{"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/commonsenseqa/papers/ran/1","list_of":"/dataset/commonsenseqa","dataset":"CommonsenseQA","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","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)"},"order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","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.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","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,"rows":[1,12],"of":12,"counts":{"papers_with_a_benchmark_row":22,"with_a_code_link":19,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":22,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":12,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":12,"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"},"first_page":"/dataset/commonsenseqa/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/paper/deep-bidirectional-language-knowledge-graph","slug":"deep-bidirectional-language-knowledge-graph","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","date":"2022-10-17","arxiv_id":"2210.09338","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":18,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":9,"pointer_only_for_licence":1,"official":{"repos":["michiyasunaga/dragon"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":9,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-bidirectional-language-knowledge-graph#ran","syntology_url":"https://syntology.ai/paper/2210.09338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09338"}}}},{"paper":"/paper/unifying-language-learning-paradigms","slug":"unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":16,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/google-research"],"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/unifying-language-learning-paradigms#ran","syntology_url":"https://syntology.ai/paper/2205.05131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05131"}}}},{"paper":"/paper/chain-of-thought-prompting-elicits-reasoning","slug":"chain-of-thought-prompting-elicits-reasoning","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","date":"2022-01-28","arxiv_id":"2201.11903","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":4,"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/chain-of-thought-prompting-elicits-reasoning#ran","syntology_url":"https://syntology.ai/paper/2201.11903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11903"}}}},{"paper":"/paper/qa-gnn-reasoning-with-language-models-and","slug":"qa-gnn-reasoning-with-language-models-and","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","date":"2021-04-13","arxiv_id":"2104.06378","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":25,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":17,"pointer_only_for_licence":5,"official":{"repos":["michiyasunaga/qagnn","worksheets.codalab.org/worksheets/0xf215deb05edf44a2ac353c711f52a25f"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":13,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qa-gnn-reasoning-with-language-models-and#ran","syntology_url":"https://syntology.ai/paper/2104.06378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06378"}}}},{"paper":"/paper/unicorn-on-rainbow-a-universal-commonsense","slug":"unicorn-on-rainbow-a-universal-commonsense","title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","date":"2021-03-24","arxiv_id":"2103.13009","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["allenai/rainbow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unicorn-on-rainbow-a-universal-commonsense#ran","syntology_url":"https://syntology.ai/paper/2103.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13009"}}}},{"paper":"/paper/unifiedqa-crossing-format-boundaries-with-a","slug":"unifiedqa-crossing-format-boundaries-with-a","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","date":"2020-05-02","arxiv_id":"2005.00700","rows_on_this_dataset":5,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["allenai/unifiedqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifiedqa-crossing-format-boundaries-with-a#ran","syntology_url":"https://syntology.ai/paper/2005.00700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00700"}}}},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","rows_on_this_dataset":1,"code_links":48,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":126,"samples_ran":81,"samples_constructed":17,"samples_ran_checked":59,"samples_ran_instrument_failed":22,"samples_unverified":45,"pointer_only_for_licence":28,"official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/albert-a-lite-bert-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/1909.11942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11942"}}}},{"paper":"/paper/graph-based-reasoning-over-heterogeneous","slug":"graph-based-reasoning-over-heterogeneous","title":"Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering","date":"2019-09-09","arxiv_id":"1909.05311","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":17,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":5,"samples_unverified":5,"pointer_only_for_licence":2,"official":{"repos":["DecstionBack/AAAI_2020_CommonsenseQA"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/graph-based-reasoning-over-heterogeneous#ran","syntology_url":"https://syntology.ai/paper/1909.05311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05311"}}}},{"paper":"/paper/kagnet-knowledge-aware-graph-networks-for","slug":"kagnet-knowledge-aware-graph-networks-for","title":"KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning","date":"2019-09-04","arxiv_id":"1909.02151","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["INK-USC/KagNet"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/kagnet-knowledge-aware-graph-networks-for#ran","syntology_url":"https://syntology.ai/paper/1909.02151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02151"}}}},{"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","slug":"roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":48,"samples_ran":37,"samples_constructed":11,"samples_ran_checked":36,"samples_ran_instrument_failed":1,"samples_unverified":11,"pointer_only_for_licence":24,"official":{"repos":["pytorch/fairseq"],"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/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"paper":"/paper/explain-yourself-leveraging-language-models","slug":"explain-yourself-leveraging-language-models","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","date":"2019-06-06","arxiv_id":"1906.02361","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/explain-yourself-leveraging-language-models#ran","syntology_url":"https://syntology.ai/paper/1906.02361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02361"}}}},{"paper":"/paper/commonsenseqa-a-question-answering-challenge","slug":"commonsenseqa-a-question-answering-challenge","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","date":"2018-11-02","arxiv_id":"1811.00937","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["jonathanherzig/commonsenseqa"],"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/commonsenseqa-a-question-answering-challenge#ran","syntology_url":"https://syntology.ai/paper/1811.00937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.00937"}}}}],"record_sha256":"8226bb8bd4234c1abdf07ca63c010181cc5e41ad454f470cb25348ed76274e29","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}