Noisy Binary Feedback","date":"2019-10-14","arxiv_id":"1910.06002","repositories_listed":0,"syntology":null},{"url":null,"slug":"submodular-maximization-under-fading-model","title":"Cascade Submodular Maximization: Question Selection and Sequencing in Online Personality Quiz","date":"2019-01-23","arxiv_id":"1901.07708","repositories_listed":0,"syntology":null},{"url":null,"slug":"playing-20-question-game-with-policy-based","title":"Playing 20 Question Game with Policy-Based Reinforcement Learning","date":"2018-08-23","arxiv_id":"1808.07645","repositories_listed":0,"syntology":null},{"url":"/paper/convkn-at-semeval-2016-task-3-answer-and","slug":"convkn-at-semeval-2016-task-3-answer-and","title":"ConvKN at SemEval-2016 Task 3: Answer and Question Selection for Question Answering on Arabic and English Fora","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"crowdsourcing-pareto-optimal-object-finding","title":"Crowdsourcing Pareto-Optimal Object Finding by Pairwise Comparisons","date":"2014-09-15","arxiv_id":"1409.4161","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/question-selection/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/question-selection/papers/ran/1","json":"/task/question-selection/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":"35bd3f49c6082fc2a1f0e9cdfa7cb8b23c1947134b96c61374f21bcc9902cc37","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}