{"id":"W7133042738","doi":"","title":"Facilitating Discovery in Open Data Repositories","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Metadata; Data element; Metadata repository; Discoverability; Metadata modeling; Open data; Linked data; Schema (genetic algorithms); Data mapping","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":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.01226506,0.0005517554,0.0009798714,0.0005743342,0.0003745601,0.01533739,0.01282481,0.0002846994,0.0005603689],"category_scores_gemma":[0.01087373,0.0004844494,0.0001187114,0.002111474,0.0001540911,0.007025572,0.01434283,0.0007941271,0.001996015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001590317,"about_ca_system_score_gemma":0.0006850674,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01879052,"about_ca_topic_score_gemma":0.02238398,"domain_scores_codex":[0.9911826,0.000811926,0.001995355,0.00314731,0.002265111,0.0005976761],"domain_scores_gemma":[0.9904678,0.00296261,0.0007329277,0.005526762,0.0001703659,0.0001395006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0008209889,0.0005242408,0.0005413904,0.002283102,0.0003852788,0.0007095566,0.4202721,0.000235861,0.0003977229,0.06056494,0.3408146,0.1724502],"study_design_scores_gemma":[0.000302394,0.00007762478,0.0007908004,0.001356711,0.0001134368,0.000002452191,0.6621501,0.002539519,0.0001186447,0.01093355,0.3210015,0.0006133085],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.3853098,0.01514469,0.01081351,0.01467025,0.0529783,0.00830024,0.006035947,0.0002549403,0.5064923],"genre_scores_gemma":[0.1632651,0.0005653845,0.003347415,0.0002748118,0.0003828566,0.000125354,0.0112111,0.00006675118,0.8207612],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3142689,"threshold_uncertainty_score":0.9997607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3245608194208772,"score_gpt":0.5522434291650822,"score_spread":0.227682609744205,"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."}}