{"id":"W4385571931","doi":"10.18653/v1/2023.acl-short.46","title":"MIReAD: Simple Method for Learning High-quality Representations from Scientific Documents","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Categorization; Simple (philosophy); Representation (politics); Transformer; Information retrieval; Class (philosophy); Quality (philosophy); Artificial intelligence; Scientific literature; Language model; Natural language processing","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001238802,0.00008343106,0.0001295607,0.0001244213,0.0004298689,0.000482731,0.0006034609,0.00003703128,0.00008046648],"category_scores_gemma":[0.0003196636,0.0000795589,0.00006750872,0.0005946658,0.00002034511,0.0004683943,0.0003600155,0.00007926276,0.0001724685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002852848,"about_ca_system_score_gemma":0.00004682298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002514158,"about_ca_topic_score_gemma":0.0001233829,"domain_scores_codex":[0.9983345,0.0001580612,0.0002747509,0.0006453721,0.000305356,0.0002819933],"domain_scores_gemma":[0.9983288,0.0007529449,0.00007636386,0.0006727156,0.00009505964,0.00007410813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001078471,0.0000814315,0.008507916,0.00003865551,0.0001005169,0.000008211961,0.005493135,0.05011532,0.03531127,0.61014,0.02965647,0.2605363],"study_design_scores_gemma":[0.0003771891,0.00001236211,0.005390798,0.000004726118,0.00000627368,3.310767e-7,0.0002480448,0.747161,0.006864151,0.2272009,0.01257418,0.0001601347],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07405308,0.000005542534,0.9225379,0.001346854,0.000607615,0.0001952503,0.000008932515,0.0005443277,0.0007005437],"genre_scores_gemma":[0.2405007,9.186587e-7,0.7463496,0.000117939,0.00006935337,0.00006086134,0.00008937923,0.000008208147,0.01280305],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6970456,"threshold_uncertainty_score":0.4654986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1047302121233201,"score_gpt":0.4317125563418593,"score_spread":0.3269823442185392,"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."}}