{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":2,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":2,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"54f458119484","filters":{"venue":"Workshop on Innovative Use of NLP for Building Educational Applications"}},"results":[{"id":"W2250996967","doi":"","title":"Cognate and Misspelling Features for Natural Language Identification","year":2013,"lang":"en","type":"article","venue":"Workshop on Innovative Use of NLP for Building Educational Applications","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Bigram; Computer science; Cognate; Natural language processing; Artificial intelligence; Classifier (UML); Natural language; Word (group theory); Identification (biology); Spelling; Syntax; Language identification; Linguistics","authors":[{"name":"Garrett Nicolai","is_ca":true},{"name":"Bradley Hauer","is_ca":true},{"name":"Mohammad Salameh","is_ca":true},{"name":"Lei Yao","is_ca":true},{"name":"Grzegorz Kondrak","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04016925118674335,"gpt":0.347697391551569,"spread":0.3075281403648256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002527087,0.001327926,0.0008709689,0.003890466,0.001020371,0.001381296,0.000874899,0.0009793027,0.002749864],"category_scores_gemma":[0.0109757,0.00023774,0.0007656406,0.00193756,0.0004682339,0.002097928,0.001537054,0.00150325,0.002163836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003309601,"about_ca_system_score_gemma":0.0008284198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00158971,"about_ca_topic_score_gemma":0.002710665,"domain_scores_codex":[0.9971951,0.0009006651,0.0003001769,0.0005909849,0.0007678008,0.0002452282],"domain_scores_gemma":[0.9895887,0.005806613,0.0008951103,0.001398646,0.001700785,0.0006100758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000848415,0.0008313481,0.04739359,0.0003870119,0.000159598,0.0004180543,0.0005387546,0.008026438,0.04497234,0.001149729,0.007068025,0.8882068],"study_design_scores_gemma":[0.0001519073,0.001221826,0.06688757,0.0001859972,0.0003158285,0.001696663,0.001313319,0.7375987,0.1559478,0.01834087,0.01605993,0.0002794624],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7547152,0.001557654,0.2256594,0.0006205891,0.0002668394,0.0002527125,0.003101665,0.007741486,0.006084489],"genre_scores_gemma":[0.8842067,0.0001697323,0.1094606,0.0000904362,0.00009078635,0.0001442146,0.003975436,0.0002351529,0.00162718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003890466,"threshold_uncertainty_score":0.01336467,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3154002721","doi":"","title":"Identifying negative language transfer in learner errors using POS information.","year":2021,"lang":"en","type":"article","venue":"Workshop on Innovative Use of NLP for Building Educational Applications","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Mistake; Negative transfer; Language model; Natural language processing; Language transfer; Artificial intelligence; First language; Cache language model; Transfer (computing); Recurrent neural network; Artificial neural network; Speech recognition; n-gram; Natural language; Universal Networking Language; Linguistics; Comprehension approach","authors":[{"name":"Leticia Farias Wanderley","is_ca":false},{"name":"Carrie Demmans Epp","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04961372036844343,"gpt":0.3623847222147725,"spread":0.3127710018463291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004061476,0.0009523025,0.0005256803,0.001545993,0.0005556867,0.001261248,0.0007883268,0.001089241,0.001708784],"category_scores_gemma":[0.02952434,0.0002221904,0.0003666626,0.0008255651,0.0006259797,0.002492539,0.001627071,0.001222733,0.001930219],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004402137,"about_ca_system_score_gemma":0.000834483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002405274,"about_ca_topic_score_gemma":0.004293432,"domain_scores_codex":[0.9953461,0.001538673,0.0004816427,0.0009508895,0.001437225,0.0002454591],"domain_scores_gemma":[0.9736785,0.01278765,0.003880508,0.003193852,0.005844962,0.0006144898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001027173,0.0006546037,0.4982485,0.0005621655,0.0002651572,0.003320662,0.004597615,0.009687923,0.06001718,0.001364579,0.00820464,0.4120498],"study_design_scores_gemma":[0.00007143235,0.001384716,0.2845087,0.000372243,0.0003888381,0.009392139,0.007794847,0.4238949,0.2414895,0.0109949,0.01939639,0.0003114558],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9341479,0.000342242,0.05631784,0.0004139442,0.000160935,0.0001007327,0.001188087,0.002351178,0.004977035],"genre_scores_gemma":[0.9865129,0.0001026817,0.009976228,0.0001014667,0.00001684359,0.0000355713,0.001094455,0.0001214008,0.002038468],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004061476,"threshold_uncertainty_score":0.02147937,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}