{"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/pop-stddev","entry":"pop_stddev","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":10,"n_papers_ran":10,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":10,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":0},"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":"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/api/metric.py","file_url":"https://github.com/babylm/evaluation-pipeline/blob/HEAD/lm_eval/api/metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"518b2201c66c2ad3","mcp_get_code":{"code_sha256":"518b2201c66c2ad3"}},{"arxiv_id":"2406.10594","paper":"/paper/blockpruner-fine-grained-pruning-for-large","title":"BlockPruner: Fine-grained Pruning for Large Language Models","date":"2024-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MrGGLS/BlockPruner","path":"lm_eval/lm_eval/metrics.py","file_url":"https://github.com/MrGGLS/BlockPruner/blob/HEAD/lm_eval/lm_eval/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"518b2201c66c2ad3","mcp_get_code":{"code_sha256":"518b2201c66c2ad3"}},{"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/metrics.py","file_url":"https://github.com/hdong920/griffin/blob/HEAD/src/lm_eval/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"518b2201c66c2ad3","mcp_get_code":{"code_sha256":"518b2201c66c2ad3"}},{"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/metrics.py","file_url":"https://github.com/cordercorder/quant_eval/blob/HEAD/quant/SpQR/lm-evaluation-harness/lm_eval/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"518b2201c66c2ad3","mcp_get_code":{"code_sha256":"518b2201c66c2ad3"}},{"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/metrics.py","file_url":"https://github.com/hdong920/less/blob/HEAD/src/lm_eval/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"518b2201c66c2ad3","mcp_get_code":{"code_sha256":"518b2201c66c2ad3"}},{"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/financial-evaluation/lm_eval/metrics.py","file_url":"https://github.com/dai-shen/laiw/blob/HEAD/src/financial-evaluation/lm_eval/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"518b2201c66c2ad3","mcp_get_code":{"code_sha256":"518b2201c66c2ad3"}},{"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/metrics.py","file_url":"https://github.com/nlp-uoregon/mlmm-evaluation/blob/HEAD/lm_eval/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"518b2201c66c2ad3","mcp_get_code":{"code_sha256":"518b2201c66c2ad3"}},{"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/metrics.py","file_url":"https://github.com/milliemaoo/prompt-position/blob/HEAD/lm_eval/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"518b2201c66c2ad3","mcp_get_code":{"code_sha256":"518b2201c66c2ad3"}},{"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/metrics.py","file_url":"https://github.com/piresramon/gpt-4-enem/blob/HEAD/lm_eval/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"518b2201c66c2ad3","mcp_get_code":{"code_sha256":"518b2201c66c2ad3"}},{"arxiv_id":"2025.naacl-long.237","paper":null,"title":"arXiv:2025.naacl-long.237","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"nbasyl/LLM-FP4","path":"lm_eval/metrics.py","file_url":"https://github.com/nbasyl/LLM-FP4/blob/HEAD/lm_eval/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"518b2201c66c2ad3","mcp_get_code":{"code_sha256":"518b2201c66c2ad3"}}]}