{"id":"W4323066598","doi":"10.48550/arxiv.2303.00923","title":"On the Role of Reviewer Expertise in Temporal Review Helpfulness Prediction","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Helpfulness; Scarcity; Computer science; Quality (philosophy); Data science; Value (mathematics); Psychology; Economics; Machine learning; Social psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01062744,0.001258573,0.001114894,0.006982117,0.001055194,0.002220687,0.001147137,0.001842454,0.001005935],"category_scores_gemma":[0.04011909,0.0004180231,0.0007627095,0.003353691,0.0005646486,0.003128606,0.0008060318,0.001403407,0.001240805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001297477,"about_ca_system_score_gemma":0.001484371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008066569,"about_ca_topic_score_gemma":0.02030741,"domain_scores_codex":[0.9955526,0.001817748,0.0003935365,0.001285304,0.00072671,0.0002240972],"domain_scores_gemma":[0.9400225,0.04253098,0.006759894,0.002236146,0.007036401,0.001414023],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001500296,0.0007273009,0.5211627,0.001401505,0.000607787,0.0008618209,0.001535899,0.04354899,0.01288204,0.003460672,0.0694969,0.3428141],"study_design_scores_gemma":[0.000135619,0.000347049,0.09130769,0.0001954269,0.0002588393,0.001329448,0.0003796152,0.8741366,0.007596837,0.006639034,0.01754874,0.0001251096],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8262442,0.02139911,0.1233141,0.004387442,0.001030506,0.0004429993,0.01121215,0.002723846,0.009245675],"genre_scores_gemma":[0.9444239,0.001674585,0.04071106,0.0003754242,0.001039216,0.0001472325,0.008730457,0.0001250421,0.002773102],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9893726,"threshold_uncertainty_score":0.05620402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1080329165715086,"score_gpt":0.2148729844220569,"score_spread":0.1068400678505482,"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."}}