{"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043443246,0.0027398174,0.9649716,0.0034729894,0.00043836617,0.000072174524,0.00010125069,0.0006847415,0.023174746],"genre_scores_gemma":[0.10910444,0.0044842935,0.8728415,0.000817676,0.00056346913,0.00022759322,0.0003536938,0.000497307,0.011110085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984131,0.0010262058,0.000103958206,0.00016018304,0.00022586608,0.00007068352],"domain_scores_gemma":[0.9986364,0.0008390363,0.000066511646,0.00021425082,0.00021260034,0.000031116888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002319196,0.0006491313,0.0006879511,0.0029088156,0.001662549,0.0050003123,0.0011265568,0.0017069458,0.008440513],"category_scores_gemma":[0.0041960785,0.0008869142,0.0009805453,0.003269722,0.005242516,0.0074267555,0.0028242012,0.0019847532,0.004532853],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080899576,0.00005814488,0.00022612422,0.00038412938,0.000025038085,0.00029458356,0.0010962683,0.0039110747,0.005376738,0.84786254,0.006335361,0.1343491],"study_design_scores_gemma":[0.000033933626,0.000053738564,0.00023715495,0.00013005036,0.000023458937,0.00044066226,0.000533872,0.028648457,0.00721441,0.9127493,0.049895022,0.00003984054],"about_ca_topic_score_codex":0.0014851665,"about_ca_topic_score_gemma":0.0018909231,"teacher_disagreement_score":0.008440513,"about_ca_system_score_codex":0.0010222436,"about_ca_system_score_gemma":0.001510561,"threshold_uncertainty_score":0.02823639},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038122762,0.004848077,0.86201525,0.0033127922,0.0052054455,0.0006429694,0.010299177,0.02153709,0.05401655],"genre_scores_gemma":[0.2592015,0.0036404955,0.66690004,0.00095455605,0.0015534223,0.0005857863,0.034956522,0.005610681,0.026596997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968874,0.0012054464,0.0002786055,0.0007499731,0.0006841851,0.00019444253],"domain_scores_gemma":[0.9895068,0.0052350666,0.0005020602,0.0017680097,0.0028162128,0.00017183645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015066938,0.0018612285,0.0019725112,0.0029082873,0.0021522401,0.0044415705,0.0019653281,0.002502593,0.022896731],"category_scores_gemma":[0.013598675,0.0011588626,0.0016333526,0.0035114284,0.001431201,0.004635796,0.0028021804,0.002777642,0.012440886],"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":[0.0008882449,0.00048553332,0.0006481786,0.0033460383,0.00023426027,0.0032357823,0.001665476,0.021310398,0.048906773,0.14666116,0.18117146,0.5914466],"study_design_scores_gemma":[0.00035703983,0.00045143752,0.0013114085,0.0008153106,0.00037630126,0.0027359964,0.0010065187,0.3425392,0.1040153,0.268793,0.27736637,0.00023209707],"about_ca_topic_score_codex":0.0015022863,"about_ca_topic_score_gemma":0.0015934979,"teacher_disagreement_score":0.022896731,"about_ca_system_score_codex":0.0012269387,"about_ca_system_score_gemma":0.0018458422,"threshold_uncertainty_score":0.076597214},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08368531,0.004751166,0.86830163,0.013505113,0.0005752726,0.00025378235,0.002042134,0.001004671,0.025880868],"genre_scores_gemma":[0.6980473,0.0049906382,0.26934397,0.0019098696,0.0033899527,0.0008609836,0.004942419,0.0017690953,0.014745825],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9847564,0.0069535784,0.00090588804,0.0023471448,0.0032993853,0.0017375649],"domain_scores_gemma":[0.7760564,0.20664836,0.0033016724,0.008820168,0.0036340645,0.0015392145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010068183,0.0018915866,0.003931131,0.0032184431,0.0024053426,0.009407007,0.0049419,0.0042814086,0.013222063],"category_scores_gemma":[0.100043185,0.0021052144,0.003775869,0.0055103637,0.004954841,0.02423318,0.0061806557,0.010156227,0.001979402],"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":[0.0013347461,0.0006514283,0.004574554,0.0012579004,0.00023648868,0.00051195285,0.0011708842,0.40436214,0.0015888755,0.43367434,0.03366266,0.116973944],"study_design_scores_gemma":[0.00006436505,0.00003850956,0.00051450904,0.000057512036,0.000039063547,0.00015926993,0.00014807076,0.4812514,0.000597914,0.5154575,0.0016346058,0.00003734607],"about_ca_topic_score_codex":0.005218279,"about_ca_topic_score_gemma":0.005499694,"teacher_disagreement_score":0.013222063,"about_ca_system_score_codex":0.00520528,"about_ca_system_score_gemma":0.004695951,"threshold_uncertainty_score":0.05324626},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10103918,0.0010610017,0.7478031,0.0027240305,0.0011406374,0.001031753,0.0012428623,0.124855414,0.019102046],"genre_scores_gemma":[0.32696995,0.0004554015,0.61438537,0.0013211038,0.0004101532,0.00079571875,0.002489549,0.030235574,0.022937177],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9893287,0.005963135,0.0009776169,0.0011840571,0.0020671522,0.00047939157],"domain_scores_gemma":[0.91537046,0.040610597,0.0032516995,0.017760726,0.020699162,0.0023072849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010186775,0.0020191167,0.0012999034,0.0024226569,0.0013170682,0.0034305349,0.002484897,0.0023208505,0.02442676],"category_scores_gemma":[0.05710834,0.0018933635,0.0011092472,0.002194168,0.0008757556,0.007805006,0.0035315074,0.003389133,0.0141649535],"study_design_candidate":"bench_or_experimental","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":[0.0026804123,0.0011951519,0.007819721,0.0012526829,0.00013363683,0.0005800332,0.0014847644,0.0066471333,0.0824338,0.009130913,0.05903308,0.82760864],"study_design_scores_gemma":[0.0012349515,0.0027504019,0.009457477,0.00044949012,0.0007932395,0.003325038,0.0012901999,0.2936416,0.5118759,0.0344213,0.14028007,0.00048034376],"about_ca_topic_score_codex":0.0013075679,"about_ca_topic_score_gemma":0.0027817106,"teacher_disagreement_score":0.02442676,"about_ca_system_score_codex":0.0010441467,"about_ca_system_score_gemma":0.0046602585,"threshold_uncertainty_score":0.08171564},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006437753,0.00047188334,0.98792225,0.00014826703,0.000119990415,0.000057531357,0.00020725407,0.003953703,0.0006812831],"genre_scores_gemma":[0.37064767,0.0007788675,0.6145535,0.0004329,0.00028865342,0.00071622775,0.0040956163,0.0016313577,0.0068551493],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99645823,0.002217133,0.00019514315,0.0005478479,0.00044535298,0.00013626448],"domain_scores_gemma":[0.9922271,0.004414101,0.00039194638,0.0016664059,0.0011878703,0.00011258102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029819102,0.0011883305,0.0017570348,0.0010666877,0.0008568317,0.0013103118,0.0020853062,0.0016352035,0.0031166538],"category_scores_gemma":[0.010683542,0.0010628257,0.0015789294,0.0015252045,0.0007327557,0.0021928144,0.0018198211,0.0029090731,0.0033698091],"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":[0.000558919,0.00033244822,0.0009888941,0.00037573226,0.0005720557,0.00030146656,0.00020685022,0.2845377,0.018035725,0.009712054,0.01840716,0.665971],"study_design_scores_gemma":[0.000014114233,0.00003371117,0.0001775496,0.000007801083,0.00002636368,0.000061385486,0.00001254275,0.9856309,0.0040161265,0.008662061,0.0013421801,0.000015290072],"about_ca_topic_score_codex":0.0028815798,"about_ca_topic_score_gemma":0.0046369247,"teacher_disagreement_score":0.0031166538,"about_ca_system_score_codex":0.00060539646,"about_ca_system_score_gemma":0.0013803153,"threshold_uncertainty_score":0.015770078},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103102475,0.0034738313,0.65236425,0.008625738,0.0073855706,0.000509668,0.06862,0.049234036,0.106684424],"genre_scores_gemma":[0.52500725,0.0023032706,0.33582813,0.0006536253,0.0009922974,0.0003168089,0.07504172,0.006300353,0.05355654],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990426,0.00031577802,0.00009389056,0.0002565211,0.0002104711,0.00008081446],"domain_scores_gemma":[0.99775606,0.0007075338,0.00012316693,0.00046550055,0.0008795362,0.00006808102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010056117,0.0007730615,0.0005257946,0.0016654023,0.0013255974,0.002480092,0.00059219834,0.0009403474,0.03354944],"category_scores_gemma":[0.0058700503,0.0005928354,0.0005515387,0.0020437778,0.00045335657,0.0027124123,0.0012636905,0.0013527431,0.021476598],"study_design_candidate":"not_applicable","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":[0.0007920467,0.00015944545,0.0030117068,0.0009198116,0.00011457796,0.001263115,0.001097011,0.011656643,0.029019497,0.05375557,0.32086608,0.57734436],"study_design_scores_gemma":[0.00025262518,0.0003302205,0.00821831,0.0003425138,0.00028508736,0.0012566275,0.0013709193,0.33724743,0.068648525,0.061043248,0.5208083,0.00019618259],"about_ca_topic_score_codex":0.007959601,"about_ca_topic_score_gemma":0.007262327,"teacher_disagreement_score":0.03354944,"about_ca_system_score_codex":0.0010082733,"about_ca_system_score_gemma":0.0023400423,"threshold_uncertainty_score":0.112234},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012870758,0.0012228006,0.70135915,0.0008727535,0.001713272,0.0008545605,0.02172454,0.22512543,0.034256805],"genre_scores_gemma":[0.06998738,0.00056885765,0.79801285,0.0006351957,0.00066768593,0.0014842872,0.07932874,0.01899421,0.030320846],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978363,0.00068518263,0.0001951216,0.00051305845,0.00053617544,0.00023412715],"domain_scores_gemma":[0.99799407,0.000573864,0.000111846995,0.00078761653,0.00041169135,0.000121020006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015195213,0.0029546292,0.002379322,0.0027692416,0.0016712013,0.004063199,0.0028575624,0.0018138033,0.046278283],"category_scores_gemma":[0.004462415,0.0013807301,0.0015108039,0.0027313824,0.00060514867,0.003093654,0.0036861731,0.0024611754,0.049600482],"study_design_candidate":"bench_or_experimental","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":[0.0019324531,0.00044863852,0.0008207777,0.0014416656,0.0003602485,0.00076990045,0.0002785976,0.0044915583,0.056220464,0.03734394,0.35011995,0.54577184],"study_design_scores_gemma":[0.0015717769,0.0013669342,0.0020337417,0.00034819456,0.00042203147,0.0023728646,0.00039066072,0.2766467,0.17834717,0.1008797,0.43531844,0.00030181083],"about_ca_topic_score_codex":0.001074052,"about_ca_topic_score_gemma":0.0018870619,"teacher_disagreement_score":0.046278283,"about_ca_system_score_codex":0.00068113767,"about_ca_system_score_gemma":0.001985114,"threshold_uncertainty_score":0.15481621},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030654768,0.00036911038,0.92875326,0.00046484714,0.00036887356,0.00086025184,0.005851702,0.01590016,0.016777067],"genre_scores_gemma":[0.213377,0.00052547007,0.74415946,0.00020821163,0.00012201832,0.00093486154,0.026853325,0.003931476,0.009888169],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992855,0.00015811133,0.00011547865,0.00020550712,0.00015078933,0.00008466229],"domain_scores_gemma":[0.9988625,0.00026616137,0.000069504764,0.00015010408,0.0005819851,0.00006962332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071472995,0.0012146692,0.0012228952,0.0035148624,0.0016010817,0.0024594234,0.0011881228,0.00066953426,0.013331406],"category_scores_gemma":[0.0027893134,0.0011106663,0.0011714163,0.003478239,0.0006847969,0.0025388424,0.0022569129,0.001414814,0.007554062],"study_design_candidate":"bench_or_experimental","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":[0.0006964793,0.00043620073,0.0039899074,0.0021261615,0.00019935425,0.0041114977,0.0026954308,0.01460752,0.1502956,0.14907087,0.08710958,0.58466136],"study_design_scores_gemma":[0.00035847997,0.00044405303,0.004691276,0.0004257676,0.0006945234,0.0026408504,0.0021339462,0.3754455,0.19161046,0.0999506,0.3213098,0.00029473362],"about_ca_topic_score_codex":0.0046816003,"about_ca_topic_score_gemma":0.007886292,"teacher_disagreement_score":0.013331406,"about_ca_system_score_codex":0.0012274226,"about_ca_system_score_gemma":0.0039397595,"threshold_uncertainty_score":0.044598043},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006968914,0.00056995585,0.9352546,0.0010362453,0.0008720128,0.00020004506,0.0012564244,0.009676233,0.044165626],"genre_scores_gemma":[0.2386493,0.00089413236,0.71542406,0.0011341742,0.000496116,0.00030158556,0.0031254946,0.0053713038,0.034603868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970066,0.0014839896,0.0002632462,0.00048382106,0.0005977761,0.0001645238],"domain_scores_gemma":[0.9954853,0.0017069409,0.00013059935,0.0016640836,0.00095386966,0.00005918067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017082561,0.00081687,0.0008194618,0.0014363286,0.0012441226,0.0023896361,0.0011233301,0.0016096283,0.0366308],"category_scores_gemma":[0.0104101505,0.00068944495,0.00077844155,0.0025647993,0.0009700379,0.004203098,0.0025987928,0.0016343071,0.019554993],"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":[0.0002367796,0.0001300301,0.0003553996,0.00090869743,0.00008635313,0.00072125555,0.0007983934,0.007300141,0.016712109,0.2378679,0.06973868,0.66514426],"study_design_scores_gemma":[0.00011553734,0.00014799339,0.0005345639,0.00031326842,0.00020296231,0.0018796095,0.00032940108,0.14495915,0.057566646,0.561829,0.23202164,0.00010021472],"about_ca_topic_score_codex":0.0011277238,"about_ca_topic_score_gemma":0.0013488613,"teacher_disagreement_score":0.0366308,"about_ca_system_score_codex":0.00054632383,"about_ca_system_score_gemma":0.001150266,"threshold_uncertainty_score":0.12254226},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012656979,0.023127476,0.07954898,0.03370966,0.7935155,0.00028003755,0.0020380346,0.00557165,0.060942892],"genre_scores_gemma":[0.009118924,0.020651951,0.03709964,0.013047982,0.60727155,0.0002521099,0.0058705476,0.007831653,0.2988557],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99701995,0.00054700184,0.0004219009,0.0006626668,0.0011397431,0.00020872668],"domain_scores_gemma":[0.98650926,0.0039019443,0.00066615245,0.0020892166,0.0056729573,0.0011604336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030202845,0.002346087,0.0023513932,0.0046962546,0.0018936023,0.0052045193,0.0023303297,0.0029319238,0.16901264],"category_scores_gemma":[0.0125939585,0.0008125741,0.0015810453,0.0035486408,0.0010223653,0.0063362066,0.0029737188,0.0045594214,0.0948416],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005760478,0.000042055504,0.00008546298,0.00043197648,0.000021508813,0.00013634418,0.000036534206,0.00016057567,0.0012602708,0.0025230716,0.8803322,0.1149125],"study_design_scores_gemma":[0.000009940013,0.000056904453,0.00030020895,0.00015096346,0.000022184911,0.0004288148,0.000032487467,0.00071889465,0.001227556,0.005117513,0.9919045,0.0000300246],"about_ca_topic_score_codex":0.00089773274,"about_ca_topic_score_gemma":0.0019543003,"teacher_disagreement_score":0.16901264,"about_ca_system_score_codex":0.0009567514,"about_ca_system_score_gemma":0.0017862006,"threshold_uncertainty_score":0.5654036},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022710482,0.00042271405,0.90474087,0.00028226041,0.0003989277,0.00039017687,0.00667253,0.060579263,0.0038026941],"genre_scores_gemma":[0.067322336,0.0003689145,0.9075293,0.00022431358,0.000086843975,0.00031593305,0.0148074785,0.0060249576,0.0033199154],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985713,0.00032030488,0.00035867142,0.00038796905,0.00027761637,0.00008413343],"domain_scores_gemma":[0.9940685,0.0018759196,0.00051371945,0.0015920199,0.0017553956,0.00019454802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002606715,0.0016427445,0.0014446451,0.0030687745,0.0010058264,0.0025860881,0.002144214,0.0013025072,0.009194428],"category_scores_gemma":[0.0057294695,0.0015022991,0.0012390027,0.003511168,0.00066259893,0.0035480037,0.0021465896,0.0015110824,0.013921952],"study_design_candidate":"bench_or_experimental","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":[0.00064776227,0.00042588197,0.0045694713,0.0014106422,0.0002923441,0.002026009,0.00069095864,0.0075755683,0.16892336,0.009498956,0.050383423,0.7535557],"study_design_scores_gemma":[0.0003464982,0.00052252493,0.008789343,0.0002993366,0.0008724215,0.0050222497,0.0009232895,0.40455756,0.38221884,0.02779903,0.16816278,0.000486039],"about_ca_topic_score_codex":0.0017393536,"about_ca_topic_score_gemma":0.0037741347,"teacher_disagreement_score":0.009194428,"about_ca_system_score_codex":0.0004765277,"about_ca_system_score_gemma":0.0021737732,"threshold_uncertainty_score":0.03075844},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038659018,0.0008216235,0.9219839,0.0006267181,0.001312724,0.0003420261,0.0032961585,0.024622727,0.008335003],"genre_scores_gemma":[0.12603785,0.00052320433,0.8511017,0.00022422256,0.00031806043,0.0002606301,0.008393636,0.0039330428,0.009207746],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99834514,0.00064253586,0.00024777374,0.00035832287,0.000288697,0.000117474585],"domain_scores_gemma":[0.99495846,0.0013354803,0.00020784406,0.0009093176,0.0024814168,0.00010759008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012368226,0.0021084042,0.0011467417,0.0017043866,0.0011237453,0.0019948313,0.0008943033,0.00069762074,0.013944941],"category_scores_gemma":[0.005473094,0.0005519444,0.0009084572,0.0021834904,0.0003872928,0.0016009476,0.0012272946,0.0018188701,0.016049307],"study_design_candidate":"bench_or_experimental","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":[0.0008858418,0.00041575864,0.0012758123,0.0008385934,0.00017822055,0.0007709028,0.0008544646,0.011413508,0.13497552,0.013230573,0.037865773,0.79729503],"study_design_scores_gemma":[0.00036387288,0.0008872119,0.0042176354,0.00018282446,0.00052083976,0.0015444619,0.001192793,0.46325538,0.3407238,0.026408296,0.16036834,0.00033443628],"about_ca_topic_score_codex":0.0036562977,"about_ca_topic_score_gemma":0.0073693544,"teacher_disagreement_score":0.013944941,"about_ca_system_score_codex":0.0004973943,"about_ca_system_score_gemma":0.0024252245,"threshold_uncertainty_score":0.04665053},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025714153,0.00017821645,0.93669754,0.00030263298,0.00025491763,0.00021041751,0.0008450493,0.032138433,0.0036585643],"genre_scores_gemma":[0.18375333,0.00015627609,0.7893629,0.00015979697,0.0001434401,0.0003278669,0.0029105714,0.0038430735,0.01934265],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981798,0.0005128578,0.0002596083,0.00042924457,0.00044462288,0.000173761],"domain_scores_gemma":[0.9963876,0.0015094843,0.00014609928,0.00064630865,0.001167184,0.00014325036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016232351,0.0011194891,0.0018710457,0.0010957938,0.001753035,0.0022064124,0.0015761092,0.0015205721,0.025341207],"category_scores_gemma":[0.0055716024,0.00087451556,0.0011396566,0.0014864277,0.0006753654,0.0020985953,0.0016310076,0.0017345845,0.012730131],"study_design_candidate":"bench_or_experimental","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":[0.0033536009,0.0005277111,0.0011661856,0.0011839494,0.0001330747,0.0016128046,0.0013424839,0.025775403,0.086574286,0.06262113,0.07692749,0.73878187],"study_design_scores_gemma":[0.00051864574,0.0008543474,0.0010634944,0.00016967216,0.00028163704,0.0011976317,0.0005434793,0.67248464,0.18659513,0.065351136,0.07068934,0.00025096256],"about_ca_topic_score_codex":0.003402582,"about_ca_topic_score_gemma":0.004037228,"teacher_disagreement_score":0.025341207,"about_ca_system_score_codex":0.0007660081,"about_ca_system_score_gemma":0.002220989,"threshold_uncertainty_score":0.08477479},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016806966,0.00068799267,0.90005994,0.0007089375,0.0005561421,0.00033456893,0.004713112,0.065902896,0.0102294935],"genre_scores_gemma":[0.10851419,0.00050814805,0.85024697,0.00039785728,0.0002919882,0.00032255868,0.016714374,0.008270195,0.0147337],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99567586,0.0012873436,0.0004209819,0.0013776498,0.0010146647,0.00022346115],"domain_scores_gemma":[0.9932213,0.0024118477,0.0002683086,0.0019420702,0.001880341,0.00027611348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003481609,0.0018446988,0.00221966,0.005649629,0.0020978574,0.0038494747,0.0031994649,0.00251119,0.030197147],"category_scores_gemma":[0.012482521,0.001479702,0.0017545826,0.005228509,0.0010559959,0.005715107,0.005807175,0.0023237949,0.022917923],"study_design_candidate":"bench_or_experimental","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":[0.0015493142,0.00037740127,0.0015411745,0.0010184915,0.00029357965,0.0016373403,0.0012236873,0.006150317,0.042981178,0.031768363,0.10804512,0.803414],"study_design_scores_gemma":[0.0006118783,0.0006732421,0.0021164753,0.00042555746,0.00060602394,0.0035027044,0.002408043,0.4500469,0.16245578,0.1671071,0.20962538,0.000420866],"about_ca_topic_score_codex":0.0032577221,"about_ca_topic_score_gemma":0.005131732,"teacher_disagreement_score":0.030197147,"about_ca_system_score_codex":0.00091751234,"about_ca_system_score_gemma":0.0029102282,"threshold_uncertainty_score":0.1010195},"labels":[],"label_agreement":null}]}