{"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/preprocessing","entry":"preprocessing","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":22,"n_papers_ran":4,"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":15,"n_samples_ran":4,"n_samples_fingerprinted":3,"n_places":23,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"unverified":11},"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":"2509.12158","paper":"/paper/arxiv-2509-12158","title":"Pun Unintended: LLMs and the Illusion of Humor Understanding","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"alezanga/punintended","path":"utils/text_processing.py","file_url":"https://github.com/alezanga/punintended/blob/HEAD/utils/text_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2e588e3310b86feb","mcp_get_code":{"code_sha256":"2e588e3310b86feb"}},{"arxiv_id":"2502.17888","paper":"/paper/rankcot-refining-knowledge-for-retrieval","title":"RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts","date":"2025-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NEUIR/RankCoT","path":"src/modelft/train_my.py","file_url":"https://github.com/NEUIR/RankCoT/blob/HEAD/src/modelft/train_my.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1124ba0a54f89363","mcp_get_code":{"code_sha256":"1124ba0a54f89363"}},{"arxiv_id":"2412.08879","paper":"/paper/video-repurposing-from-user-generated-content","title":"Video Repurposing from User Generated Content: A Large-scale Dataset and Benchmark","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yongliang-wu/repurpose","path":"dataset/RepurposeClip.py","file_url":"https://github.com/yongliang-wu/repurpose/blob/HEAD/dataset/RepurposeClip.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b5e324c2c10d0c39","mcp_get_code":{"code_sha256":"b5e324c2c10d0c39"}},{"arxiv_id":"2410.04959","paper":"/paper/failure-proof-non-contrastive-self-supervised","title":"Failure-Proof Non-Contrastive Self-Supervised Learning","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"emsansone/CPLearn","path":"main_collapses.py","file_url":"https://github.com/emsansone/CPLearn/blob/HEAD/main_collapses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"11b0a0980664894c","mcp_get_code":{"code_sha256":"11b0a0980664894c"}},{"arxiv_id":"2405.16584","paper":"/paper/mentalmanip-a-dataset-for-fine-grained","title":"MentalManip: A Dataset For Fine-grained Analysis of Mental Manipulation in Conversations","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"audreycs/MentalManip","path":"statistic_analysis/mentalManip_stats.py","file_url":"https://github.com/audreycs/MentalManip/blob/HEAD/statistic_analysis/mentalManip_stats.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"81944bfd8e89a6b9","mcp_get_code":{"code_sha256":"81944bfd8e89a6b9"}},{"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":"2ffa5ef1b40e1a7e","mcp_get_code":{"code_sha256":"2ffa5ef1b40e1a7e"}},{"arxiv_id":"2310.04678","paper":"/paper/doris-mae-scientific-document-retrieval-using","title":"DORIS-MAE: Scientific Document Retrieval using Multi-level Aspect-based Queries","date":"2023-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Real-Doris-Mae/Doris-Mae-Dataset","path":"benchmarking/model_embedding.py","file_url":"https://github.com/Real-Doris-Mae/Doris-Mae-Dataset/blob/HEAD/benchmarking/model_embedding.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"07c727c3c3526bc5","mcp_get_code":{"code_sha256":"07c727c3c3526bc5"}},{"arxiv_id":"2305.15086","paper":"/paper/unpaired-image-to-image-translation-via-1","title":"Unpaired Image-to-Image Translation via Neural Schrödinger Bridge","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alpc91/NICE-GAN-pytorch","path":"utils.py","file_url":"https://github.com/alpc91/NICE-GAN-pytorch/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eab7ba887c245523","mcp_get_code":{"code_sha256":"eab7ba887c245523"}},{"arxiv_id":"2205.01876","paper":"/paper/fairlib-a-unified-framework-for-assessing-and","title":"fairlib: A Unified Framework for Assessing and Improving Classification Fairness","date":"2022-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HanXudong/fairlib","path":"fairlib/datasets/Adult/Adult.py","file_url":"https://github.com/HanXudong/fairlib/blob/HEAD/fairlib/datasets/Adult/Adult.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":"bf5f54a02e90d15f","mcp_get_code":{"code_sha256":"bf5f54a02e90d15f"}},{"arxiv_id":"2205.01876","paper":"/paper/fairlib-a-unified-framework-for-assessing-and","title":"fairlib: A Unified Framework for Assessing and Improving Classification Fairness","date":"2022-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HanXudong/fairlib","path":"fairlib/datasets/COMPAS/COMPAS.py","file_url":"https://github.com/HanXudong/fairlib/blob/HEAD/fairlib/datasets/COMPAS/COMPAS.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":"a44cb9421db7cccc","mcp_get_code":{"code_sha256":"a44cb9421db7cccc"}},{"arxiv_id":"2006.06676","paper":"/paper/training-generative-adversarial-networks-with-2","title":"Training Generative Adversarial Networks with Limited Data","date":"2020-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sangyun884/Face2Webtoon","path":"utils.py","file_url":"https://github.com/sangyun884/Face2Webtoon/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eab7ba887c245523","mcp_get_code":{"code_sha256":"eab7ba887c245523"}},{"arxiv_id":"2006.02286","paper":"/paper/learning-kernel-tests-without-data-splitting","title":"Learning Kernel Tests Without Data Splitting","date":"2020-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MPI-IS/tests-wo-splitting","path":"tests_wo_split/methods/wald.py","file_url":"https://github.com/MPI-IS/tests-wo-splitting/blob/HEAD/tests_wo_split/methods/wald.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f1baa9637253a70c","mcp_get_code":{"code_sha256":"f1baa9637253a70c"}},{"arxiv_id":"1907.10830","paper":"/paper/u-gat-it-unsupervised-generative-attentional","title":"U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation","date":"2019-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"znxlwm/UGATIT-pytorch","path":"utils.py","file_url":"https://github.com/znxlwm/UGATIT-pytorch/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eab7ba887c245523","mcp_get_code":{"code_sha256":"eab7ba887c245523"}},{"arxiv_id":"1905.01723","paper":"/paper/few-shot-unsupervised-image-to-image","title":"Few-Shot Unsupervised Image-to-Image Translation","date":"2019-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/FUNIT-Tensorflow","path":"utils.py","file_url":"https://github.com/taki0112/FUNIT-Tensorflow/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eab7ba887c245523","mcp_get_code":{"code_sha256":"eab7ba887c245523"}},{"arxiv_id":"1905.01270","paper":"/paper/drit-diverse-image-to-image-translation-via","title":"DRIT++: Diverse Image-to-Image Translation via Disentangled Representations","date":"2019-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/DRIT-Tensorflow","path":"utils.py","file_url":"https://github.com/taki0112/DRIT-Tensorflow/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eab7ba887c245523","mcp_get_code":{"code_sha256":"eab7ba887c245523"}},{"arxiv_id":"1904.05342","paper":"/paper/clinicalbert-modeling-clinical-notes-and","title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","date":"2019-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kexinhuang12345/clinicalBERT","path":"preprocess.py","file_url":"https://github.com/kexinhuang12345/clinicalBERT/blob/HEAD/preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c31eb3b60757c5f","mcp_get_code":{"code_sha256":"5c31eb3b60757c5f"}},{"arxiv_id":"1903.07291","paper":"/paper/semantic-image-synthesis-with-spatially","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","date":"2019-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/SPADE-Tensorflow","path":"utils.py","file_url":"https://github.com/taki0112/SPADE-Tensorflow/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eab7ba887c245523","mcp_get_code":{"code_sha256":"eab7ba887c245523"}},{"arxiv_id":"1812.09912","paper":"/paper/image-to-image-translation-via-group-wise","title":"Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation","date":"2018-12-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/GDWCT-Tensorflow","path":"utils.py","file_url":"https://github.com/taki0112/GDWCT-Tensorflow/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eab7ba887c245523","mcp_get_code":{"code_sha256":"eab7ba887c245523"}},{"arxiv_id":"1809.11096","paper":"/paper/large-scale-gan-training-for-high-fidelity","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","date":"2018-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/BigGAN-Tensorflow","path":"utils.py","file_url":"https://github.com/taki0112/BigGAN-Tensorflow/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7c108866402e9866","mcp_get_code":{"code_sha256":"7c108866402e9866"}},{"arxiv_id":"1804.04732","paper":"/paper/multimodal-unsupervised-image-to-image","title":"Multimodal Unsupervised Image-to-Image Translation","date":"2018-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/MUNIT-Tensorflow","path":"utils.py","file_url":"https://github.com/taki0112/MUNIT-Tensorflow/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eab7ba887c245523","mcp_get_code":{"code_sha256":"eab7ba887c245523"}},{"arxiv_id":"1703.06868","paper":"/paper/arbitrary-style-transfer-in-real-time-with","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","date":"2017-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JeongsolKim/BiS400_term_project","path":"StyleTransfer.py","file_url":"https://github.com/JeongsolKim/BiS400_term_project/blob/HEAD/StyleTransfer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"994ad288a2dff0d9","mcp_get_code":{"code_sha256":"994ad288a2dff0d9"}},{"arxiv_id":"1703.00848","paper":"/paper/unsupervised-image-to-image-translation","title":"Unsupervised Image-to-Image Translation Networks","date":"2017-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taki0112/UNIT-Tensorflow","path":"DatasetAPI/utils.py","file_url":"https://github.com/taki0112/UNIT-Tensorflow/blob/HEAD/DatasetAPI/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eab7ba887c245523","mcp_get_code":{"code_sha256":"eab7ba887c245523"}},{"arxiv_id":"1612.02297","paper":"/paper/spatially-adaptive-computation-time-for","title":"Spatially Adaptive Computation Time for Residual Networks","date":"2016-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mfigurnov/sact","path":"imagenet_ponder_map.py","file_url":"https://github.com/mfigurnov/sact/blob/HEAD/imagenet_ponder_map.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"4219e649c9a3608a","mcp_get_code":{"code_sha256":"4219e649c9a3608a"}}]}