{"meta":{"query_hash":"0f8f2e53290b","filters":{"venue":"Machine Translation"},"cohort_total":14,"direct_labels_cover":0,"predictions_cover":14,"exported":14,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/0f8f2e53290b","api":"https://metacan.xera.ac/api/v1/cohort?venue=Machine+Translation"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computational linguistics; Computer science; Natural language processing; Artificial intelligence; Linguistics; Philosophy","score_opus":0.021196146565790542,"score_gpt":0.2848283274894695,"score_spread":0.26363218092367896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496822098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019080862,0.007793543,0.9587915,0.009847169,0.00007441137,0.00082970114,0.000028459131,0.0007337947,0.0028205672],"genre_scores_gemma":[0.93062085,0.000028992446,0.06833241,0.0005885129,0.000044381166,0.000081137216,0.00016477102,0.000030347457,0.000108613225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977119,0.00027162305,0.00048045808,0.00059504935,0.00049709796,0.0004438868],"domain_scores_gemma":[0.9992581,0.000060794337,0.000045050907,0.00048248758,0.000029431112,0.00012415826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007119485,0.00033176038,0.00027776737,0.0003643375,0.0001436864,0.00021024383,0.0008712162,0.00019653942,0.000024286745],"category_scores_gemma":[0.000009580794,0.00024084012,0.00013314704,0.0019461816,0.00006501223,0.0006492446,0.000021973196,0.00057362666,0.000007476006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016982964,0.00037156424,0.0008916122,0.00006294715,0.00002670666,0.000027853497,0.01699649,0.00023908657,0.012867082,0.009495369,0.00015193093,0.9586995],"study_design_scores_gemma":[0.0027892557,0.00031642764,0.004508833,0.0001097567,0.000057251436,0.00017202173,0.000074872034,0.967526,0.007739383,0.0101854475,0.005359944,0.0011607968],"about_ca_topic_score_codex":0.0010228168,"about_ca_topic_score_gemma":0.00065452536,"teacher_disagreement_score":0.96728694,"about_ca_system_score_codex":0.000058998856,"about_ca_system_score_gemma":0.00005227527,"threshold_uncertainty_score":0.98211753},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01603385525805243,"score_gpt":0.2694640035533037,"score_spread":0.25343014829525123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594980056","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047801305,0.010032861,0.97816277,0.0017903823,0.00006114943,0.00029428638,0.00002765272,0.00066195946,0.004188803],"genre_scores_gemma":[0.6954555,0.000049980194,0.30426678,0.00005870342,0.000019819961,0.0000072604844,0.000051401785,0.000009666592,0.000080871505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888134,0.00007826445,0.00033699794,0.00026546375,0.00027489342,0.00016301694],"domain_scores_gemma":[0.99943393,0.000057863403,0.000078722194,0.0003370426,0.000047611928,0.000044844903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023471509,0.00014676302,0.00016707394,0.00015923685,0.00009276344,0.000044454213,0.00040859808,0.00008712524,0.00024046673],"category_scores_gemma":[0.000005710932,0.00013426486,0.0000888576,0.00049658585,0.000034717785,0.00061653263,0.000007676796,0.00017204997,0.00001587436],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022143546,0.000054532196,0.00015844245,0.000027603866,0.000008211627,0.0000017796029,0.0008726231,0.00023350691,0.007526607,0.0044372953,0.000013774496,0.9866435],"study_design_scores_gemma":[0.0013083428,0.00016989603,0.001987987,0.000072750234,0.00004449279,0.000026818861,0.0000036887552,0.92294985,0.02312299,0.045432877,0.004434827,0.00044548354],"about_ca_topic_score_codex":0.00023733471,"about_ca_topic_score_gemma":0.00009701625,"teacher_disagreement_score":0.986198,"about_ca_system_score_codex":0.000017188804,"about_ca_system_score_gemma":0.000025445568,"threshold_uncertainty_score":0.5475162},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08034618598023999,"score_gpt":0.2992751910534103,"score_spread":0.21892900507317034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1702922849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007030793,0.0027843881,0.98807144,0.0013562738,0.000019927284,0.0001590491,0.000003731528,0.00014542359,0.00042898755],"genre_scores_gemma":[0.5557181,0.000013648602,0.4442388,0.000012337868,0.000003579029,0.0000048432476,0.0000035814526,0.0000017185095,0.0000033495326],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953806,0.00003136743,0.00013321036,0.0001254031,0.000111259185,0.000060669227],"domain_scores_gemma":[0.99972665,0.00003226801,0.00005401286,0.000105955594,0.00003991717,0.000041195268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020047242,0.00005430773,0.00007114062,0.000081661405,0.000059997496,0.000041936335,0.0000893715,0.00002424091,6.1189405e-7],"category_scores_gemma":[0.000019466706,0.0000482016,0.000008991887,0.00016826231,0.000049338214,0.00031753985,0.000029882587,0.00005125639,1.800233e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013985668,0.00013861991,0.008675978,0.00028499632,0.00002506831,0.0000016386832,0.011678351,0.00022005363,0.0088833785,0.53836495,0.00013360864,0.4315794],"study_design_scores_gemma":[0.00054114667,0.00010519974,0.0025167286,0.00006335576,0.00001655092,0.00002531494,0.000033835502,0.6126906,0.00415673,0.37942162,0.00027300062,0.00015590501],"about_ca_topic_score_codex":0.00012035786,"about_ca_topic_score_gemma":0.00006525796,"teacher_disagreement_score":0.61247057,"about_ca_system_score_codex":0.0000119698,"about_ca_system_score_gemma":0.000017331417,"threshold_uncertainty_score":0.19656043},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.04654180184988662,"score_gpt":0.2987353309047347,"score_spread":0.2521935290548481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982816048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02717088,0.0051256223,0.9594523,0.0056351856,0.00020657881,0.00075228664,0.0000032848475,0.0008421614,0.00081174425],"genre_scores_gemma":[0.68894833,0.0000062221575,0.31080475,0.00010259881,0.000036980633,0.000026989037,0.000012391009,0.00001200376,0.000049744132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984334,0.000106191364,0.000251754,0.00045766964,0.0005170719,0.00023387231],"domain_scores_gemma":[0.99936724,0.000038065755,0.00005007439,0.00033821826,0.0001258852,0.00008053579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058857934,0.00017974876,0.00014463124,0.0001922902,0.00016864823,0.0001127412,0.00043893838,0.0000743801,0.00008489517],"category_scores_gemma":[0.0000407049,0.00016874088,0.000040286843,0.0007097662,0.000016866743,0.00075531146,0.000014407505,0.00015963611,0.000035090765],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010304481,0.000068504945,0.0002284797,0.000027385135,0.000009318332,0.000001532343,0.0062246523,0.00010871612,0.015512147,0.00039363693,0.00010357906,0.97731173],"study_design_scores_gemma":[0.002341654,0.0003794775,0.010668601,0.00022619122,0.00011382138,0.00006135259,0.00002791976,0.63071316,0.29835996,0.014457866,0.040642153,0.0020078544],"about_ca_topic_score_codex":0.000020769294,"about_ca_topic_score_gemma":0.00018909997,"teacher_disagreement_score":0.9753039,"about_ca_system_score_codex":0.00005899472,"about_ca_system_score_gemma":0.00004708571,"threshold_uncertainty_score":0.68810534},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03837286427808482,"score_gpt":0.3087072662634866,"score_spread":0.27033440198540176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991522508","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038108524,0.002643156,0.9940985,0.0010295992,0.00009415862,0.0006231944,0.00007293227,0.0007327933,0.00032460975],"genre_scores_gemma":[0.47754598,0.0000057300053,0.52203727,0.00011766126,0.00003070821,0.000016689826,0.00021368686,0.000015173899,0.000017126571],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984132,0.00004611783,0.0004370854,0.00042156782,0.00036349404,0.00031853683],"domain_scores_gemma":[0.99913037,0.00029265494,0.000095613854,0.00027467223,0.0001153115,0.0000913608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085072406,0.00021127489,0.00018708044,0.00021079557,0.00017073305,0.0001070209,0.00036928212,0.00013606329,0.0000109790935],"category_scores_gemma":[0.00003757014,0.00019937965,0.00007979352,0.00033116576,0.000028094833,0.00079831923,0.0000133872345,0.00019948136,0.0000035721007],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012508544,0.000056360244,0.00005025417,0.00006846854,0.000009809788,0.0000026120654,0.0017332626,0.004027517,0.007938693,0.03031659,0.000033886594,0.95563745],"study_design_scores_gemma":[0.0008035268,0.000084087165,0.00008957044,0.000017095324,0.000021683085,0.0000054145253,0.0000061989317,0.94098884,0.004287011,0.05325133,0.00021759461,0.00022767413],"about_ca_topic_score_codex":0.00007412958,"about_ca_topic_score_gemma":0.00026747846,"teacher_disagreement_score":0.95540977,"about_ca_system_score_codex":0.000050742015,"about_ca_system_score_gemma":0.000049744907,"threshold_uncertainty_score":0.8130466},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.019574542661990844,"score_gpt":0.28103619519751294,"score_spread":0.2614616525355221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005440678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007307342,0.008479242,0.97088224,0.01854588,0.00008369312,0.00048247277,0.000004982036,0.00041209153,0.00037869313],"genre_scores_gemma":[0.59351873,0.000027022319,0.40591612,0.0001664096,0.000115735405,0.000052544852,0.000019901408,0.000013956443,0.00016955525],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991186,0.000041125833,0.00021824763,0.0002361459,0.0001811489,0.00020472298],"domain_scores_gemma":[0.99940616,0.00017029366,0.00007168377,0.0002680779,0.00005165946,0.000032127446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038985314,0.00012913937,0.00008967454,0.000055054497,0.00027723523,0.00018798659,0.0004711828,0.00006730104,0.000017303866],"category_scores_gemma":[0.000011579669,0.000089703884,0.000084267165,0.00014248992,0.000026924006,0.000307146,0.00001149498,0.00011890247,0.000012714896],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024904759,0.000017075201,0.00013775415,0.000013163311,0.000006041867,3.5461258e-7,0.00044701074,0.000031599026,0.00086770585,0.004845115,0.00012753824,0.99348176],"study_design_scores_gemma":[0.0025512502,0.00028718554,0.002584002,0.000101053854,0.00006191186,0.000042963016,0.0000061869227,0.78296477,0.034287356,0.036617976,0.13967459,0.000820764],"about_ca_topic_score_codex":0.000009460629,"about_ca_topic_score_gemma":0.0001651722,"teacher_disagreement_score":0.992661,"about_ca_system_score_codex":0.000025024481,"about_ca_system_score_gemma":0.000014228049,"threshold_uncertainty_score":0.36580184},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.020245452710936356,"score_gpt":0.25645432421122505,"score_spread":0.2362088715002887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034060496","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004666453,0.014318681,0.97388,0.0033800646,0.00009823739,0.0003294542,0.000012496922,0.0014174621,0.0018971602],"genre_scores_gemma":[0.6529948,0.000036930218,0.34643522,0.00024007655,0.000052748077,0.00001235756,0.0000690949,0.000019402592,0.0001393563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982793,0.00012553843,0.0003657688,0.0004723388,0.0004704198,0.00028665166],"domain_scores_gemma":[0.99917173,0.000084466184,0.0001147166,0.00048582745,0.000056966408,0.00008628315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035109543,0.00024302713,0.00022104109,0.00024508536,0.0004483384,0.000068367524,0.0006635877,0.00013317341,0.00004184532],"category_scores_gemma":[0.000019251402,0.0002207855,0.00011297569,0.000664322,0.000057933295,0.0008687941,0.00004309695,0.00033173358,0.000016269874],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051601393,0.00012506374,0.0005387952,0.00005415137,0.000019870451,0.00004018238,0.0043374435,0.00023807025,0.012370414,0.0033696182,0.00033549056,0.9785193],"study_design_scores_gemma":[0.0018380044,0.00032388928,0.0014656063,0.00010374615,0.000041186428,0.00028966466,0.000005851084,0.9002522,0.054939155,0.014125423,0.025661256,0.0009540036],"about_ca_topic_score_codex":0.0001126938,"about_ca_topic_score_gemma":0.00006439977,"teacher_disagreement_score":0.9775653,"about_ca_system_score_codex":0.00003739683,"about_ca_system_score_gemma":0.000038059796,"threshold_uncertainty_score":0.9003371},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.019152476021540424,"score_gpt":0.2812119978952083,"score_spread":0.2620595218736679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037632172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008485733,0.01072589,0.97859186,0.00044225086,0.000097881944,0.0008600344,0.00005347716,0.0004729927,0.00026988008],"genre_scores_gemma":[0.57365596,0.00003315458,0.42612046,0.000020648218,0.000048170208,0.000055628498,0.000047359084,0.000010524073,0.000008094878],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988622,0.000046087804,0.00037634015,0.00036158302,0.00019383471,0.00015995615],"domain_scores_gemma":[0.9991922,0.0001665837,0.00016812989,0.00026937368,0.00015330254,0.00005040741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022157554,0.00018331101,0.00021679413,0.00019585421,0.00013980216,0.00006441427,0.00024707417,0.00011430968,0.0000130195285],"category_scores_gemma":[0.00004124715,0.0001684892,0.00007785522,0.00039897408,0.00007274682,0.0005832143,0.000015426647,0.0001496352,7.6057495e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030631047,0.000067635825,0.0009899135,0.00014017256,0.00001522271,2.9160185e-7,0.0038000229,0.000051174437,0.006574819,0.0048852935,0.000004893084,0.9834399],"study_design_scores_gemma":[0.0014392325,0.0001155547,0.00029427462,0.00002916369,0.000031477273,0.000015465674,0.000016393025,0.9619344,0.009314737,0.025911978,0.0006397358,0.00025758572],"about_ca_topic_score_codex":0.000028642691,"about_ca_topic_score_gemma":0.00004906083,"teacher_disagreement_score":0.9831824,"about_ca_system_score_codex":0.000016503922,"about_ca_system_score_gemma":0.000014392836,"threshold_uncertainty_score":0.6870791},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0072064830078437106,"score_gpt":0.2440312977121587,"score_spread":0.236824814704315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063381274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022651528,0.005590333,0.98702216,0.0014776931,0.000053364474,0.000080700556,0.0000031129834,0.00054290285,0.0029646081],"genre_scores_gemma":[0.6247342,0.0000018474492,0.3750406,0.00006293669,0.000028236162,0.0000024414253,0.000024206349,0.0000055038886,0.00010000309],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932086,0.000030425022,0.00014415338,0.00020300927,0.00016689,0.00013466657],"domain_scores_gemma":[0.99970895,0.000026967255,0.000045011155,0.0001787253,0.000020476095,0.000019899135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012861277,0.000092257775,0.00007522603,0.00006864731,0.00007722838,0.00011335045,0.00028617866,0.000047105783,0.000010014981],"category_scores_gemma":[0.0000040750488,0.000082408726,0.000033018518,0.00023863293,0.000013795571,0.00045582483,0.000013815704,0.000101449376,0.000008940297],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035320652,0.00003138753,0.0005340062,0.000008955718,0.0000020098507,0.0000034987415,0.00012983897,0.000017589216,0.05022648,0.0072450666,0.00086463045,0.940933],"study_design_scores_gemma":[0.0009566608,0.0000973202,0.0018130591,0.00005803419,0.000020217374,0.000037744514,0.0000029371345,0.55360836,0.26822704,0.15438238,0.020077351,0.0007188659],"about_ca_topic_score_codex":0.00022731042,"about_ca_topic_score_gemma":0.00007291936,"teacher_disagreement_score":0.94021416,"about_ca_system_score_codex":0.000018736808,"about_ca_system_score_gemma":0.000009633007,"threshold_uncertainty_score":0.336053},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Computational linguistics; Natural language processing; Artificial intelligence","score_opus":0.0073987869319434,"score_gpt":0.25830550127037893,"score_spread":0.25090671433843553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081743236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001220826,0.000054362492,0.95444626,0.03960184,0.00077187596,0.00015906454,0.0000016437405,0.000564429,0.0031796917],"genre_scores_gemma":[0.44314632,7.145468e-7,0.5340157,0.0014176912,0.021192899,0.000009093015,0.000024577279,0.000013467104,0.00017949328],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99919045,0.000053381016,0.00013488342,0.000284724,0.00020542629,0.00013114054],"domain_scores_gemma":[0.99958146,0.000034135905,0.000040917006,0.000244662,0.000056255103,0.000042545667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030031847,0.000094936135,0.00008278593,0.00014283026,0.00009164094,0.0000986639,0.0002778822,0.0000415986,0.00007358854],"category_scores_gemma":[0.000089776804,0.000085473715,0.000026987933,0.00026110563,0.000007360033,0.00032804336,0.000020534804,0.00013725922,0.000120506054],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011794822,0.00001384757,0.000018894623,0.0000075332387,0.0000013736902,5.6285387e-7,0.00055837486,0.00010539373,0.0044496185,0.01267004,0.0026669607,0.9794956],"study_design_scores_gemma":[0.0007094668,0.0010086953,0.0015049733,0.000075049815,0.000015666174,0.000025701456,0.000013221177,0.20629416,0.12529789,0.03218264,0.632173,0.00069954846],"about_ca_topic_score_codex":0.00002803348,"about_ca_topic_score_gemma":0.00003117161,"teacher_disagreement_score":0.97879606,"about_ca_system_score_codex":0.000024219025,"about_ca_system_score_gemma":0.0000057923767,"threshold_uncertainty_score":0.3485517},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.015257152663782294,"score_gpt":0.27391012940859066,"score_spread":0.25865297674480836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118491422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007536123,0.00029161168,0.9866029,0.0037572016,0.000031658168,0.0007753949,0.000035282366,0.0009107676,0.00005905808],"genre_scores_gemma":[0.50773585,9.514543e-7,0.49154118,0.0004172364,0.000015908961,0.00012097581,0.00015495635,0.00000993695,0.0000029749003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985995,0.000050556457,0.00026279845,0.00051431044,0.00028847402,0.0002843444],"domain_scores_gemma":[0.99920964,0.00017847477,0.00011253662,0.00032295656,0.0000911909,0.00008522374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030099705,0.00020959954,0.00022343166,0.00010012235,0.00016328893,0.00010601725,0.00043152255,0.0001271923,0.0000115815465],"category_scores_gemma":[0.000038571998,0.00015104696,0.000054133,0.0003136196,0.00009764548,0.00024799656,0.00002382593,0.00022060562,0.000007129286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017345733,0.0011144563,0.001840384,0.00019588078,0.000041537736,0.0002807137,0.0003996064,0.008202186,0.07013679,0.400562,0.00014295417,0.5153489],"study_design_scores_gemma":[0.0062485854,0.0020215781,0.002035445,0.00007478643,0.000057140413,0.00017855376,0.000003882801,0.7244746,0.039294258,0.22413144,0.0007057575,0.00077396847],"about_ca_topic_score_codex":0.000056173627,"about_ca_topic_score_gemma":0.000019404473,"teacher_disagreement_score":0.7162724,"about_ca_system_score_codex":0.000065557724,"about_ca_system_score_gemma":0.0000589561,"threshold_uncertainty_score":0.61595166},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.017936208754936653,"score_gpt":0.2589407352169916,"score_spread":0.24100452646205497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132891320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020977503,0.00199661,0.9927237,0.00066241814,0.00025314852,0.0010267246,0.00017010169,0.000815897,0.00025365409],"genre_scores_gemma":[0.54306346,0.0000051706415,0.4564219,0.00019221017,0.000037896538,0.0000703718,0.00016613227,0.000023325778,0.000019501684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816364,0.00008320974,0.00043398706,0.0005999027,0.00031235078,0.00040691614],"domain_scores_gemma":[0.9990577,0.00014866507,0.000108456494,0.00036892894,0.00016487871,0.00015137225],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047655552,0.0002877464,0.00024871062,0.00016563162,0.00016641071,0.00013505615,0.00054151996,0.00012761942,0.000031590527],"category_scores_gemma":[0.00007625814,0.00027067395,0.00008357627,0.00033323155,0.000028783183,0.00074947404,0.00003523957,0.00022346401,0.0000033964316],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033791197,0.00014491545,0.00009739576,0.000106123625,0.000027849086,0.000004907332,0.008171529,0.00001683415,0.03843059,0.0047553317,0.0001564866,0.94775015],"study_design_scores_gemma":[0.003297725,0.0013993545,0.00086174725,0.00012069121,0.00010793791,0.000018323964,0.0000506148,0.87109476,0.09379132,0.02445987,0.003411572,0.0013860556],"about_ca_topic_score_codex":0.00035804455,"about_ca_topic_score_gemma":0.00021419479,"teacher_disagreement_score":0.94636405,"about_ca_system_score_codex":0.00006485869,"about_ca_system_score_gemma":0.0000349769,"threshold_uncertainty_score":0.99997455},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.0330547707272114,"score_gpt":0.2821371979595065,"score_spread":0.24908242723229507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145084016","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00285655,0.001382698,0.9924081,0.00079316396,0.00011479959,0.0005877545,0.000013291064,0.0013573071,0.00048634017],"genre_scores_gemma":[0.51206225,0.0000040938717,0.4876647,0.00006787482,0.00006780553,0.000024466402,0.00008019988,0.000011091262,0.00001752666],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887735,0.000086085405,0.00031243378,0.00033671223,0.0001806689,0.00020678272],"domain_scores_gemma":[0.99943703,0.000104472165,0.00007670991,0.00026293405,0.000072775976,0.000046066252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035028093,0.00016348119,0.00018296638,0.00013958025,0.00020805938,0.00015104646,0.00036791217,0.00008899545,0.000020484405],"category_scores_gemma":[0.0000028153183,0.00015765603,0.00008593843,0.00035512308,0.000017121609,0.00060651766,0.0000074868426,0.00012277029,0.000014465141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039903985,0.000022465458,0.00003697046,0.000133521,0.000008770658,0.0000010809946,0.0005703074,0.0007377783,0.0013737445,0.011217508,0.000022103386,0.98583585],"study_design_scores_gemma":[0.00069799565,0.000086102045,0.00025819548,0.00010486793,0.000015919359,0.000018353934,0.0000031416084,0.98993534,0.0012456953,0.003159755,0.0042698486,0.00020479973],"about_ca_topic_score_codex":0.00006191944,"about_ca_topic_score_gemma":0.00002738404,"teacher_disagreement_score":0.98919755,"about_ca_system_score_codex":0.000040450424,"about_ca_system_score_gemma":0.000020387308,"threshold_uncertainty_score":0.6429026},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.029544977834232312,"score_gpt":0.3163444565220911,"score_spread":0.28679947868785877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159939228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06154811,0.0009847915,0.9314224,0.0042948895,0.00026899396,0.00037612638,0.000025900872,0.00069013186,0.00038862342],"genre_scores_gemma":[0.5630591,0.000002309746,0.43653506,0.00026091567,0.0000762755,0.000014247832,0.000025014851,0.000011611465,0.000015512715],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985979,0.000060373364,0.00026669615,0.00046508847,0.00036389532,0.00024599742],"domain_scores_gemma":[0.9991968,0.00015141926,0.000046519923,0.00041478788,0.0000744154,0.000116038726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003212969,0.00017772095,0.00016235425,0.00018492385,0.00011128292,0.00015982141,0.00059510855,0.00012752751,0.0001052398],"category_scores_gemma":[0.000028644274,0.00016026595,0.0000761799,0.0005074627,0.00003126936,0.0005773023,0.000017468992,0.0004660957,0.000028341092],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036513695,0.000034411984,0.00028156003,0.000009976707,0.000008019718,0.000005124614,0.003949223,0.00003283112,0.20611456,0.0027763625,0.000023254923,0.78672814],"study_design_scores_gemma":[0.0030514984,0.00038425095,0.0056571634,0.00011428598,0.000060131857,0.000030028152,0.000031247982,0.52989453,0.312847,0.12742224,0.019036828,0.0014708082],"about_ca_topic_score_codex":0.0004891935,"about_ca_topic_score_gemma":0.002051932,"teacher_disagreement_score":0.78525734,"about_ca_system_score_codex":0.000015645293,"about_ca_system_score_gemma":0.000091164286,"threshold_uncertainty_score":0.65354556},"labels":[],"label_agreement":null}]}