{"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/anli","name":"ANLI","full_name":"Adversarial NLI","description_markdown":"The Adversarial Natural Language Inference (**ANLI**, Nie et al.) is a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. Particular, the data is selected to be difficult to the state-of-the-art models, including BERT and RoBERTa.\r\n\r\nSource: [The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding](https://arxiv.org/abs/2002.07972)\r\nImage Source: [https://arxiv.org/pdf/1910.14599.pdf](https://arxiv.org/pdf/1910.14599.pdf)","description_withheld":null,"homepage":"https://github.com/facebookresearch/anli","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/adversarial-nli-a-new-benchmark-for-natural","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","first_author":"Yixin Nie","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://github.com/facebookresearch/anli/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"}],"languages":[],"variants":["ANLI test","ANLI","ANLI-all","ANLI-r3"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/facebook/anli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/anli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/KETI-AIR/anli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/KETI-AIR/kor_anli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#adversarial-natural-language-inference-anli-corpus","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/anli","frameworks":["tf","jax"]},{"repo":"https://github.com/facebookresearch/anli","url":"https://github.com/facebookresearch/anli","frameworks":["pytorch"]}],"num_papers_in_archive":287,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/natural-language-inference-on-anli-test","task":"Natural Language Inference","dataset_variant":"ANLI test","rows":25,"metrics":["A1","A2","A3"],"first_row_in_archive_order":{"model":"T5-3B (explanation prompting)","paper":"/paper/prompting-for-explanations-improves","metrics":{"A1":"81.8","A2":"72.5","A3":"74.8"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/natural-language-inference-on-anli","task":"Natural Language Inference","dataset_variant":"ANLI","rows":0,"metrics":["Accuracy","F1 Macro","F1 Micro","F1 Weighted","Precision Macro","Precision Micro","Precision Weighted","Recall Macro","Recall Micro","Recall Weighted","loss"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/natural-language-inference-on-anli-r3","task":"Natural Language Inference","dataset_variant":"ANLI-r3","rows":0,"metrics":["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":14,"of":14,"counts":{"papers_with_a_benchmark_row":14,"with_a_code_link":11,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":14,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":4,"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/a-systematic-study-and-comprehensive","slug":"a-systematic-study-and-comprehensive","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","date":"2023-05-29","arxiv_id":"2305.18486","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/the-cot-collection-improving-zero-shot-and","slug":"the-cot-collection-improving-zero-shot-and","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","date":"2023-05-23","arxiv_id":"2305.14045","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/prompting-for-explanations-improves","slug":"prompting-for-explanations-improves","title":"Prompting for explanations improves Adversarial NLI. Is this true? {Yes} it is {true} because {it weakens superficial cues}","date":"2023-05-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/exploring-the-benefits-of-training-expert","slug":"exploring-the-benefits-of-training-expert","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","date":"2023-02-07","arxiv_id":"2302.03202","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["joeljang/elm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-benefits-of-training-expert#ran","syntology_url":"https://syntology.ai/paper/2302.03202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03202"}}}},{"paper":"/paper/knowledge-in-context-towards-knowledgeable","slug":"knowledge-in-context-towards-knowledgeable","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","date":"2022-10-28","arxiv_id":"2210.16433","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/large-language-models-can-self-improve","slug":"large-language-models-can-self-improve","title":"Large Language Models Can Self-Improve","date":"2022-10-20","arxiv_id":"2210.11610","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/guess-the-instruction-making-language-models","slug":"guess-the-instruction-making-language-models","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","date":"2022-10-06","arxiv_id":"2210.02969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/infobert-improving-robustness-of-language-1","slug":"infobert-improving-robustness-of-language-1","title":"InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective","date":"2020-10-05","arxiv_id":"2010.02329","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["AI-secure/InfoBERT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/infobert-improving-robustness-of-language-1#ran","syntology_url":"https://syntology.ai/paper/2010.02329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02329"}}}},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"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/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/adversarial-training-for-large-neural","slug":"adversarial-training-for-large-neural","title":"Adversarial Training for Large Neural Language Models","date":"2020-04-20","arxiv_id":"2004.08994","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"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":"2026-10-05T00:36:11+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/xlnet-generalized-autoregressive-pretraining","slug":"xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","arxiv_id":"1906.08237","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":15,"samples_constructed":2,"samples_ran_checked":10,"samples_ran_instrument_failed":5,"samples_unverified":9,"pointer_only_for_licence":4,"official":{"repos":["zihangdai/xlnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xlnet-generalized-autoregressive-pretraining#ran","syntology_url":"https://syntology.ai/paper/1906.08237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08237"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/a-systematic-study-and-comprehensive","slug":"a-systematic-study-and-comprehensive","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","date":"2023-05-29","arxiv_id":"2305.18486","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/the-cot-collection-improving-zero-shot-and","slug":"the-cot-collection-improving-zero-shot-and","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","date":"2023-05-23","arxiv_id":"2305.14045","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/prompting-for-explanations-improves","slug":"prompting-for-explanations-improves","title":"Prompting for explanations improves Adversarial NLI. Is this true? {Yes} it is {true} because {it weakens superficial cues}","date":"2023-05-01","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/exploring-the-benefits-of-training-expert","slug":"exploring-the-benefits-of-training-expert","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","date":"2023-02-07","arxiv_id":"2302.03202","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["joeljang/elm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/exploring-the-benefits-of-training-expert#ran","syntology_url":"https://syntology.ai/paper/2302.03202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03202"}}}},{"paper":"/paper/knowledge-in-context-towards-knowledgeable","slug":"knowledge-in-context-towards-knowledgeable","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","date":"2022-10-28","arxiv_id":"2210.16433","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/large-language-models-can-self-improve","slug":"large-language-models-can-self-improve","title":"Large Language Models Can Self-Improve","date":"2022-10-20","arxiv_id":"2210.11610","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/guess-the-instruction-making-language-models","slug":"guess-the-instruction-making-language-models","title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","date":"2022-10-06","arxiv_id":"2210.02969","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/infobert-improving-robustness-of-language-1","slug":"infobert-improving-robustness-of-language-1","title":"InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective","date":"2020-10-05","arxiv_id":"2010.02329","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["AI-secure/InfoBERT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/infobert-improving-robustness-of-language-1#ran","syntology_url":"https://syntology.ai/paper/2010.02329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02329"}}}},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"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/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/adversarial-training-for-large-neural","slug":"adversarial-training-for-large-neural","title":"Adversarial Training for Large Neural Language Models","date":"2020-04-20","arxiv_id":"2004.08994","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"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":"2026-10-05T00:36:11+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/xlnet-generalized-autoregressive-pretraining","slug":"xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","arxiv_id":"1906.08237","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":15,"samples_constructed":2,"samples_ran_checked":10,"samples_ran_instrument_failed":5,"samples_unverified":9,"pointer_only_for_licence":4,"official":{"repos":["zihangdai/xlnet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/xlnet-generalized-autoregressive-pretraining#ran","syntology_url":"https://syntology.ai/paper/1906.08237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.08237"}}}}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/anli/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/anli/papers/ran/1","json":"/dataset/anli/papers/ran/1.json","rows":5}],"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":5,"samples_harvested":144,"samples_ran":104,"samples_constructed":13,"samples_ran_checked":86,"samples_ran_instrument_failed":18,"samples_unverified":40,"pointer_only_for_licence":42,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":4,"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":"5b577e193d538e97307ce293fd0693d65b0d8bc8fac50bd6fbb39bcbf6ee4ebd","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}