{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003026938,0.001367856,0.000960578,0.005364683,0.000584617,0.001783662,0.002194548,0.002022181,0.005214181],"category_scores_gemma":[0.0136146,0.0005048287,0.001717507,0.004632961,0.0005690695,0.004206866,0.002200829,0.002652695,0.004141523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001079243,"about_ca_system_score_gemma":0.002394577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003173389,"about_ca_topic_score_gemma":0.007797683,"domain_scores_codex":[0.9986608,0.0003650378,0.0001315881,0.0003397342,0.0004097391,0.00009308541],"domain_scores_gemma":[0.9961552,0.001800874,0.0002857361,0.0009400296,0.0006752562,0.0001429904],"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":[0.0006338145,0.0004544412,0.005316872,0.0009042165,0.0004779043,0.0002009544,0.000314742,0.0432754,0.01635999,0.0106658,0.08780849,0.8335875],"study_design_scores_gemma":[0.0002786883,0.0003465882,0.002408595,0.0001418383,0.0001967431,0.0004183659,0.0001818772,0.8844447,0.02618946,0.03893186,0.04634694,0.000114238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02538427,0.002870726,0.923341,0.001223366,0.0003869327,0.000353614,0.008256529,0.03526843,0.002915117],"genre_scores_gemma":[0.2123989,0.001886882,0.7351133,0.0009254631,0.0004412484,0.0009884036,0.03855865,0.001818554,0.007868676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005364683,"threshold_uncertainty_score":0.01744318,"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."}}