{"id":"W3210704534","doi":"10.20944/preprints202110.0382.v1","title":"Employing Statistical Machine Reading for Inferring Key Concepts of a Research Field From a Body of Abstracts and Blog Posts","year":2021,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reading (process); Field (mathematics); Data science; Function (biology); Computer science; Comprehension; Conversation; Key (lock); Management science; Political science; Psychology; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.01974844,0.001614606,0.001074209,0.03631767,0.001677253,0.006831852,0.001583601,0.001740337,0.004063988],"category_scores_gemma":[0.1445736,0.0005440934,0.00140259,0.01795638,0.002225911,0.009851145,0.002732766,0.002340224,0.003751051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001566717,"about_ca_system_score_gemma":0.00342459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001900119,"about_ca_topic_score_gemma":0.004607971,"domain_scores_codex":[0.9860621,0.007223753,0.001721476,0.002351595,0.002295897,0.0003450755],"domain_scores_gemma":[0.7315613,0.2250403,0.01748846,0.01040979,0.0144703,0.001029748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007668639,0.0004239572,0.05483896,0.008539628,0.0005823614,0.0017382,0.02607822,0.004285651,0.02213232,0.02755984,0.02033992,0.832714],"study_design_scores_gemma":[0.000221657,0.001326802,0.1142234,0.005439081,0.001168668,0.002663586,0.0533655,0.1959416,0.04289888,0.4040281,0.1777383,0.0009845189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2828018,0.01290927,0.6315567,0.01216588,0.001583945,0.002122005,0.01935351,0.006097578,0.03140928],"genre_scores_gemma":[0.478803,0.004018382,0.496874,0.001196148,0.001304685,0.001605886,0.01217893,0.0003879021,0.003630973],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9636824,"threshold_uncertainty_score":0.1044409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2271925651014114,"score_gpt":0.4556321232008874,"score_spread":0.228439558099476,"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."}}