{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":3,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":3,"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":"96b9e3b2fc0b","filters":{"venue":"Natural language processing."}},"results":[{"id":"W4397012280","doi":"10.1017/nlp.2024.7","title":"A survey of context in neural machine translation and its evaluation","year":2024,"lang":"en","type":"article","venue":"Natural language processing.","topic":"Natural Language Processing Techniques","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":"National Research Council Canada","funders":"Dublin City University; Science Foundation Ireland","keywords":"Machine translation; Computer science; Artificial intelligence; Evaluation of machine translation; Context (archaeology); Natural language processing; Terminology; Machine translation software usability; Consistency (knowledge bases); Example-based machine translation; Sentence; Computer-assisted translation; Task (project management); Paragraph; Transfer-based machine translation; Machine learning; Linguistics; World Wide Web; Engineering","authors":[{"name":"Sheila Castilho","is_ca":false},{"name":"Rebecca Knowles","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03055695989947995,"gpt":0.3326759585021715,"spread":0.3021189986026915,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01459207,0.001505316,0.002215877,0.005426799,0.0009528288,0.002986988,0.00232088,0.002165894,0.00245355],"category_scores_gemma":[0.0428756,0.0005654492,0.001071757,0.004938262,0.001059618,0.003304939,0.001921739,0.001297651,0.0006592994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002650352,"about_ca_system_score_gemma":0.001526525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006481652,"about_ca_topic_score_gemma":0.00597721,"domain_scores_codex":[0.9810293,0.01208333,0.001605879,0.00158278,0.00338028,0.0003183962],"domain_scores_gemma":[0.9710484,0.01944213,0.001335664,0.001746735,0.006013337,0.0004139499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001611747,0.0002274243,0.008395502,0.003897435,0.0009233701,0.00009182491,0.0002090971,0.043231,0.002981775,0.005636111,0.005521835,0.9272729],"study_design_scores_gemma":[0.0005812291,0.004859946,0.03096424,0.00749666,0.002693787,0.001068671,0.001099785,0.7670239,0.04423236,0.05328752,0.08629181,0.0004000997],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1701156,0.6623136,0.1246416,0.003520195,0.0009076901,0.0005511797,0.001355852,0.002970085,0.03362423],"genre_scores_gemma":[0.8122588,0.06769282,0.1117437,0.001003793,0.000789605,0.0004311239,0.002638011,0.0006064857,0.002835674],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01459207,"threshold_uncertainty_score":0.07717115,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4399298003","doi":"10.1017/nlp.2024.5","title":"Calibration and context in human evaluation of machine translation","year":2024,"lang":"en","type":"article","venue":"Natural language processing.","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Calibration; Context (archaeology); Translation (biology); Machine translation; Computer science; Artificial intelligence; Natural language processing; Machine learning; Chemistry; Biology; Mathematics; Statistics; Biochemistry","authors":[{"name":"Rebecca Knowles","is_ca":true},{"name":"Chi-kiu Lo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01995254238234069,"gpt":0.3295239246854237,"spread":0.3095713823030831,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1233818,0.001277344,0.00113178,0.003155762,0.002381086,0.005163773,0.002104234,0.002147941,0.002098529],"category_scores_gemma":[0.3890582,0.0009923097,0.0006853218,0.002324636,0.004251792,0.004760565,0.00757032,0.00229917,0.0006238022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002286055,"about_ca_system_score_gemma":0.001582256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001379956,"about_ca_topic_score_gemma":0.002022447,"domain_scores_codex":[0.6229384,0.334097,0.00805994,0.01305972,0.02059283,0.001252177],"domain_scores_gemma":[0.602674,0.2989887,0.03130128,0.02853955,0.03582019,0.002676276],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01326505,0.001083081,0.121547,0.003837435,0.002758399,0.0007053195,0.03593083,0.0489224,0.06267169,0.03181332,0.007383508,0.670082],"study_design_scores_gemma":[0.001503211,0.008361804,0.2977031,0.005963982,0.002537868,0.002746942,0.01399983,0.2096984,0.1756246,0.2177701,0.06204737,0.002042646],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6657237,0.01135859,0.2795195,0.002429877,0.000580689,0.001490472,0.0004726325,0.001385321,0.0370393],"genre_scores_gemma":[0.9514693,0.000307143,0.04635189,0.0003473379,0.0001205802,0.0004972448,0.0001580964,0.0001955351,0.000552889],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8766181,"threshold_uncertainty_score":0.6525133,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4411558583","doi":"10.1017/nlp.2024.6","title":"Editors’ foreword","year":2025,"lang":"en","type":"article","venue":"Natural language processing.","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":"National Research Council Canada","funders":"","keywords":"Psychology; Computer science; Cognitive science","authors":[{"name":"Sheila Castilho","is_ca":false},{"name":"Rebecca Knowles","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004900954798458003,"gpt":0.2795578525872755,"spread":0.2746568977888175,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002824329,0.001556597,0.001462624,0.002413735,0.001456384,0.006337774,0.002189811,0.004292259,0.1581357],"category_scores_gemma":[0.01572473,0.0004774113,0.001162962,0.001452864,0.0007724263,0.003780216,0.001821005,0.006871327,0.1244862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001449521,"about_ca_system_score_gemma":0.001916848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000908301,"about_ca_topic_score_gemma":0.001697827,"domain_scores_codex":[0.9977179,0.0002826693,0.0002621046,0.0004570418,0.001061346,0.0002189467],"domain_scores_gemma":[0.9877302,0.002660177,0.0007120003,0.0004865437,0.006481486,0.001929603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001219194,0.000005752529,0.00001930708,0.000074203,0.000002310415,0.00001822678,0.00000476835,0.0000172312,0.00003881815,0.0002624205,0.9894014,0.01014335],"study_design_scores_gemma":[0.00001012297,0.00001622115,0.0001405164,0.0001631169,0.00000490275,0.00006966721,0.000014683,0.00005091273,0.0001033252,0.0004664116,0.998953,0.000007099789],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0001184969,0.005257195,0.0004327724,0.04670741,0.9267867,0.00005229886,0.0004848828,0.0002046031,0.01995552],"genre_scores_gemma":[0.002154171,0.009427588,0.0006456177,0.04924219,0.772261,0.0001314814,0.0008199013,0.000428094,0.16489],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.1581357,"threshold_uncertainty_score":0.5290167,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}