{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.004061518,0.0002951388,0.0004972107,0.0007474665,0.000234182,0.001188816,0.004639508,0.0001404304,0.00003134374],"category_scores_gemma":[0.0003120071,0.0002275985,0.0001778029,0.002101324,0.0003501082,0.001417686,0.01256946,0.0007157535,0.0001564116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001954203,"about_ca_system_score_gemma":0.000316221,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003081363,"about_ca_topic_score_gemma":0.02686152,"domain_scores_codex":[0.9962901,0.0004114194,0.0007591414,0.00166452,0.0004955184,0.0003792893],"domain_scores_gemma":[0.9933464,0.001919156,0.0005042538,0.004042202,0.00009641857,0.00009160405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009046879,0.0001364905,0.009453174,0.0001381823,0.0001616605,0.000126269,0.0001729529,0.01213799,0.000007921814,0.9613453,0.01445715,0.001772406],"study_design_scores_gemma":[0.000635302,0.00005249463,0.02176094,0.0003723054,0.0004390595,0.000002158955,0.006760708,0.03418957,0.00002023446,0.8448451,0.090073,0.0008491112],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6371059,0.0008436034,0.253215,0.002387882,0.005098517,0.003236562,0.007983371,0.0002822526,0.08984692],"genre_scores_gemma":[0.9639369,0.001048167,0.00004777382,0.00004008587,0.0001630433,0.000006599835,0.0004579195,0.00001954834,0.03427994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.326831,"threshold_uncertainty_score":0.9998481,"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."}}