{"id":"W2264085712","doi":"10.1609/icwsm.v9i4.14686","title":"Everyone's Invited: A New Paradigm for Evaluation on Non-Transferable Datasets","year":2021,"lang":"en","type":"article","venue":"Proceedings of the International AAAI Conference on Web and Social Media","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Data science; Social media; Process (computing); Context (archaeology); Task (project management); Geolocation; Computational sociology; Resource (disambiguation); Analytics; Scale (ratio); World Wide Web","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2800017,0.002773419,0.003562856,0.007203729,0.004519994,0.01161268,0.008015466,0.007052844,0.01317876],"category_scores_gemma":[0.3929168,0.001332575,0.004897405,0.006596621,0.008225662,0.0248346,0.02140668,0.009124732,0.003738859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003781396,"about_ca_system_score_gemma":0.007274872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003467306,"about_ca_topic_score_gemma":0.003890853,"domain_scores_codex":[0.6396495,0.2843402,0.01392888,0.01882037,0.03978714,0.003473842],"domain_scores_gemma":[0.6156014,0.2259071,0.01075208,0.1047065,0.03604039,0.006992481],"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":[0.007688927,0.00275135,0.020704,0.003095111,0.002398857,0.0004273199,0.006858074,0.02561157,0.006682052,0.3125145,0.05460979,0.5566586],"study_design_scores_gemma":[0.002626884,0.005279183,0.006052836,0.00100574,0.0006244956,0.0006496458,0.002942726,0.2269117,0.008739377,0.650427,0.09431889,0.0004214638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02477262,0.001083716,0.9323959,0.006717284,0.001452904,0.005639582,0.003189629,0.00490736,0.01984105],"genre_scores_gemma":[0.2353031,0.0002755758,0.7391554,0.003354733,0.0006691203,0.01125622,0.003506973,0.00229991,0.00417911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2800017,"threshold_uncertainty_score":0.887886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03986226007874676,"score_gpt":0.3032576873639515,"score_spread":0.2633954272852047,"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."}}