{"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/load-and-preprocess-data","entry":"load_and_preprocess_data","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":6,"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":6,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":5},"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":"2605.02954","paper":"/paper/arxiv-2605-02954","title":"EFGPP: Exploratory framework for genotype-phenotype prediction","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"MuhammadMuneeb007/EFGPP","path":"Step12-Combinations.py","file_url":"https://github.com/MuhammadMuneeb007/EFGPP/blob/HEAD/Step12-Combinations.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"036ed9fb720a189c","mcp_get_code":{"code_sha256":"036ed9fb720a189c"}},{"arxiv_id":"2501.16226","paper":"/paper/the-effect-of-optimal-self-distillation-in","title":"The Effect of Optimal Self-Distillation in Noisy Gaussian Mixture Model","date":"2025-01-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taka255/self-distillation-analysis","path":"Experiments/linear_probe.py","file_url":"https://github.com/taka255/self-distillation-analysis/blob/HEAD/Experiments/linear_probe.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f4a73fc8ae705839","mcp_get_code":{"code_sha256":"f4a73fc8ae705839"}},{"arxiv_id":"2411.02023","paper":"/paper/optimal-classification-under-performative","title":"Optimal Classification under Performative Distribution Shift","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"totilas/PerfOpti","path":"creditdatasetpreprocess.py","file_url":"https://github.com/totilas/PerfOpti/blob/HEAD/creditdatasetpreprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d0969caf164d114","mcp_get_code":{"code_sha256":"0d0969caf164d114"}},{"arxiv_id":"2310.19727","paper":"/paper/generating-medical-instructions-with","title":"Generating Medical Prescriptions with Conditional Transformer","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HECTA-UoM/Label-To-Text-Transformer","path":"Modules/DataHelp.py","file_url":"https://github.com/HECTA-UoM/Label-To-Text-Transformer/blob/HEAD/Modules/DataHelp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"84eaec28aee89722","mcp_get_code":{"code_sha256":"84eaec28aee89722"}},{"arxiv_id":"2304.04507","paper":"/paper/hist2rna-an-efficient-deep-learning","title":"hist2RNA: An efficient deep learning architecture to predict gene expression from breast cancer histopathology images","date":"2023-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raktim-mondol/hist2rna","path":"generate_box_plot_and_AUC-RCH.py","file_url":"https://github.com/raktim-mondol/hist2rna/blob/HEAD/generate_box_plot_and_AUC-RCH.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a2383ddb66fe348","mcp_get_code":{"code_sha256":"9a2383ddb66fe348"}},{"arxiv_id":"2006.09043","paper":"/paper/improved-deep-point-cloud-geometry","title":"Improved Deep Point Cloud Geometry Compression","date":"2020-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pmclSF/DeepCompress","path":"src/cli_train.py","file_url":"https://github.com/pmclSF/DeepCompress/blob/HEAD/src/cli_train.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29c977decc3bde78","mcp_get_code":{"code_sha256":"29c977decc3bde78"}}]}