{"id":"W4393626689","doi":"10.5281/zenodo.3381673","title":"Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval","year":2019,"lang":"en","type":"dataset","venue":"Figshare","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Information retrieval; Sentence; Computer science; Domain (mathematical analysis); Natural language processing; Artificial intelligence; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003470471,0.002537994,0.001230384,0.002372223,0.0008767672,0.001918651,0.002935594,0.002227176,0.03433885],"category_scores_gemma":[0.0141953,0.0007811289,0.002938905,0.002208271,0.0005430999,0.00238779,0.001692256,0.003667069,0.04550572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001544528,"about_ca_system_score_gemma":0.001520209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01174358,"about_ca_topic_score_gemma":0.01933041,"domain_scores_codex":[0.9987473,0.0004601199,0.00009456345,0.0004000623,0.0002003339,0.00009757703],"domain_scores_gemma":[0.9952747,0.002332271,0.0001505871,0.001349068,0.0007015562,0.000191867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001022224,0.0004294296,0.005006846,0.001322199,0.0003933153,0.0001550464,0.0000615757,0.02131996,0.001718707,0.001745782,0.9056665,0.06115843],"study_design_scores_gemma":[0.002087182,0.001210745,0.03277162,0.0009455301,0.001034156,0.001275369,0.0003668563,0.5011376,0.01983944,0.03248899,0.4065023,0.0003403463],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.03091795,0.002883287,0.03707089,0.001976572,0.001167426,0.0006034305,0.8907994,0.02486539,0.009715647],"genre_scores_gemma":[0.03245374,0.0004402584,0.0171374,0.0002748608,0.0001098328,0.0004431384,0.9429979,0.0007004814,0.00544242],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03433885,"threshold_uncertainty_score":0.114875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2650748796003983,"score_gpt":0.382171404372805,"score_spread":0.1170965247724067,"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."}}