{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4443332,0.002405703,0.004070159,0.01594495,0.008088636,0.03768529,0.009397742,0.01716395,0.005826397],"category_scores_gemma":[0.6688346,0.002919219,0.003267862,0.02407745,0.03342992,0.07325903,0.02152779,0.03277919,0.004272322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008956787,"about_ca_system_score_gemma":0.03215597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00399683,"about_ca_topic_score_gemma":0.002960807,"domain_scores_codex":[0.604546,0.282538,0.04243176,0.01332964,0.05395398,0.003200635],"domain_scores_gemma":[0.1819879,0.6259692,0.03656094,0.07859792,0.07081633,0.006067723],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002292661,0.0001200236,0.003176385,0.00133792,0.00007694487,0.0001477227,0.003967052,0.002378141,0.0003914054,0.8617699,0.05552477,0.07088062],"study_design_scores_gemma":[0.0001088385,0.00009125259,0.0005730687,0.003085067,0.00003877255,0.0001375603,0.00239775,0.009284213,0.0008814851,0.8529316,0.1303267,0.0001437949],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003764737,0.003295165,0.8015593,0.1730644,0.003013591,0.001497477,0.003434782,0.0009451883,0.009425396],"genre_scores_gemma":[0.06475701,0.003105255,0.8833661,0.03233742,0.003521182,0.005506236,0.004717309,0.0007203915,0.001969124],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5556668,"threshold_uncertainty_score":0.6852361,"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."}}