{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/make-table","entry":"make_table","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":15,"n_papers_ran":1,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":9,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":18,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":8},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2606.04980","paper":"/paper/arxiv-2606-04980","title":"AlphaQ: Calibration-Free Bit Allocation for Mixture-of-Experts Quantization","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Superone77/AlphaQ","path":"eval_utils.py","file_url":"https://github.com/Superone77/AlphaQ/blob/HEAD/eval_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f5f924ce5962ca8f","mcp_get_code":{"code_sha256":"f5f924ce5962ca8f"}},{"arxiv_id":"2504.08165","paper":"/paper/findings-of-the-babylm-challenge-sample","title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"babylm/evaluation-pipeline","path":"lm_eval/evaluator.py","file_url":"https://github.com/babylm/evaluation-pipeline/blob/HEAD/lm_eval/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"910a58b3f0fe9967","mcp_get_code":{"code_sha256":"910a58b3f0fe9967"}},{"arxiv_id":"2409.03856","paper":"/paper/sirius-contextual-sparsity-with-correction","title":"Sirius: Contextual Sparsity with Correction for Efficient LLMs","date":"2024-09-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"9d95c14130837ee4","mcp_get_code":{"code_sha256":"9d95c14130837ee4"}},{"arxiv_id":"2404.01365","paper":"/paper/prompt-prompted-mixture-of-experts-for","title":"Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation","date":"2024-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hdong920/griffin","path":"src/lm_eval/evaluator.py","file_url":"https://github.com/hdong920/griffin/blob/HEAD/src/lm_eval/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9d95c14130837ee4","mcp_get_code":{"code_sha256":"9d95c14130837ee4"}},{"arxiv_id":"2402.16775","paper":"/paper/a-comprehensive-evaluation-of-quantization","title":"A Comprehensive Evaluation of Quantization Strategies for Large Language Models","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cordercorder/quant_eval","path":"quant/SpQR/lm-evaluation-harness/lm_eval/evaluator.py","file_url":"https://github.com/cordercorder/quant_eval/blob/HEAD/quant/SpQR/lm-evaluation-harness/lm_eval/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9d95c14130837ee4","mcp_get_code":{"code_sha256":"9d95c14130837ee4"}},{"arxiv_id":"2402.12659","paper":"/paper/the-finben-an-holistic-financial-benchmark","title":"FinBen: A Holistic Financial Benchmark for Large Language Models","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chancefocus/pixiu","path":"src/evaluator.py","file_url":"https://github.com/chancefocus/pixiu/blob/HEAD/src/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9d95c14130837ee4","mcp_get_code":{"code_sha256":"9d95c14130837ee4"}},{"arxiv_id":"2402.09739","paper":"/paper/qurating-selecting-high-quality-data-for","title":"QuRating: Selecting High-Quality Data for Training Language Models","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/QuRating","path":"eval/lm-evaluation-harness/lm_eval/evaluator.py","file_url":"https://github.com/princeton-nlp/QuRating/blob/HEAD/eval/lm-evaluation-harness/lm_eval/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9d95c14130837ee4","mcp_get_code":{"code_sha256":"9d95c14130837ee4"}},{"arxiv_id":"2402.09398","paper":"/paper/get-more-with-less-synthesizing-recurrence","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hdong920/less","path":"src/lm_eval/evaluator.py","file_url":"https://github.com/hdong920/less/blob/HEAD/src/lm_eval/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9d95c14130837ee4","mcp_get_code":{"code_sha256":"9d95c14130837ee4"}},{"arxiv_id":"2310.05620","paper":"/paper/laiw-a-chinese-legal-large-language-models","title":"LAiW: A Chinese Legal Large Language Models Benchmark","date":"2023-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dai-shen/laiw","path":"src/evaluator.py","file_url":"https://github.com/dai-shen/laiw/blob/HEAD/src/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9d95c14130837ee4","mcp_get_code":{"code_sha256":"9d95c14130837ee4"}},{"arxiv_id":"2307.16039","paper":"/paper/okapi-instruction-tuned-large-language-models","title":"Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback","date":"2023-07-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlp-uoregon/mlmm-evaluation","path":"lm_eval/evaluator.py","file_url":"https://github.com/nlp-uoregon/mlmm-evaluation/blob/HEAD/lm_eval/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9d95c14130837ee4","mcp_get_code":{"code_sha256":"9d95c14130837ee4"}},{"arxiv_id":"2305.14493","paper":"/paper/prompt-position-really-matters-in-few-shot","title":"Do prompt positions really matter?","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"milliemaoo/prompt-position","path":"lm_eval/evaluator.py","file_url":"https://github.com/milliemaoo/prompt-position/blob/HEAD/lm_eval/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9d95c14130837ee4","mcp_get_code":{"code_sha256":"9d95c14130837ee4"}},{"arxiv_id":"2303.17003","paper":"/paper/evaluating-gpt-3-5-and-gpt-4-models-on","title":"Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams","date":"2023-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"piresramon/gpt-4-enem","path":"lm_eval/evaluator.py","file_url":"https://github.com/piresramon/gpt-4-enem/blob/HEAD/lm_eval/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9d95c14130837ee4","mcp_get_code":{"code_sha256":"9d95c14130837ee4"}},{"arxiv_id":"2009.14193","paper":"/paper/uncertainty-sets-for-image-classifiers-using","title":"Uncertainty Sets for Image Classifiers using Conformal Prediction","date":"2020-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aangelopoulos/conformal_classification","path":"experiments/table1.py","file_url":"https://github.com/aangelopoulos/conformal_classification/blob/HEAD/experiments/table1.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8ce51944e3958c60","mcp_get_code":{"code_sha256":"8ce51944e3958c60"}},{"arxiv_id":"2009.14193","paper":"/paper/uncertainty-sets-for-image-classifiers-using","title":"Uncertainty Sets for Image Classifiers using Conformal Prediction","date":"2020-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aangelopoulos/conformal_classification","path":"experiments/table11.py","file_url":"https://github.com/aangelopoulos/conformal_classification/blob/HEAD/experiments/table11.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"837d496b65e5409a","mcp_get_code":{"code_sha256":"837d496b65e5409a"}},{"arxiv_id":"2009.14193","paper":"/paper/uncertainty-sets-for-image-classifiers-using","title":"Uncertainty Sets for Image Classifiers using Conformal Prediction","date":"2020-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aangelopoulos/conformal_classification","path":"experiments/table2.py","file_url":"https://github.com/aangelopoulos/conformal_classification/blob/HEAD/experiments/table2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e5323ecb83f4191","mcp_get_code":{"code_sha256":"3e5323ecb83f4191"}},{"arxiv_id":"2009.14193","paper":"/paper/uncertainty-sets-for-image-classifiers-using","title":"Uncertainty Sets for Image Classifiers using Conformal Prediction","date":"2020-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aangelopoulos/conformal_classification","path":"experiments/table5.py","file_url":"https://github.com/aangelopoulos/conformal_classification/blob/HEAD/experiments/table5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"153f3eb42aa57f6e","mcp_get_code":{"code_sha256":"153f3eb42aa57f6e"}},{"arxiv_id":"2005.01831","paper":"/paper/evaluating-explainable-ai-which-algorithmic","title":"Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?","date":"2020-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"peterbhase/InterpretableNLP-ACL2020","path":"tabular/anchor/make_graphs_and_table.py","file_url":"https://github.com/peterbhase/InterpretableNLP-ACL2020/blob/HEAD/tabular/anchor/make_graphs_and_table.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1db3f658ae6ec3e0","mcp_get_code":{"code_sha256":"1db3f658ae6ec3e0"}},{"arxiv_id":"2003.07082","paper":"/paper/stanza-a-python-natural-language-processing","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","date":"2020-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rasoolims/stanza","path":"stanza/pipeline/core.py","file_url":"https://github.com/rasoolims/stanza/blob/HEAD/stanza/pipeline/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"99a85098b6a5141d","mcp_get_code":{"code_sha256":"99a85098b6a5141d"}}]}