{"id":"W4405035632","doi":"10.48550/arxiv.2412.01953","title":"The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Mental Health; Bundesministerium für Bildung und Forschung; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Data science; Data discovery; Computer science; Geography; World Wide Web","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2246197,0.001804438,0.00332275,0.01790327,0.003469297,0.01531072,0.006759512,0.006528899,0.003950436],"category_scores_gemma":[0.6141172,0.001700236,0.002912482,0.0186705,0.0194432,0.02527962,0.008126573,0.0101549,0.0007205994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007908661,"about_ca_system_score_gemma":0.0109153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004846433,"about_ca_topic_score_gemma":0.004306859,"domain_scores_codex":[0.7947943,0.1571871,0.009669592,0.01231366,0.02512004,0.0009153484],"domain_scores_gemma":[0.1498893,0.7977309,0.01382643,0.02385672,0.01349445,0.001202356],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0003626914,0.0001378766,0.02712983,0.01350225,0.001876827,0.0003753224,0.001732178,0.03490778,0.0005098143,0.5876802,0.01822281,0.3135624],"study_design_scores_gemma":[0.00006198779,0.00008468977,0.0025892,0.003798621,0.0002796716,0.0002177297,0.0003912072,0.0328779,0.0006891481,0.9314092,0.02752804,0.00007251884],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01472056,0.1095988,0.7820126,0.07925016,0.0007239272,0.0004571836,0.003839681,0.0008532977,0.008543816],"genre_scores_gemma":[0.4156599,0.05088757,0.5108366,0.01256633,0.00233604,0.00155993,0.004883274,0.0005302805,0.0007400459],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.7753803,"threshold_uncertainty_score":0.9561819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.281484289759273,"score_gpt":0.3330710474130075,"score_spread":0.05158675765373455,"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."}}