{"id":"W6921540341","doi":"10.7939/dvn/10485","title":"TSM Corpus - A Version","year":2015,"lang":"en","type":"dataset","venue":"Borealis","topic":"Education Methods and Technologies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Corpus linguistics; China; Computational linguistics; Text corpus","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008839381,0.000100664,0.0001586517,0.000110502,0.0002242023,0.00006485889,0.0005285291,0.0004059268,0.0002532382],"category_scores_gemma":[0.001683979,0.00009218954,0.00004779823,0.0001875287,0.0002471575,0.00005802314,0.00008016444,0.0002020033,0.00008574982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001447432,"about_ca_system_score_gemma":0.0005509692,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.37501,"about_ca_topic_score_gemma":0.08705968,"domain_scores_codex":[0.9989513,0.0001741549,0.0001154224,0.0001821938,0.0003800326,0.0001968959],"domain_scores_gemma":[0.9990893,0.0001135352,0.0001251455,0.0004307568,0.0001442687,0.00009698379],"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":[0.000001984043,0.00001904244,0.000008002378,0.000006684655,0.000005870777,0.000003616028,0.000240483,3.298294e-8,1.582262e-7,0.001449689,0.9944475,0.003816921],"study_design_scores_gemma":[0.0000504248,0.00001784622,0.000017406,0.00001669312,0.00002205903,3.872163e-7,0.001693568,5.802734e-8,0.000002624728,0.004819793,0.9932445,0.000114654],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000004786552,0.0003151844,0.000003324779,0.002015622,0.0006067762,0.0001206108,0.9829597,0.0001268056,0.0138472],"genre_scores_gemma":[8.144189e-7,0.001547077,0.0009912199,0.0001664343,0.0004029431,0.00001743409,0.9961028,0.000005501267,0.0007658326],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2879503,"threshold_uncertainty_score":0.9295991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07565520443162371,"score_gpt":0.4042287287701127,"score_spread":0.328573524338489,"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."}}