{"id":"W4415532898","doi":"10.1093/icc/dtaf044","title":"How small is big enough? Open labeled datasets and the development of deep learning","year":2025,"lang":"en","type":"article","venue":"Industrial and Corporate Change","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Canadian Institute for Advanced Research","keywords":"Deep learning; Function (biology); Citation; Object (grammar); Key (lock); Development (topology)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007521618,0.00009875265,0.0001760891,0.00006484471,0.0002433771,0.0004206763,0.0005689501,0.00007339683,0.000002454203],"category_scores_gemma":[0.0001099856,0.00006627385,0.0000102301,0.0003284886,0.00007842986,0.0001738865,0.0008213602,0.0002085633,0.000001429545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009056748,"about_ca_system_score_gemma":0.0000709184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000208292,"about_ca_topic_score_gemma":0.000169854,"domain_scores_codex":[0.9991724,0.0001733573,0.0001719782,0.0002717589,0.00009180127,0.000118715],"domain_scores_gemma":[0.9992836,0.0001091377,0.000262862,0.0002631596,0.00004062785,0.00004063203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000597316,0.00001700653,0.00256932,0.00001394258,0.00002152992,0.000001019362,0.001505561,2.992323e-7,0.0001102389,0.01212944,0.0003323753,0.9832395],"study_design_scores_gemma":[0.01316897,0.0002504288,0.02301133,0.0003087819,0.00008717967,0.00001086897,0.001584898,0.02404392,0.004896779,0.004744591,0.9272273,0.0006649391],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7303148,0.005586747,0.1390483,0.113692,0.001961848,0.004592586,0.0002177307,0.0003063746,0.004279644],"genre_scores_gemma":[0.9936946,0.0001916021,0.00375016,0.0005797732,0.0001580481,0.0000997162,0.000248468,0.000006613637,0.001271003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9825746,"threshold_uncertainty_score":0.4056591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2451403693709484,"score_gpt":0.2879666968852078,"score_spread":0.04282632751425935,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}