{"id":"W3003312070","doi":"10.22148/001c.11830","title":"Is there a text in my data? (Part 1): on counting words","year":2020,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Word (group theory); Context (archaeology); Simple (philosophy); Normalization (sociology); Natural language processing; Linguistics; Artificial intelligence; Epistemology; Philosophy; History; Sociology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002279573,0.0001320379,0.0002643903,0.00005338736,0.0001150121,0.0008091169,0.0004649202,0.00002998701,0.001538605],"category_scores_gemma":[0.0001086192,0.00008300057,0.000116892,0.00005997915,0.00008657794,0.001228034,0.00007386616,0.0004003607,0.00007494389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003475662,"about_ca_system_score_gemma":0.0000336841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001862996,"about_ca_topic_score_gemma":0.000232279,"domain_scores_codex":[0.998819,0.00002297844,0.000488814,0.000121465,0.0003703984,0.0001773593],"domain_scores_gemma":[0.9992285,0.00004944014,0.0002890542,0.0001331818,0.0002031771,0.00009667697],"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":[0.000446134,0.0004086852,0.004339511,0.000190846,0.0005112353,0.000537821,0.1778997,0.0003458996,0.00003222658,0.1404863,0.6666762,0.008125448],"study_design_scores_gemma":[0.0003806475,0.0002552917,0.0002331983,0.0001785786,0.00004650369,0.00001046407,0.02903624,0.0005623952,0.00001232677,0.0007920451,0.9683377,0.0001546495],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7872122,0.0006551065,0.000002539022,0.008581355,0.000532428,0.00006959635,0.0001127927,0.00001681514,0.2028172],"genre_scores_gemma":[0.9867961,0.00007943761,0.00001646208,0.003920354,0.0023294,1.989743e-7,0.00001165646,0.0000108827,0.006835485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3016614,"threshold_uncertainty_score":0.9993742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1950699218308501,"score_gpt":0.292525711556765,"score_spread":0.09745578972591484,"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."}}