{"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/data-preprocessing","entry":"data_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":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":5,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":4},"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":"2608.11285","paper":"/paper/arxiv-2608-11285","title":"SegPAR: Class-Centric Decision-Based Sparse Attack for Semantic Segmentation","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"KAU-QuantumAILab/SegPAR","path":"function.py","file_url":"https://github.com/KAU-QuantumAILab/SegPAR/blob/HEAD/function.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0c145c9918da38ed","mcp_get_code":{"code_sha256":"0c145c9918da38ed"}},{"arxiv_id":"2606.23739","paper":"/paper/arxiv-2606-23739","title":"Systematic Exploration of 4-Expert Heterogeneous Mixture-of-Experts via Automated Pipeline Search","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"ABrain-One/nn-gpt","path":"ab/gpt/act/AccPredictor.py","file_url":"https://github.com/ABrain-One/nn-gpt/blob/HEAD/ab/gpt/act/AccPredictor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c835268f24f02d57","mcp_get_code":{"code_sha256":"c835268f24f02d57"}},{"arxiv_id":"2601.08517","paper":"/paper/arxiv-2601-08517","title":"Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"ABrain-One/NN-GPT","path":"ab/gpt/act/AccPredictor.py","file_url":"https://github.com/ABrain-One/NN-GPT/blob/HEAD/ab/gpt/act/AccPredictor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c835268f24f02d57","mcp_get_code":{"code_sha256":"c835268f24f02d57"}},{"arxiv_id":"2206.06602","paper":"/paper/deep-isolation-forest-for-anomaly-detection","title":"Deep Isolation Forest for Anomaly Detection","date":"2022-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xuhongzuo/deep-iforest","path":"utils.py","file_url":"https://github.com/xuhongzuo/deep-iforest/blob/HEAD/utils.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":"9eb090ee2b6ed905","mcp_get_code":{"code_sha256":"9eb090ee2b6ed905"}},{"arxiv_id":"1906.06532","paper":"/paper/attributed-graph-clustering-a-deep","title":"Attributed Graph Clustering: A Deep Attentional Embedding Approach","date":"2019-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Tiger101010/DAEGC","path":"DAEGC/utils.py","file_url":"https://github.com/Tiger101010/DAEGC/blob/HEAD/DAEGC/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"95dd16f7e992d4ef","mcp_get_code":{"code_sha256":"95dd16f7e992d4ef"}},{"arxiv_id":"1812.04960","paper":"/paper/object-centric-auto-encoders-and-dummy","title":"Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video","date":"2018-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fjchange/object_centric_VAD","path":"utils/util.py","file_url":"https://github.com/fjchange/object_centric_VAD/blob/HEAD/utils/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b4a21234a5f5f5c3","mcp_get_code":{"code_sha256":"b4a21234a5f5f5c3"}}]}