{"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/get-category-sizes","entry":"get_category_sizes","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":0,"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":4,"n_samples_ran":0,"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":0,"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":"2601.22816","paper":"/paper/arxiv-2601-22816","title":"Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"yandex-research/tab-ddpm","path":"lib/data.py","file_url":"https://github.com/yandex-research/tab-ddpm/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4d744cd924d61d6f","mcp_get_code":{"code_sha256":"4d744cd924d61d6f"}},{"arxiv_id":"2410.20626","paper":"/paper/tabdiff-a-multi-modal-diffusion-model-for","title":"TabDiff: a Multi-Modal Diffusion Model for Tabular Data Generation","date":"2024-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minkaixu/tabdiff","path":"src/data.py","file_url":"https://github.com/minkaixu/tabdiff/blob/HEAD/src/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4d744cd924d61d6f","mcp_get_code":{"code_sha256":"4d744cd924d61d6f"}},{"arxiv_id":"2310.04668","paper":"/paper/label-free-node-classification-on-graphs-with","title":"Label-free Node Classification on Graphs with Large Language Models (LLMS)","date":"2023-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pmernyei/wiki-cs-dataset","path":"data_processing/pyscripts/inspect_milestone_tree.py","file_url":"https://github.com/pmernyei/wiki-cs-dataset/blob/HEAD/data_processing/pyscripts/inspect_milestone_tree.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d905d3619fb5a98","mcp_get_code":{"code_sha256":"7d905d3619fb5a98"}},{"arxiv_id":"2211.16887","paper":"/paper/t2g-former-organizing-tabular-features-into","title":"T2G-Former: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction","date":"2022-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jyansir/t2g-former","path":"lib/data.py","file_url":"https://github.com/jyansir/t2g-former/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"556fd303cef00ac0","mcp_get_code":{"code_sha256":"556fd303cef00ac0"}},{"arxiv_id":"2209.15421","paper":"/paper/tabddpm-modelling-tabular-data-with-diffusion","title":"TabDDPM: Modelling Tabular Data with Diffusion Models","date":"2022-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rotot0/tab-ddpm","path":"lib/data.py","file_url":"https://github.com/rotot0/tab-ddpm/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4d744cd924d61d6f","mcp_get_code":{"code_sha256":"4d744cd924d61d6f"}},{"arxiv_id":"2203.05556","paper":"/paper/on-embeddings-for-numerical-features-in","title":"On Embeddings for Numerical Features in Tabular Deep Learning","date":"2022-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yura52/tabular-dl-num-embeddings","path":"lib/data.py","file_url":"https://github.com/Yura52/tabular-dl-num-embeddings/blob/HEAD/lib/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f2a902735fdb4d9","mcp_get_code":{"code_sha256":"7f2a902735fdb4d9"}}]}