{"id":"W2753703079","doi":"10.1186/s12961-017-0242-4","title":"The SPARK Tool to prioritise questions for systematic reviews in health policy and systems research: development and initial validation","year":2017,"lang":"en","type":"article","venue":"Health Research Policy and Systems","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University Medical Centre; McMaster University","funders":"Alliance for Health Policy and Systems Research; World Health Organization","keywords":"Systematic review; Scope (computer science); SPARK (programming language); Health services research; Process management; Benchmarking; Computer science; Medicine; Management science; MEDLINE; Public health; Political science; Engineering; Nursing; Business","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1682221,0.0002797185,0.001145033,0.001576648,0.01927759,0.001001304,0.0006302733,0.0002021767,0.000001577261],"category_scores_gemma":[0.1137484,0.0002056722,0.00002946903,0.001069594,0.0005426725,0.0004678658,0.0006013609,0.00114526,0.00006635398],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003048841,"about_ca_system_score_gemma":0.01619747,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.09992566,"about_ca_topic_score_gemma":0.01271913,"domain_scores_codex":[0.9611446,0.02842201,0.004038213,0.0008598168,0.001837462,0.003697894],"domain_scores_gemma":[0.9702016,0.02338687,0.001377398,0.001324743,0.001514711,0.002194657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001727993,0.00006691308,0.003837871,0.3238322,0.00002720116,0.000005413101,0.0946217,0.000006989723,0.00002475296,0.5133417,0.03875995,0.0253026],"study_design_scores_gemma":[0.001982424,0.000725774,0.01849316,0.04885081,0.000002313294,0.00003947811,0.01879231,0.001015326,0.00000230806,0.00123549,0.9085336,0.000327029],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1918092,0.02011274,0.001554361,0.6277,0.001935383,0.153461,0.0006525393,0.0001657757,0.002609089],"genre_scores_gemma":[0.9179173,0.01867442,0.000904565,0.007727863,0.003794851,0.04392054,0.00002334825,0.0001012778,0.006935876],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8697736,"threshold_uncertainty_score":0.9893798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.937649951510094,"score_gpt":0.7843373099113006,"score_spread":0.1533126415987934,"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."}}