{"id":"W4226145103","doi":"10.18653/v1/2022.findings-acl.326","title":"On the data requirements of probing","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Reliability (semiconductor); Context (archaeology); Construct (python library); Data mining; Machine learning; Artificial intelligence; Power (physics)","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":[0.1514632,0.002077524,0.005660926,0.003211724,0.004348049,0.01122486,0.01005458,0.01074506,0.01188878],"category_scores_gemma":[0.685493,0.003752362,0.003197118,0.007854061,0.01009687,0.03424552,0.01430576,0.01449659,0.004753011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003703604,"about_ca_system_score_gemma":0.006071488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004637831,"about_ca_topic_score_gemma":0.003509584,"domain_scores_codex":[0.7993628,0.1466337,0.01085994,0.01743936,0.02287018,0.002834147],"domain_scores_gemma":[0.149344,0.7665843,0.006776336,0.0593323,0.01448048,0.003482618],"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":[0.009351456,0.001184792,0.05405917,0.002786642,0.0007923673,0.001582256,0.006661666,0.06693953,0.008518392,0.4485721,0.1200505,0.2795013],"study_design_scores_gemma":[0.0008555682,0.0004845809,0.006930318,0.0005116955,0.0001913161,0.00124559,0.002498881,0.2380625,0.003625033,0.719126,0.02631887,0.0001496617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1293585,0.007681459,0.6953404,0.118013,0.002287666,0.001941252,0.01294484,0.006339601,0.02609326],"genre_scores_gemma":[0.5066476,0.002337239,0.446109,0.01365018,0.00233689,0.004114285,0.01786789,0.002705138,0.004231726],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1514632,"threshold_uncertainty_score":0.8010237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05416273860118753,"score_gpt":0.291028757242492,"score_spread":0.2368660186413045,"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."}}