{"id":"W4386566652","doi":"10.18653/v1/2023.eacl-main.195","title":"On Evaluation of Document Classification with RVL-CDIP","year":2023,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited","keywords":"Benchmarking; Benchmark (surveying); Computer science; Scope (computer science); Resource (disambiguation); Artificial intelligence; Task (project management); Machine learning; Information retrieval; Data mining; Pattern recognition (psychology); Engineering; Business","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001145047,0.00007316966,0.00007804992,0.0001988627,0.00004027468,0.00004402665,0.0004711847,0.00003335844,0.00004162716],"category_scores_gemma":[0.00008431329,0.00005558682,0.00001669438,0.0008128086,0.00003039051,0.000367587,0.0000584835,0.00004777772,0.0001918518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008676811,"about_ca_system_score_gemma":0.00009069966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007567113,"about_ca_topic_score_gemma":0.000003455924,"domain_scores_codex":[0.9985216,0.0000931595,0.0001870233,0.0002809125,0.0007990722,0.0001181905],"domain_scores_gemma":[0.9986335,0.00008630177,0.0001286444,0.0008236055,0.0002985118,0.00002941897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006123006,0.00003733361,0.0001434472,0.000006370051,0.000007357284,2.832236e-7,0.0001005537,0.0001589658,0.006262791,0.9052433,0.009046827,0.07898664],"study_design_scores_gemma":[0.0009071353,0.000452978,0.1105717,0.00006894339,0.00002325408,0.00000317335,0.0001100607,0.5500532,0.170697,0.1643276,0.002466113,0.0003188121],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02510067,0.000004555716,0.9448231,0.002528933,0.00008941888,0.0005472607,0.000003592634,0.0009716362,0.02593086],"genre_scores_gemma":[0.9705768,0.000007303554,0.02873411,0.0001116428,0.000008394933,0.0001354965,0.00003566758,0.000005593567,0.0003849516],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9454762,"threshold_uncertainty_score":0.2465931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07528893480864146,"score_gpt":0.3406554908920777,"score_spread":0.2653665560834362,"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."}}