{"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/calculate-correlation","entry":"calculate_correlation","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":5,"n_papers_ran":5,"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":6,"n_samples_ran":5,"n_samples_fingerprinted":1,"n_places":7,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"unverified":1},"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":"2410.02184","paper":"/paper/codejudge-evaluating-code-generation-with","title":"CodeJudge: Evaluating Code Generation with Large Language Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VichyTong/CodeJudge","path":"evaluation/apps/calculate_single_correlation.py","file_url":"https://github.com/VichyTong/CodeJudge/blob/HEAD/evaluation/apps/calculate_single_correlation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2dbad7c7765ac00d","mcp_get_code":{"code_sha256":"2dbad7c7765ac00d"}},{"arxiv_id":"2410.02184","paper":"/paper/codejudge-evaluating-code-generation-with","title":"CodeJudge: Evaluating Code Generation with Large Language Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VichyTong/CodeJudge","path":"evaluation/apps/calculate_table.py","file_url":"https://github.com/VichyTong/CodeJudge/blob/HEAD/evaluation/apps/calculate_table.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5216eb6022b6ac5b","mcp_get_code":{"code_sha256":"5216eb6022b6ac5b"}},{"arxiv_id":"2410.02184","paper":"/paper/codejudge-evaluating-code-generation-with","title":"CodeJudge: Evaluating Code Generation with Large Language Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VichyTong/CodeJudge","path":"evaluation/apps/calculate_accuracy.py","file_url":"https://github.com/VichyTong/CodeJudge/blob/HEAD/evaluation/apps/calculate_accuracy.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":"8afc902197b67802","mcp_get_code":{"code_sha256":"8afc902197b67802"}},{"arxiv_id":"2406.16749","paper":"/paper/inferring-stochastic-low-rank-recurrent","title":"Inferring stochastic low-rank recurrent neural networks from neural data","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mackelab/smc_rnns","path":"evaluation/calc_stats.py","file_url":"https://github.com/mackelab/smc_rnns/blob/HEAD/evaluation/calc_stats.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":"8e47cd6071cb66e5","mcp_get_code":{"code_sha256":"8e47cd6071cb66e5"}},{"arxiv_id":"2404.19563","paper":"/paper/repeval-effective-text-evaluation-with-llm","title":"RepEval: Effective Text Evaluation with LLM Representation","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maszhongming/UniEval","path":"reproduce/correlation.py","file_url":"https://github.com/maszhongming/UniEval/blob/HEAD/reproduce/correlation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31b107371370f1bf","mcp_get_code":{"code_sha256":"31b107371370f1bf"}},{"arxiv_id":"2310.05657","paper":"/paper/a-closer-look-into-automatic-evaluation-using","title":"A Closer Look into Automatic Evaluation Using Large Language Models","date":"2023-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"d223302/a-closer-look-to-llm-evaluation","path":"all_eval.py","file_url":"https://github.com/d223302/a-closer-look-to-llm-evaluation/blob/HEAD/all_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f8f9c3b9fc2b97e9","mcp_get_code":{"code_sha256":"f8f9c3b9fc2b97e9"}},{"arxiv_id":"2303.16634","paper":"/paper/gpteval-nlg-evaluation-using-gpt-4-with","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","date":"2023-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlpyang/geval","path":"meta_eval_summeval.py","file_url":"https://github.com/nlpyang/geval/blob/HEAD/meta_eval_summeval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f8f9c3b9fc2b97e9","mcp_get_code":{"code_sha256":"f8f9c3b9fc2b97e9"}}]}