{"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/winogrande","name":"Winogrande","slug":"winogrande","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":26,"papers_with_code":12,"benchmarks":0,"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":null,"slug":"winogrande-on-winogrande","dataset":"WinoGrande","dataset_url":"/dataset/winogrande","rows_in_archive":0,"metrics":["Accuracy"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/winogrande","name":"WinoGrande","full_name":"","num_papers_in_archive":703}],"subtasks":[],"parent_tasks":[{"url":"/task/common-sense-reasoning","name":"Common Sense Reasoning"}],"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":26,"of":26,"of_with_code":12,"tagged_in_all":26,"counts":{"archive_papers_tagged":26,"with_a_code_link":12,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":26,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":5,"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/winogrande-an-adversarial-winograd-schema","slug":"winogrande-an-adversarial-winograd-schema","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","date":"2019-07-24","arxiv_id":"1907.10641","repositories_listed":10,"syntology":null},{"url":"/paper/designing-effective-sparse-expert-models","slug":"designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/designing-effective-sparse-expert-models#ran","syntology_url":"https://syntology.ai/paper/2202.08906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.08906"}},"official":{"repos":["tensorflow/mesh"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"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/bridging-the-gap-enhancing-llm-performance","slug":"bridging-the-gap-enhancing-llm-performance","title":"Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments","date":"2024-12-16","arxiv_id":"2412.12417","repositories_listed":1,"syntology":null},{"url":"/paper/texttt-metabench-a-sparse-benchmark-to","slug":"texttt-metabench-a-sparse-benchmark-to","title":"$\\texttt{metabench}$ -- A Sparse Benchmark to Measure General Ability in Large Language Models","date":"2024-07-04","arxiv_id":"2407.12844","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"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) · 1 unverified","sample_list":"/paper/texttt-metabench-a-sparse-benchmark-to#ran","syntology_url":"https://syntology.ai/paper/2407.12844","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12844"}},"official":{"repos":["adkipnis/metabench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/layer-skip-enabling-early-exit-inference-and","slug":"layer-skip-enabling-early-exit-inference-and","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","date":"2024-04-25","arxiv_id":"2404.16710","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/layer-skip-enabling-early-exit-inference-and#ran","syntology_url":"https://syntology.ai/paper/2404.16710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16710"}},"official":{"repos":["facebookresearch/layerskip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lisa-layerwise-importance-sampling-for-memory","slug":"lisa-layerwise-importance-sampling-for-memory","title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning","date":"2024-03-26","arxiv_id":"2403.17919","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/lisa-layerwise-importance-sampling-for-memory#ran","syntology_url":"https://syntology.ai/paper/2403.17919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17919"}},"official":{"repos":["optimalscale/lmflow"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/are-hard-examples-also-harder-to-explain-a","slug":"are-hard-examples-also-harder-to-explain-a","title":"Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations","date":"2022-11-14","arxiv_id":"2211.07517","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/are-hard-examples-also-harder-to-explain-a#ran","syntology_url":"https://syntology.ai/paper/2211.07517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07517"}},"official":{"repos":["swarnahub/explanationhardness"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-curriculum-learning-for-commonsense","slug":"on-curriculum-learning-for-commonsense","title":"On Curriculum Learning for Commonsense Reasoning","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-out-of-domain-transfer-learning-of","slug":"few-shot-out-of-domain-transfer-learning-of","title":"Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup","date":"2021-12-12","arxiv_id":"2112.06204","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/g-daug-generative-data-augmentation-for","slug":"g-daug-generative-data-augmentation-for","title":"Generative Data Augmentation for Commonsense Reasoning","date":"2020-04-24","arxiv_id":"2004.11546","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/g-daug-generative-data-augmentation-for#ran","syntology_url":"https://syntology.ai/paper/2004.11546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.11546"}},"official":{"repos":["yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":null,"slug":"elastic-weight-consolidation-for-full","title":"Elastic Weight Consolidation for Full-Parameter Continual Pre-Training of Gemma2","date":"2025-05-09","arxiv_id":"2505.05946","repositories_listed":0,"syntology":null},{"url":null,"slug":"more-is-less-the-pitfalls-of-multi-model","title":"More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment","date":"2025-04-03","arxiv_id":"2504.02193","repositories_listed":0,"syntology":null},{"url":null,"slug":"winowhat-a-parallel-corpus-of-paraphrased","title":"WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorization","date":"2025-03-31","arxiv_id":"2503.23779","repositories_listed":0,"syntology":null},{"url":null,"slug":"obliviate-efficient-unmemorization-for","title":"Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models","date":"2025-02-20","arxiv_id":"2502.15010","repositories_listed":0,"syntology":null},{"url":null,"slug":"portllm-personalizing-evolving-large-language","title":"PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches","date":"2024-10-08","arxiv_id":"2410.10870","repositories_listed":0,"syntology":null},{"url":null,"slug":"judgment-of-thoughts-courtroom-of-the-binary","title":"Judgment of Thoughts: Courtroom of the Binary Logical Reasoning in Large Language Models","date":"2024-09-25","arxiv_id":"2409.16635","repositories_listed":0,"syntology":null},{"url":null,"slug":"promises-outlooks-and-challenges-of-diffusion","title":"Promises, Outlooks and Challenges of Diffusion Language Modeling","date":"2024-06-17","arxiv_id":"2406.11473","repositories_listed":0,"syntology":null},{"url":null,"slug":"who-s-harry-potter-approximate-unlearning-in","title":"Who's Harry Potter? Approximate Unlearning in LLMs","date":"2023-10-03","arxiv_id":"2310.02238","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-warm-start-and-a-clean-crawled-corpus-a-1","title":"A Warm Start and a Clean Crawled Corpus - A Recipe for Good Language Models","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-application-of-pseudo-log-likelihoods-to","title":"An Application of Pseudo-Log-Likelihoods to Natural Language Scoring","date":"2022-01-23","arxiv_id":"2201.09377","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-warm-start-and-a-clean-crawled-corpus-a","title":"A Warm Start and a Clean Crawled Corpus -- A Recipe for Good Language Models","date":"2022-01-14","arxiv_id":"2201.05601","repositories_listed":0,"syntology":null},{"url":null,"slug":"not-so-fine-tuning-measures-of-common-sense","title":"Not-so fine-tuning: Measures of Common Sense for Language Models","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-pronoun-resolution-via-masked","title":"Unsupervised Pronoun Resolution via Masked Noun-Phrase Prediction","date":"2021-05-26","arxiv_id":"2105.12392","repositories_listed":0,"syntology":null},{"url":"/paper/tttttackling-winogrande-schemas","slug":"tttttackling-winogrande-schemas","title":"TTTTTackling WinoGrande Schemas","date":"2020-03-18","arxiv_id":"2003.08380","repositories_listed":0,"syntology":null}],"syntology_records":7,"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":6,"papers_where_code_ran_first_page":"/task/winogrande/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/winogrande/papers/ran/1","json":"/task/winogrande/papers/ran/1.json","rows":6}],"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":"ffef97ddf3c12127f8132f0818b9cc6f47fb73a9e18197c66368b72ec7cc20a2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}