{"id":"W4318148079","doi":"10.1109/bigdata55660.2022.10020681","title":"Don’t Blindly Use Data: Towards a Data Statement for Computational Financial Research","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Statement (logic); Data science; Data quality; Context (archaeology); Problem statement; Focus (optics); Quality (philosophy); Work (physics); Management science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007859824,0.0003204349,0.0003086058,0.0005789054,0.001000998,0.001740532,0.03841855,0.0000776883,0.0003180532],"category_scores_gemma":[0.003013388,0.0003376369,0.00002993699,0.0007330783,0.0001659673,0.00485014,0.03782948,0.001138848,0.000122343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002645286,"about_ca_system_score_gemma":0.002472907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001405975,"about_ca_topic_score_gemma":0.001092074,"domain_scores_codex":[0.9912679,0.0007454842,0.00084484,0.003263452,0.003270721,0.0006075887],"domain_scores_gemma":[0.9841397,0.0009281028,0.0004524404,0.01364921,0.0006305694,0.0001999977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002197829,0.000507305,0.000176139,0.00002340631,0.00009250003,0.00002819058,0.00008689985,0.0007853724,0.0001057044,0.04686062,0.6117989,0.3393151],"study_design_scores_gemma":[0.0006289837,0.0001229807,0.001008608,0.00001901942,0.00001104276,0.00001190551,0.00005829606,0.5085685,0.000005508988,0.001371167,0.4879778,0.0002162476],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0007385315,0.00004600239,0.6619424,0.01674653,0.005959207,0.0007169757,0.313174,0.0001356504,0.0005407151],"genre_scores_gemma":[0.1855578,0.0002053567,0.03264333,0.001170495,0.001720918,0.0001784737,0.777316,0.00003922691,0.001168373],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.6292991,"threshold_uncertainty_score":0.9999076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7268565196499841,"score_gpt":0.4798004812067899,"score_spread":0.2470560384431942,"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."}}