{"id":"W6969375112","doi":"10.5281/zenodo.7998351","title":"Known Items and Narrow Topics: What Queries Say About Data Search Strategies","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Public Safety Research and Treatment","funders":"","keywords":"Exploratory search; Semantic search; Identifier; Search engine; Phrase search; Search analytics; Keyword search; Web search query","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":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002274642,0.00008559394,0.0001190548,0.0002076973,0.003315354,0.003182182,0.0009506755,0.00004916863,0.005204078],"category_scores_gemma":[0.0006986929,0.00008668748,0.0000271345,0.0009920596,0.0003995629,0.001251895,0.001280112,0.0001564052,0.001741368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004761977,"about_ca_system_score_gemma":0.00001858357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000272965,"about_ca_topic_score_gemma":0.00002934462,"domain_scores_codex":[0.9978701,0.0007953247,0.0001685175,0.0003709952,0.0004864225,0.0003086519],"domain_scores_gemma":[0.9989707,0.0001126478,0.00004611744,0.0003459795,0.0003783691,0.0001461174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001789369,0.00003728784,0.0000214051,0.00004706314,0.00005037568,0.00000965758,0.02056543,0.0001759736,0.0002557821,0.09498143,0.09269308,0.7911446],"study_design_scores_gemma":[0.0001044946,0.00003917447,0.001358495,0.00001844243,0.000008789838,0.000003264387,0.01955199,0.001563168,0.00001304572,0.002827244,0.9744067,0.0001052042],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2174095,0.004098735,0.01122028,0.05083921,0.001091707,0.00151497,0.0005027507,0.004919879,0.7084029],"genre_scores_gemma":[0.9385766,0.00810255,0.001836628,0.0003348449,0.001902801,1.570926e-7,0.006291021,0.00114835,0.04180708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8817136,"threshold_uncertainty_score":0.9990359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1267412096778616,"score_gpt":0.371176084487303,"score_spread":0.2444348748094414,"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."}}