{"id":"W3031973162","doi":"","title":"NLP Scholar: A Dataset for Examining the State of NLP Research.","year":2020,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Metadata; Artificial intelligence; Information retrieval; Natural language processing; Citation; Focus (optics); Named entity; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.001510847,0.00006922181,0.0001038393,0.00005261657,0.0001671874,0.0001685797,0.001738676,0.00002597953,0.000009670384],"category_scores_gemma":[0.00101816,0.00004651037,0.00002119961,0.0004641841,0.00008795068,0.000421663,0.0006652502,0.0003747911,0.000008478799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000144429,"about_ca_system_score_gemma":0.00007900238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009782477,"about_ca_topic_score_gemma":0.000002144585,"domain_scores_codex":[0.9988376,0.0001292392,0.0001543851,0.0002716051,0.0003642106,0.000242918],"domain_scores_gemma":[0.9988607,0.0003469968,0.00006669774,0.0005008204,0.0001591349,0.00006567427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005847159,0.00004167872,0.0000381626,0.0001902335,0.0000247798,0.00002355149,0.005708279,0.000005418151,0.2523847,0.03033499,0.2147087,0.496481],"study_design_scores_gemma":[0.0005223992,0.0007464276,0.00008670887,0.000133384,0.00000959132,0.00001133249,0.0001567956,0.04400227,0.3963352,0.4087697,0.1489101,0.0003161357],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01532787,0.001575825,0.9607942,0.01916287,0.0001359979,0.000985143,0.0007201203,0.0004911458,0.0008068666],"genre_scores_gemma":[0.3727126,0.000009297158,0.6261878,0.0009175316,0.00004863987,0.00003413212,0.0000403065,0.000008730183,0.00004095097],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4961649,"threshold_uncertainty_score":0.3230921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1219329346152474,"score_gpt":0.3756270129000298,"score_spread":0.2536940782847824,"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."}}