{"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":"/paper/tabrepo-a-large-scale-repository-of-tabular","title":"TabRepo: A Large Scale Repository of Tabular Model Evaluations and its AutoML Applications","arxiv_id":"2311.02971","date":"2023-11-06","proceeding":null,"authors":["David Salinas","Nick Erickson"],"abstract":"We introduce TabRepo, a new dataset of tabular model evaluations and predictions. TabRepo contains the predictions and metrics of 1310 models evaluated on 200 classification and regression datasets. We illustrate the benefit of our dataset in multiple ways. First, we show that it allows to perform analysis such as comparing Hyperparameter Optimization against current AutoML systems while also considering ensembling at marginal cost by using precomputed model predictions. Second, we show that our dataset can be readily leveraged to perform transfer-learning. In particular, we show that applying standard transfer-learning techniques allows to outperform current state-of-the-art tabular systems in accuracy, runtime and latency.","url_abs":"https://arxiv.org/abs/2311.02971v3","url_pdf":"https://arxiv.org/pdf/2311.02971v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tabrepo-a-large-scale-repository-of-tabular","repo_url":"https://github.com/autogluon/autogluon","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"tabrepo-a-large-scale-repository-of-tabular","repo_url":"https://github.com/autogluon/tabrepo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"tabrepo-a-large-scale-repository-of-tabular","repo_url":"https://github.com/awslabs/autogluon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2311.02971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02971"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/autogluon/tabrepo","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/awslabs/autogluon","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/autogluon/autogluon","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":8},"by_repo_kind":{"listed":{"samples":8,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2607590bf0e7883b","entry":"bin_column","repo":"awslabs/autogluon","repo_kind":"listed","path":"features/src/autogluon/features/binning.py","file_url":"https://github.com/awslabs/autogluon/blob/HEAD/features/src/autogluon/features/binning.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2607590bf0e7883b"}},{"code_sha256_prefix":"0cce82f5a2c83f58","entry":"clip_and_astype","repo":"awslabs/autogluon","repo_kind":"listed","path":"features/src/autogluon/features/utils.py","file_url":"https://github.com/awslabs/autogluon/blob/HEAD/features/src/autogluon/features/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0cce82f5a2c83f58"}},{"code_sha256_prefix":"e5c9afc2fef8368c","entry":"generate_bins","repo":"awslabs/autogluon","repo_kind":"listed","path":"features/src/autogluon/features/binning.py","file_url":"https://github.com/awslabs/autogluon/blob/HEAD/features/src/autogluon/features/binning.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e5c9afc2fef8368c"}},{"code_sha256_prefix":"9ab1251987476bd3","entry":"get_bins","repo":"awslabs/autogluon","repo_kind":"listed","path":"features/src/autogluon/features/binning.py","file_url":"https://github.com/awslabs/autogluon/blob/HEAD/features/src/autogluon/features/binning.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9ab1251987476bd3"}},{"code_sha256_prefix":"9614ea507fa59bf0","entry":"get_ngram_freq","repo":"awslabs/autogluon","repo_kind":"listed","path":"features/src/autogluon/features/vectorizers.py","file_url":"https://github.com/awslabs/autogluon/blob/HEAD/features/src/autogluon/features/vectorizers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9614ea507fa59bf0"}},{"code_sha256_prefix":"7043d0d583fd5160","entry":"get_smallest_valid_dtype_int","repo":"awslabs/autogluon","repo_kind":"listed","path":"features/src/autogluon/features/utils.py","file_url":"https://github.com/awslabs/autogluon/blob/HEAD/features/src/autogluon/features/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7043d0d583fd5160"}},{"code_sha256_prefix":"b38bf754376eaa21","entry":"is_useless_feature","repo":"awslabs/autogluon","repo_kind":"listed","path":"features/src/autogluon/features/utils.py","file_url":"https://github.com/awslabs/autogluon/blob/HEAD/features/src/autogluon/features/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b38bf754376eaa21"}},{"code_sha256_prefix":"da258afb34969824","entry":"update_version","repo":"awslabs/autogluon","repo_kind":"listed","path":"core/src/autogluon/core/_setup_utils.py","file_url":"https://github.com/awslabs/autogluon/blob/HEAD/core/src/autogluon/core/_setup_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"da258afb34969824"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}