{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":14,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":14,"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"},"query_hash":"0f8f2e53290b","filters":{"venue":"Machine Translation"}},"results":[{"id":"W1982816048","doi":"10.1023/b:coat.0000010117.98933.a0","title":"Trans Type: Development-Evaluation Cycles to Boost Translator's Productivity","year":2002,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine translation; Productivity; Context (archaeology); Translation (biology); Process (computing); Set (abstract data type); Interface (matter); Artificial intelligence; Evaluation of machine translation; Natural language processing; Rule-based machine translation; Software engineering; Machine learning; Programming language; Example-based machine translation; Machine translation software usability","retraction":null,"screen_n_in":null,"score":{"opus":0.04654180184988662,"gpt":0.2987353309047347,"spread":0.2521935290548481,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005885793,0.0001797488,0.0001446312,0.0001922902,0.0001686482,0.0001127412,0.0004389384,0.0000743801,0.00008489517],"category_scores_gemma":[0.0000407049,0.0001687409,0.00004028684,0.0007097662,0.00001686674,0.0007553115,0.0000144075,0.0001596361,0.00003509076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005899472,"about_ca_system_score_gemma":0.00004708571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002076929,"about_ca_topic_score_gemma":0.0001891,"domain_scores_codex":[0.9984334,0.0001061914,0.000251754,0.0004576696,0.0005170719,0.0002338723],"domain_scores_gemma":[0.9993672,0.00003806575,0.00005007439,0.0003382183,0.0001258852,0.00008053579],"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":[0.00001030448,0.00006850495,0.0002284797,0.00002738513,0.000009318332,0.000001532343,0.006224652,0.0001087161,0.01551215,0.0003936369,0.0001035791,0.9773117],"study_design_scores_gemma":[0.002341654,0.0003794775,0.0106686,0.0002261912,0.0001138214,0.00006135259,0.00002791976,0.6307132,0.29836,0.01445787,0.04064215,0.002007854],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02717088,0.005125622,0.9594523,0.005635186,0.0002065788,0.0007522866,0.000003284847,0.0008421614,0.0008117442],"genre_scores_gemma":[0.6889483,0.000006222157,0.3108048,0.0001025988,0.00003698063,0.00002698904,0.00001239101,0.00001200376,0.00004974413],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9753039,"threshold_uncertainty_score":0.6881053,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991522508","doi":"10.1007/s10590-008-9036-3","title":"Semi-supervised model adaptation for statistical machine translation","year":2007,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; National Research Council Canada","funders":"","keywords":"Machine translation; Computer science; Translation (biology); Artificial intelligence; Adaptation (eye); Computational linguistics; Natural language processing; Machine learning; Statistical analysis; Statistical model; Statistics; Mathematics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.03837286427808482,"gpt":0.3087072662634866,"spread":0.2703344019854018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008507241,0.0002112749,0.0001870804,0.0002107956,0.0001707331,0.0001070209,0.0003692821,0.0001360633,0.00001097909],"category_scores_gemma":[0.00003757014,0.0001993796,0.00007979352,0.0003311658,0.00002809483,0.0007983192,0.00001338723,0.0001994814,0.000003572101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005074202,"about_ca_system_score_gemma":0.00004974491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007412958,"about_ca_topic_score_gemma":0.0002674785,"domain_scores_codex":[0.9984132,0.00004611783,0.0004370854,0.0004215678,0.000363494,0.0003185368],"domain_scores_gemma":[0.9991304,0.0002926549,0.00009561385,0.0002746722,0.0001153115,0.0000913608],"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":[0.0001250854,0.00005636024,0.00005025417,0.00006846854,0.000009809788,0.000002612065,0.001733263,0.004027517,0.007938693,0.03031659,0.00003388659,0.9556375],"study_design_scores_gemma":[0.0008035268,0.00008408717,0.00008957044,0.00001709532,0.00002168308,0.000005414525,0.000006198932,0.9409888,0.004287011,0.05325133,0.0002175946,0.0002276741],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003810852,0.002643156,0.9940985,0.001029599,0.00009415862,0.0006231944,0.00007293227,0.0007327933,0.0003246097],"genre_scores_gemma":[0.477546,0.000005730005,0.5220373,0.0001176613,0.00003070821,0.00001668983,0.0002136869,0.0000151739,0.00001712657],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9554098,"threshold_uncertainty_score":0.8130466,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132891320","doi":"10.1007/s10590-011-9112-y","title":"Improved Arabic-to-English statistical machine translation by reordering post-verbal subjects for word alignment","year":2011,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"University of Pennsylvania","keywords":"Computer science; Machine translation; Natural language processing; Word order; Artificial intelligence; Phrase; Parsing; Word (group theory); Translation (biology); Speech recognition; Arabic; Computational linguistics; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01793620875493665,"gpt":0.2589407352169916,"spread":0.241004526462055,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004765555,0.0002877464,0.0002487106,0.0001656316,0.0001664107,0.0001350562,0.00054152,0.0001276194,0.00003159053],"category_scores_gemma":[0.00007625814,0.0002706739,0.00008357627,0.0003332316,0.00002878318,0.000749474,0.00003523957,0.000223464,0.000003396432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006485869,"about_ca_system_score_gemma":0.0000349769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003580445,"about_ca_topic_score_gemma":0.0002141948,"domain_scores_codex":[0.9981636,0.00008320974,0.0004339871,0.0005999027,0.0003123508,0.0004069161],"domain_scores_gemma":[0.9990577,0.0001486651,0.0001084565,0.0003689289,0.0001648787,0.0001513723],"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":[0.000337912,0.0001449155,0.00009739576,0.0001061236,0.00002784909,0.000004907332,0.008171529,0.00001683415,0.03843059,0.004755332,0.0001564866,0.9477502],"study_design_scores_gemma":[0.003297725,0.001399355,0.0008617472,0.0001206912,0.0001079379,0.00001832396,0.0000506148,0.8710948,0.09379132,0.02445987,0.003411572,0.001386056],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00209775,0.00199661,0.9927237,0.0006624181,0.0002531485,0.001026725,0.0001701017,0.000815897,0.0002536541],"genre_scores_gemma":[0.5430635,0.000005170642,0.4564219,0.0001922102,0.00003789654,0.0000703718,0.0001661323,0.00002332578,0.00001950168],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.946364,"threshold_uncertainty_score":0.9999745,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2081743236","doi":"10.1007/s10590-014-9166-8","title":"Introduction to special issue on post-editing","year":2014,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Computational linguistics; Natural language processing; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.0073987869319434,"gpt":0.2583055012703789,"spread":0.2509067143384355,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003003185,0.00009493613,0.00008278593,0.0001428303,0.00009164094,0.0000986639,0.0002778822,0.0000415986,0.00007358854],"category_scores_gemma":[0.0000897768,0.00008547372,0.00002698793,0.0002611056,0.000007360033,0.0003280434,0.0000205348,0.0001372592,0.0001205061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002421903,"about_ca_system_score_gemma":0.000005792377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002803348,"about_ca_topic_score_gemma":0.00003117161,"domain_scores_codex":[0.9991904,0.00005338102,0.0001348834,0.000284724,0.0002054263,0.0001311405],"domain_scores_gemma":[0.9995815,0.0000341359,0.00004091701,0.000244662,0.0000562551,0.00004254567],"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":[0.00001179482,0.00001384757,0.00001889462,0.000007533239,0.00000137369,5.628539e-7,0.0005583749,0.0001053937,0.004449619,0.01267004,0.002666961,0.9794956],"study_design_scores_gemma":[0.0007094668,0.001008695,0.001504973,0.00007504981,0.00001566617,0.00002570146,0.00001322118,0.2062942,0.1252979,0.03218264,0.632173,0.0006995485],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001220826,0.00005436249,0.9544463,0.03960184,0.000771876,0.0001590645,0.00000164374,0.000564429,0.003179692],"genre_scores_gemma":[0.4431463,7.145468e-7,0.5340157,0.001417691,0.0211929,0.000009093015,0.00002457728,0.0000134671,0.0001794933],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9787961,"threshold_uncertainty_score":0.3485517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118491422","doi":"10.1007/s10590-004-7693-4","title":"A Morphological Tagger for Korean: Statistical Tagging Combined with Corpus-Based Morphological Rule Application","year":2004,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; University of Pennsylvania; Yale University","keywords":"Agglutinative language; Computer science; Artificial intelligence; Natural language processing; Lemma (botany); Trigram; Part-of-speech tagging; Part of speech; Component (thermodynamics); Tag system; Rule-based system; Word (group theory); Precision and recall; Computational linguistics; Speech recognition; Linguistics; Parsing; Algorithm; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01525715266378229,"gpt":0.2739101294085907,"spread":0.2586529767448084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003009971,0.0002095995,0.0002234317,0.0001001223,0.0001632889,0.0001060173,0.0004315226,0.0001271923,0.00001158155],"category_scores_gemma":[0.000038572,0.000151047,0.000054133,0.0003136196,0.00009764548,0.0002479966,0.00002382593,0.0002206056,0.000007129286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006555772,"about_ca_system_score_gemma":0.0000589561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005617363,"about_ca_topic_score_gemma":0.00001940447,"domain_scores_codex":[0.9985995,0.00005055646,0.0002627985,0.0005143104,0.000288474,0.0002843444],"domain_scores_gemma":[0.9992096,0.0001784748,0.0001125366,0.0003229566,0.0000911909,0.00008522374],"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":[0.001734573,0.001114456,0.001840384,0.0001958808,0.00004153774,0.0002807137,0.0003996064,0.008202186,0.07013679,0.400562,0.0001429542,0.5153489],"study_design_scores_gemma":[0.006248585,0.002021578,0.002035445,0.00007478643,0.00005714041,0.0001785538,0.000003882801,0.7244746,0.03929426,0.2241314,0.0007057575,0.0007739685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007536123,0.0002916117,0.9866029,0.003757202,0.00003165817,0.0007753949,0.00003528237,0.0009107676,0.00005905808],"genre_scores_gemma":[0.5077358,9.514543e-7,0.4915412,0.0004172364,0.00001590896,0.0001209758,0.0001549563,0.00000993695,0.0000029749],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7162724,"threshold_uncertainty_score":0.6159517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145084016","doi":"10.1023/a:1012262211784","title":"Unit Completion for a Computer-aided Translation Typing System","year":2000,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Computational linguistics; Natural language processing; Context (archaeology); Word (group theory); Artificial intelligence; Machine translation; Linguistics; History","retraction":null,"screen_n_in":null,"score":{"opus":0.0330547707272114,"gpt":0.2821371979595065,"spread":0.2490824272322951,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003502809,0.0001634812,0.0001829664,0.0001395803,0.0002080594,0.0001510465,0.0003679122,0.00008899545,0.00002048441],"category_scores_gemma":[0.000002815318,0.000157656,0.00008593843,0.0003551231,0.00001712161,0.0006065177,0.000007486843,0.0001227703,0.00001446514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004045042,"about_ca_system_score_gemma":0.00002038731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006191944,"about_ca_topic_score_gemma":0.00002738404,"domain_scores_codex":[0.9988773,0.00008608541,0.0003124338,0.0003367122,0.0001806689,0.0002067827],"domain_scores_gemma":[0.999437,0.0001044722,0.00007670991,0.000262934,0.00007277598,0.00004606625],"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":[0.00003990399,0.00002246546,0.00003697046,0.000133521,0.000008770658,0.000001080995,0.0005703074,0.0007377783,0.001373744,0.01121751,0.00002210339,0.9858359],"study_design_scores_gemma":[0.0006979957,0.00008610205,0.0002581955,0.0001048679,0.00001591936,0.00001835393,0.000003141608,0.9899353,0.001245695,0.003159755,0.004269849,0.0002047997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00285655,0.001382698,0.9924081,0.000793164,0.0001147996,0.0005877545,0.00001329106,0.001357307,0.0004863402],"genre_scores_gemma":[0.5120623,0.000004093872,0.4876647,0.00006787482,0.00006780553,0.0000244664,0.00008019988,0.00001109126,0.00001752666],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9891976,"threshold_uncertainty_score":0.6429026,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1594980056","doi":"10.1023/a:1012244918183","title":"Machine Translation of Closed Captions","year":2000,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Machine translation; Natural language processing; Artificial intelligence; Domain (mathematical analysis); Closed captioning; Speech translation; Computational linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01603385525805243,"gpt":0.2694640035533037,"spread":0.2534301482952512,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002347151,0.000146763,0.0001670739,0.0001592368,0.00009276344,0.00004445421,0.0004085981,0.00008712524,0.0002404667],"category_scores_gemma":[0.000005710932,0.0001342649,0.0000888576,0.0004965859,0.00003471778,0.0006165326,0.000007676796,0.00017205,0.00001587436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000171888,"about_ca_system_score_gemma":0.00002544557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002373347,"about_ca_topic_score_gemma":0.00009701625,"domain_scores_codex":[0.9988813,0.00007826445,0.0003369979,0.0002654638,0.0002748934,0.0001630169],"domain_scores_gemma":[0.9994339,0.0000578634,0.00007872219,0.0003370426,0.00004761193,0.0000448449],"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":[0.00002214355,0.0000545322,0.0001584424,0.00002760387,0.000008211627,0.000001779603,0.0008726231,0.0002335069,0.007526607,0.004437295,0.0000137745,0.9866435],"study_design_scores_gemma":[0.001308343,0.000169896,0.001987987,0.00007275023,0.00004449279,0.00002681886,0.000003688755,0.9229499,0.02312299,0.04543288,0.004434827,0.0004454835],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00478013,0.01003286,0.9781628,0.001790382,0.00006114943,0.0002942864,0.00002765272,0.0006619595,0.004188803],"genre_scores_gemma":[0.6954555,0.00004998019,0.3042668,0.00005870342,0.00001981996,0.000007260484,0.00005140178,0.000009666592,0.0000808715],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.986198,"threshold_uncertainty_score":0.5475162,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1496822098","doi":"10.1023/a:1013136005350","title":"Towards a Lexicographic Approach to Lexical Transfer in Machine Translation (Illustrated by the German–Russian Language Pair)","year":2001,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computational linguistics; Computer science; Natural language processing; Artificial intelligence; Linguistics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.02119614656579054,"gpt":0.2848283274894695,"spread":0.263632180923679,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007119485,0.0003317604,0.0002777674,0.0003643375,0.0001436864,0.0002102438,0.0008712162,0.0001965394,0.00002428674],"category_scores_gemma":[0.000009580794,0.0002408401,0.000133147,0.001946182,0.00006501223,0.0006492446,0.0000219732,0.0005736267,0.000007476006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005899886,"about_ca_system_score_gemma":0.00005227527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001022817,"about_ca_topic_score_gemma":0.0006545254,"domain_scores_codex":[0.9977119,0.0002716231,0.0004804581,0.0005950494,0.000497098,0.0004438868],"domain_scores_gemma":[0.9992581,0.00006079434,0.00004505091,0.0004824876,0.00002943111,0.0001241583],"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":[0.0001698296,0.0003715642,0.0008916122,0.00006294715,0.00002670666,0.0000278535,0.01699649,0.0002390866,0.01286708,0.009495369,0.0001519309,0.9586995],"study_design_scores_gemma":[0.002789256,0.0003164276,0.004508833,0.0001097567,0.00005725144,0.0001720217,0.00007487203,0.967526,0.007739383,0.01018545,0.005359944,0.001160797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01908086,0.007793543,0.9587915,0.009847169,0.00007441137,0.0008297011,0.00002845913,0.0007337947,0.002820567],"genre_scores_gemma":[0.9306208,0.00002899245,0.06833241,0.0005885129,0.00004438117,0.00008113722,0.000164771,0.00003034746,0.0001086132],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9672869,"threshold_uncertainty_score":0.9821175,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159939228","doi":"10.1007/s10590-011-9089-6","title":"TransSearch: from a bilingual concordancer to a translation finder","year":2010,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Computer science; Machine translation; Natural language processing; Translation (biology); Artificial intelligence; Sentence; Word (group theory); Example-based machine translation; Computer-assisted translation; Bilingual dictionary; Feature (linguistics); Machine translation software usability; Identification (biology); Computational linguistics; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02954497783423231,"gpt":0.3163444565220911,"spread":0.2867994786878588,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003212969,0.000177721,0.0001623542,0.0001849238,0.0001112829,0.0001598214,0.0005951085,0.0001275275,0.0001052398],"category_scores_gemma":[0.00002864427,0.0001602659,0.0000761799,0.0005074627,0.00003126936,0.0005773023,0.00001746899,0.0004660957,0.00002834109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001564529,"about_ca_system_score_gemma":0.00009116429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004891935,"about_ca_topic_score_gemma":0.002051932,"domain_scores_codex":[0.9985979,0.00006037336,0.0002666962,0.0004650885,0.0003638953,0.0002459974],"domain_scores_gemma":[0.9991968,0.0001514193,0.00004651992,0.0004147879,0.0000744154,0.0001160387],"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":[0.00003651369,0.00003441198,0.00028156,0.000009976707,0.000008019718,0.000005124614,0.003949223,0.00003283112,0.2061146,0.002776362,0.00002325492,0.7867281],"study_design_scores_gemma":[0.003051498,0.0003842509,0.005657163,0.000114286,0.00006013186,0.00003002815,0.00003124798,0.5298945,0.312847,0.1274222,0.01903683,0.001470808],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06154811,0.0009847915,0.9314224,0.00429489,0.000268994,0.0003761264,0.00002590087,0.0006901319,0.0003886234],"genre_scores_gemma":[0.5630591,0.000002309746,0.4365351,0.0002609157,0.0000762755,0.00001424783,0.00002501485,0.00001161147,0.00001551271],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7852573,"threshold_uncertainty_score":0.6535456,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2037632172","doi":"10.1023/b:coat.0000010116.83274.c3","title":"Construction of a Chinese–English Verb Lexicon for Machine Translation and Embedded Multilingual Applications","year":2002,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Directorate for Computer and Information Science and Engineering; National Science Foundation","keywords":"Computer science; Lexicon; Natural language processing; Machine translation; Artificial intelligence; Verb; Lexical database; WordNet","retraction":null,"screen_n_in":null,"score":{"opus":0.01915247602154042,"gpt":0.2812119978952083,"spread":0.2620595218736679,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002215755,0.000183311,0.0002167941,0.0001958542,0.0001398022,0.00006441427,0.0002470742,0.0001143097,0.00001301953],"category_scores_gemma":[0.00004124715,0.0001684892,0.00007785522,0.0003989741,0.00007274682,0.0005832143,0.00001542665,0.0001496352,7.605749e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001650392,"about_ca_system_score_gemma":0.00001439284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002864269,"about_ca_topic_score_gemma":0.00004906083,"domain_scores_codex":[0.9988622,0.0000460878,0.0003763401,0.000361583,0.0001938347,0.0001599562],"domain_scores_gemma":[0.9991922,0.0001665837,0.0001681299,0.0002693737,0.0001533025,0.00005040741],"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":[0.00003063105,0.00006763582,0.0009899135,0.0001401726,0.00001522271,2.916019e-7,0.003800023,0.00005117444,0.006574819,0.004885294,0.000004893084,0.9834399],"study_design_scores_gemma":[0.001439232,0.0001155547,0.0002942746,0.00002916369,0.00003147727,0.00001546567,0.00001639303,0.9619344,0.009314737,0.02591198,0.0006397358,0.0002575857],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008485733,0.01072589,0.9785919,0.0004422509,0.00009788194,0.0008600344,0.00005347716,0.0004729927,0.0002698801],"genre_scores_gemma":[0.573656,0.00003315458,0.4261205,0.00002064822,0.00004817021,0.0000556285,0.00004735908,0.00001052407,0.000008094878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9831824,"threshold_uncertainty_score":0.6870791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2063381274","doi":"10.1007/s10590-006-9017-3","title":"EBMT by tree-phrasing","year":2006,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Universität Stuttgart","keywords":"Computer science; Machine translation; Natural language processing; Exploit; Phrase; Artificial intelligence; Example-based machine translation; Machine translation software usability; Translation (biology); Dependency (UML); Tree (set theory); Simple (philosophy); Computational linguistics; Transfer-based machine translation","retraction":null,"screen_n_in":null,"score":{"opus":0.007206483007843711,"gpt":0.2440312977121587,"spread":0.236824814704315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001286128,0.00009225777,0.00007522603,0.00006864731,0.00007722838,0.0001133504,0.0002861787,0.00004710578,0.00001001498],"category_scores_gemma":[0.000004075049,0.00008240873,0.00003301852,0.0002386329,0.00001379557,0.0004558248,0.0000138157,0.0001014494,0.000008940297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001873681,"about_ca_system_score_gemma":0.000009633007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002273104,"about_ca_topic_score_gemma":0.00007291936,"domain_scores_codex":[0.9993209,0.00003042502,0.0001441534,0.0002030093,0.00016689,0.0001346666],"domain_scores_gemma":[0.999709,0.00002696725,0.00004501115,0.0001787253,0.00002047609,0.00001989913],"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":[0.000003532065,0.00003138753,0.0005340062,0.000008955718,0.000002009851,0.000003498742,0.000129839,0.00001758922,0.05022648,0.007245067,0.0008646304,0.940933],"study_design_scores_gemma":[0.0009566608,0.0000973202,0.001813059,0.00005803419,0.00002021737,0.00003774451,0.000002937134,0.5536084,0.268227,0.1543824,0.02007735,0.0007188659],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002265153,0.005590333,0.9870222,0.001477693,0.00005336447,0.00008070056,0.000003112983,0.0005429029,0.002964608],"genre_scores_gemma":[0.6247342,0.000001847449,0.3750406,0.00006293669,0.00002823616,0.000002441425,0.00002420635,0.000005503889,0.0001000031],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9402142,"threshold_uncertainty_score":0.336053,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034060496","doi":"10.1007/s10590-008-9048-z","title":"METIS-II: low resource machine translation","year":2008,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Metis; Scope (computer science); Computer science; German; Machine translation; Computational linguistics; Natural language processing; Resource (disambiguation); Linguistics; Artificial intelligence; Programming language; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.02024545271093636,"gpt":0.256454324211225,"spread":0.2362088715002887,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003510954,0.0002430271,0.0002210411,0.0002450854,0.0004483384,0.00006836752,0.0006635877,0.0001331734,0.00004184532],"category_scores_gemma":[0.0000192514,0.0002207855,0.0001129757,0.000664322,0.0000579333,0.0008687941,0.00004309695,0.0003317336,0.00001626987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003739683,"about_ca_system_score_gemma":0.0000380598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001126938,"about_ca_topic_score_gemma":0.00006439977,"domain_scores_codex":[0.9982793,0.0001255384,0.0003657688,0.0004723388,0.0004704198,0.0002866517],"domain_scores_gemma":[0.9991717,0.00008446618,0.0001147166,0.0004858274,0.00005696641,0.00008628315],"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":[0.00005160139,0.0001250637,0.0005387952,0.00005415137,0.00001987045,0.00004018238,0.004337444,0.0002380702,0.01237041,0.003369618,0.0003354906,0.9785193],"study_design_scores_gemma":[0.001838004,0.0003238893,0.001465606,0.0001037461,0.00004118643,0.0002896647,0.000005851084,0.9002522,0.05493915,0.01412542,0.02566126,0.0009540036],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004666453,0.01431868,0.97388,0.003380065,0.00009823739,0.0003294542,0.00001249692,0.001417462,0.00189716],"genre_scores_gemma":[0.6529948,0.00003693022,0.3464352,0.0002400766,0.00005274808,0.00001235756,0.0000690949,0.00001940259,0.0001393563],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9775653,"threshold_uncertainty_score":0.9003371,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005440678","doi":"10.1007/s10590-005-2403-4","title":"The Long-Term Forecast for Weather Bulletin Translation","year":2005,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Machine translation; Computer science; Phrase; Task (project management); Sentence; Focus (optics); Natural language processing; Term (time); Artificial intelligence; Translation (biology); Rule-based machine translation; Computational linguistics; Artificial neural network; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01957454266199084,"gpt":0.2810361951975129,"spread":0.2614616525355221,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003898531,0.0001291394,0.00008967454,0.0000550545,0.0002772352,0.0001879866,0.0004711828,0.00006730104,0.00001730387],"category_scores_gemma":[0.00001157967,0.00008970388,0.00008426717,0.0001424899,0.00002692401,0.000307146,0.00001149498,0.0001189025,0.0000127149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002502448,"about_ca_system_score_gemma":0.00001422805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009460629,"about_ca_topic_score_gemma":0.0001651722,"domain_scores_codex":[0.9991186,0.00004112583,0.0002182476,0.0002361459,0.0001811489,0.000204723],"domain_scores_gemma":[0.9994062,0.0001702937,0.00007168377,0.0002680779,0.00005165946,0.00003212745],"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":[0.00002490476,0.0000170752,0.0001377541,0.00001316331,0.000006041867,3.546126e-7,0.0004470107,0.00003159903,0.0008677059,0.004845115,0.0001275382,0.9934818],"study_design_scores_gemma":[0.00255125,0.0002871855,0.002584002,0.0001010539,0.00006191186,0.00004296302,0.000006186923,0.7829648,0.03428736,0.03661798,0.1396746,0.000820764],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007307342,0.008479242,0.9708822,0.01854588,0.00008369312,0.0004824728,0.000004982036,0.0004120915,0.0003786931],"genre_scores_gemma":[0.5935187,0.00002702232,0.4059161,0.0001664096,0.0001157354,0.00005254485,0.00001990141,0.00001395644,0.0001695552],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.992661,"threshold_uncertainty_score":0.3658018,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1702922849","doi":"10.1007/s10590-015-9172-5","title":"Complexity of alignment and decoding problems: restrictions and approximations","year":2015,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Decoding methods; Viterbi algorithm; Computer science; Parameterized complexity; Computational complexity theory; Sentence; Sequential decoding; Algorithm; Word (group theory); Polynomial; Iterative Viterbi decoding; List decoding; Theoretical computer science; Mathematics; Artificial intelligence; Block code","retraction":null,"screen_n_in":null,"score":{"opus":0.08034618598023999,"gpt":0.2992751910534103,"spread":0.2189290050731703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002004724,0.00005430773,0.00007114062,0.0000816614,0.0000599975,0.00004193634,0.0000893715,0.00002424091,6.118941e-7],"category_scores_gemma":[0.00001946671,0.0000482016,0.000008991887,0.0001682623,0.00004933821,0.0003175398,0.00002988259,0.00005125639,1.800233e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000119698,"about_ca_system_score_gemma":0.00001733142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001203579,"about_ca_topic_score_gemma":0.00006525796,"domain_scores_codex":[0.9995381,0.00003136743,0.0001332104,0.0001254031,0.0001112592,0.00006066923],"domain_scores_gemma":[0.9997267,0.00003226801,0.00005401286,0.0001059556,0.00003991717,0.00004119527],"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":[0.00001398567,0.0001386199,0.008675978,0.0002849963,0.00002506831,0.000001638683,0.01167835,0.0002200536,0.008883378,0.5383649,0.0001336086,0.4315794],"study_design_scores_gemma":[0.0005411467,0.0001051997,0.002516729,0.00006335576,0.00001655092,0.00002531494,0.0000338355,0.6126906,0.00415673,0.3794216,0.0002730006,0.000155905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007030793,0.002784388,0.9880714,0.001356274,0.00001992728,0.0001590491,0.000003731528,0.0001454236,0.0004289876],"genre_scores_gemma":[0.5557181,0.0000136486,0.4442388,0.00001233787,0.000003579029,0.000004843248,0.000003581453,0.000001718509,0.000003349533],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6124706,"threshold_uncertainty_score":0.1965604,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}