{"meta":{"query_hash":"a762c0bd551b","filters":{"venue":"ACM Transactions on Asian and Low-Resource Language Information Processing"},"cohort_total":28,"direct_labels_cover":0,"predictions_cover":28,"exported":28,"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/a762c0bd551b","api":"https://metacan.xera.ac/api/v1/cohort?venue=ACM+Transactions+on+Asian+and+Low-Resource+Language+Information+Processing"},"results":[{"id":"W2765190181","doi":"10.1145/3133323","title":"Linguistic-Relationships-Based Approach for Improving Word Alignment","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Vietnamese; Computer science; Word (group theory); Natural language processing; Machine translation; Phrase; Artificial intelligence; Linguistics; Quality (philosophy); Bilingual dictionary","score_opus":0.015150148058170393,"score_gpt":0.26381645205486953,"score_spread":0.24866630399669915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765190181","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":[0.0004141963,0.0002736195,0.9951474,0.001010773,0.00006547687,0.00045721416,0.000016554459,0.0005357395,0.0020790212],"genre_scores_gemma":[0.5749272,7.649986e-7,0.42442766,0.00042113705,0.000036719004,0.000079346064,0.000022678292,0.000010996139,0.00007352574],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986545,0.000037404756,0.00038485907,0.00030314073,0.00030162762,0.00031849876],"domain_scores_gemma":[0.9982789,0.00009485324,0.00042487198,0.0009345651,0.0001368173,0.00012998821],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005039948,0.0002360678,0.00018563999,0.00029367785,0.0020883558,0.0018280894,0.0011157643,0.00015490453,0.0000054304383],"category_scores_gemma":[0.000527277,0.00021652994,0.00007917204,0.00015862382,0.0000991492,0.0020094663,0.000037991173,0.00037488362,0.000004335393],"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":[0.00003073807,0.000049454957,0.000012470658,0.0003816616,0.000008359399,0.0000016494058,0.008379301,0.00039933782,0.00015382197,0.0007064222,0.00001644607,0.98986036],"study_design_scores_gemma":[0.0025402803,0.00018977466,0.00024488312,0.00058377365,0.0000934493,0.00004323237,0.0044236225,0.9546574,0.028830511,0.0032448429,0.004017049,0.0011311898],"about_ca_topic_score_codex":0.0000212658,"about_ca_topic_score_gemma":0.0000050642993,"teacher_disagreement_score":0.9887291,"about_ca_system_score_codex":0.00007325741,"about_ca_system_score_gemma":0.000099988014,"threshold_uncertainty_score":0.9992108},"labels":[],"label_agreement":null},{"id":"W2792210162","doi":"10.1145/3160488","title":"Expanding Paraphrase Lexicons by Exploiting Generalities","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Japan Society for the Promotion of Science","keywords":"Paraphrase; Computer science; Natural language processing; Lexicon; Artificial intelligence; Leverage (statistics); Task (project management); Substitution (logic); Set (abstract data type); Semantic equivalence","score_opus":0.00916648332078006,"score_gpt":0.2578009485067484,"score_spread":0.24863446518596832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792210162","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":[0.020703917,0.00088307017,0.9735418,0.0013599165,0.00006903638,0.00016797107,0.000018177225,0.0010522143,0.0022039213],"genre_scores_gemma":[0.873732,0.000011207049,0.12324106,0.0026525373,0.00007338414,0.000036208043,0.00002219495,0.00001584077,0.00021560572],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99858505,0.000051844112,0.00039951788,0.00027281768,0.00031629435,0.00037449997],"domain_scores_gemma":[0.99903375,0.0000570157,0.00021015825,0.00046022382,0.0000974963,0.00014133484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002648619,0.0002433932,0.00017917313,0.0003721497,0.0008394205,0.0009655566,0.00064163527,0.00012537358,0.000048046182],"category_scores_gemma":[0.000077798104,0.00022401888,0.00005539541,0.0005167248,0.00016297161,0.0035941943,0.000037765694,0.000307651,0.000025793412],"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":[0.000015250345,0.00002779811,0.000006781557,0.000112250396,0.000011234506,0.0000039081497,0.031435985,0.0000079094525,0.0033878987,0.00042655604,0.00043442613,0.96413],"study_design_scores_gemma":[0.0022204188,0.00048153728,0.000037081445,0.0016899722,0.000067860725,0.00039865074,0.05933669,0.04364179,0.8642846,0.005670622,0.02002742,0.0021433646],"about_ca_topic_score_codex":0.000021453992,"about_ca_topic_score_gemma":0.0000057028924,"teacher_disagreement_score":0.96198666,"about_ca_system_score_codex":0.00005352883,"about_ca_system_score_gemma":0.000050806357,"threshold_uncertainty_score":0.93108845},"labels":[],"label_agreement":null},{"id":"W2901907079","doi":"10.1145/3236391","title":"Arabic Authorship Attribution","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Cybercrime; Computer science; Anonymity; Authorship attribution; The Internet; Identity (music); Cyberspace; Online identity; Stylometry; Artificial intelligence; Computer security; World Wide Web","score_opus":0.013757917713083193,"score_gpt":0.2626968309772169,"score_spread":0.24893891326413373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901907079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018952882,0.000073526804,0.97439504,0.0029187424,0.00014877049,0.00017472281,0.000012113085,0.00047365707,0.0028505668],"genre_scores_gemma":[0.9840354,0.0000037785996,0.013743331,0.0017219197,0.000088971516,0.00001731835,0.00003139912,0.000008987851,0.00034890274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859816,0.00009553627,0.0003876652,0.00024420896,0.0003193708,0.00035503262],"domain_scores_gemma":[0.9989685,0.000049086157,0.00017986847,0.00046600463,0.00014343862,0.00019313126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057892717,0.00019738749,0.00015234688,0.00032798504,0.0008525276,0.0005619516,0.0004946513,0.00017166951,0.00010469907],"category_scores_gemma":[0.00009618451,0.00018440363,0.0000606067,0.0007340889,0.00011978713,0.0023903074,0.000023822373,0.0003666255,0.00025654517],"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":[0.00002663063,0.00002658871,0.00002610321,0.00006514576,0.000008228041,0.0000017664443,0.021325715,0.00004127606,0.00017776283,0.0021198778,0.0000557575,0.9761251],"study_design_scores_gemma":[0.007274581,0.0016765599,0.013005942,0.002138456,0.00019498165,0.0008314048,0.03869624,0.46273968,0.18709378,0.010302233,0.27160254,0.0044436017],"about_ca_topic_score_codex":0.000007455498,"about_ca_topic_score_gemma":0.000005488002,"teacher_disagreement_score":0.97168154,"about_ca_system_score_codex":0.000063541476,"about_ca_system_score_gemma":0.000073380565,"threshold_uncertainty_score":0.7519762},"labels":[],"label_agreement":null},{"id":"W2910606374","doi":"10.1145/3265752","title":"Low-Resource Machine Transliteration Using Recurrent Neural Networks","year":2019,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Transliteration; Computer science; Grapheme; Pronunciation; Artificial intelligence; Machine translation; Word error rate; Natural language processing; Speech recognition; Artificial neural network; Vietnamese; Translation (biology); Recurrent neural network; Sequence (biology); Linguistics","score_opus":0.006320644909480506,"score_gpt":0.24000113453451388,"score_spread":0.23368048962503338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910606374","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":[0.02684149,0.0013643185,0.96901345,0.00081069896,0.0001355123,0.00046688723,0.000014155926,0.0007771547,0.00057635864],"genre_scores_gemma":[0.9381686,0.000008525964,0.059866548,0.001700868,0.000057130124,0.00001941433,0.000067001085,0.000026118096,0.000085800195],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980242,0.00010015896,0.00058558583,0.00039512134,0.0004496262,0.0004452729],"domain_scores_gemma":[0.9987193,0.00006433873,0.0002980771,0.0006553811,0.000096913056,0.00016600026],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00033639584,0.00035956036,0.0002825147,0.00047487236,0.0004738464,0.0010676489,0.0007737539,0.00020663737,0.00005708016],"category_scores_gemma":[0.000031877364,0.000326484,0.00010667633,0.00075740117,0.00006035813,0.0036609285,0.00003809625,0.00067566335,0.000015515987],"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":[0.00004608478,0.0000534301,0.000015344556,0.00025413398,0.000011894562,0.000005080989,0.011350599,0.0066264654,0.00055477896,0.00011238499,0.000014659131,0.9809551],"study_design_scores_gemma":[0.00075203256,0.00011497252,0.00002759383,0.0004989898,0.000024320436,0.00011988203,0.0013502202,0.9900193,0.0053501646,0.00011521793,0.0011385223,0.00048873987],"about_ca_topic_score_codex":0.000015571952,"about_ca_topic_score_gemma":0.000006204365,"teacher_disagreement_score":0.9833929,"about_ca_system_score_codex":0.00009528218,"about_ca_system_score_gemma":0.00004993688,"threshold_uncertainty_score":0.99996936},"labels":[],"label_agreement":null},{"id":"W3096542808","doi":"10.1145/3402884","title":"Condition-Transforming Variational Autoencoder for Generating Diverse Short Text Conversations","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Natural Science Foundation of China","keywords":"Latent variable; Autoencoder; Sequence (biology); Dependency (UML); Conditional probability distribution; Computer science; Artificial intelligence; Gaussian; Latent variable model; Pattern recognition (psychology); Transformation (genetics); Variable (mathematics); Multivariate normal distribution; Multivariate statistics; Algorithm; Mathematics; Statistics; Machine learning","score_opus":0.01530751449655362,"score_gpt":0.2482199830368645,"score_spread":0.23291246854031086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096542808","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":[0.0034282212,0.000024638834,0.9905109,0.0044579557,0.000063852865,0.00033599336,0.000045337318,0.00025559872,0.0008775121],"genre_scores_gemma":[0.7959271,0.0000022524648,0.19986281,0.003944876,0.000084338346,0.000057138575,0.00007734136,0.000009789804,0.00003432815],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988826,0.00002344787,0.00038486335,0.00022958517,0.00026163005,0.00021785487],"domain_scores_gemma":[0.99936926,0.000081002756,0.000101274876,0.00020540615,0.00010016861,0.00014289474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015617648,0.00015903209,0.00013679313,0.00015351005,0.00070311426,0.00043729282,0.00031671487,0.00008519393,0.00006238711],"category_scores_gemma":[0.0000722812,0.00016363249,0.000065804525,0.00026623203,0.0000341721,0.0025182138,0.000013288438,0.0001884801,0.000015657186],"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":[0.000018648941,0.000027250417,0.000018565406,0.00020495475,0.000029638806,0.0000017173992,0.07419676,0.05406592,0.00049716374,0.0018598695,0.00007278075,0.86900675],"study_design_scores_gemma":[0.0005826923,0.000040506024,0.0000448192,0.00005493784,0.000022233737,0.000012336051,0.008427579,0.98725975,0.0009409731,0.00013268455,0.0022723402,0.00020918135],"about_ca_topic_score_codex":0.000006928672,"about_ca_topic_score_gemma":0.0000040353425,"teacher_disagreement_score":0.9331938,"about_ca_system_score_codex":0.000043220934,"about_ca_system_score_gemma":0.00010158192,"threshold_uncertainty_score":0.6672739},"labels":[],"label_agreement":null},{"id":"W3165505241","doi":"10.1145/3446678","title":"Two New Large Corpora for Vietnamese Aspect-based Sentiment Analysis at Sentence Level","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Benchmark (surveying); Vietnamese; Natural language processing; Artificial intelligence; Task (project management); Sentence; Deep learning; Sentiment analysis; Resource (disambiguation); Code (set theory); Linguistics","score_opus":0.01779395492959392,"score_gpt":0.27241162286545834,"score_spread":0.25461766793586443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165505241","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":[0.009837416,0.00019439579,0.9866713,0.0022876782,0.000058854952,0.00015845717,0.00003836281,0.0001253368,0.00062816986],"genre_scores_gemma":[0.89596397,0.000006318792,0.09920857,0.0027173143,0.000046911606,0.000026254782,0.0002513081,0.000013076034,0.0017662637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984533,0.000045860896,0.00045900894,0.00033165584,0.00039250441,0.00031766127],"domain_scores_gemma":[0.9987973,0.00006862088,0.0002746754,0.00053815,0.0001376209,0.0001836418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027157774,0.0002070092,0.00027173944,0.00047925388,0.0006038231,0.0006147194,0.00034438143,0.000065550834,0.00022685711],"category_scores_gemma":[0.000038181322,0.00020007683,0.0002503034,0.0013782093,0.000026519703,0.0010322845,0.000032802447,0.0001357408,0.000030449228],"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":[0.00009600146,0.00033007225,0.0007824018,0.00026783592,0.0006969546,0.000025443904,0.037367824,0.018625284,0.0012005825,0.0006663552,0.0007429473,0.9391983],"study_design_scores_gemma":[0.0035535197,0.00007131267,0.001014057,0.00020323087,0.0005543367,0.000027739203,0.016347047,0.94143885,0.02609161,0.00010177575,0.009952578,0.00064391375],"about_ca_topic_score_codex":0.000017101127,"about_ca_topic_score_gemma":0.00008948804,"teacher_disagreement_score":0.9385544,"about_ca_system_score_codex":0.0000818396,"about_ca_system_score_gemma":0.00014709642,"threshold_uncertainty_score":0.81588966},"labels":[],"label_agreement":null},{"id":"W3208515366","doi":"10.1145/3467019","title":"Blockchain-based Framework for Reducing Fake or Vicious News Spread on Social Media/Messaging Platforms","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Accountability; Transparency (behavior); Internet privacy; Social media; Virtuous circle and vicious circle; Immutability; Computer security; Business; Computer science; Public relations; Political science; Blockchain; World Wide Web; Law; Economics","score_opus":0.014490928464158195,"score_gpt":0.26339360883018675,"score_spread":0.24890268036602856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208515366","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":[0.05322408,0.000079210615,0.9385755,0.006511456,0.00007915219,0.00029323032,0.00002937347,0.0004968257,0.0007111661],"genre_scores_gemma":[0.91923493,0.000004421293,0.07755245,0.0029194164,0.00006350466,0.00012875296,0.000030976473,0.000017076909,0.000048473215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986103,0.000021832695,0.0004152647,0.00033323775,0.00026495437,0.00035439755],"domain_scores_gemma":[0.9987023,0.00033276825,0.00021114902,0.00054476294,0.00010783626,0.000101169426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021737955,0.00022985549,0.00023164549,0.00031363455,0.0010741353,0.00034919515,0.000498947,0.000291824,0.000033097298],"category_scores_gemma":[0.0002095281,0.00020394952,0.00009044843,0.0006906599,0.00008644745,0.00024061445,0.000022228418,0.0005122626,0.000010436983],"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":[0.00005317412,0.00010249244,0.0000021450087,0.00015044954,0.000016054195,0.000006234593,0.026273001,0.0011722862,0.000058782643,0.0051474343,0.000057418547,0.96696055],"study_design_scores_gemma":[0.008618547,0.00056552904,0.00046506381,0.0028433264,0.00022514233,0.00035211822,0.15086958,0.6485045,0.10910336,0.04086172,0.03441584,0.0031752784],"about_ca_topic_score_codex":0.0000066543907,"about_ca_topic_score_gemma":0.00003630515,"teacher_disagreement_score":0.96378523,"about_ca_system_score_codex":0.00006286272,"about_ca_system_score_gemma":0.00015865298,"threshold_uncertainty_score":0.831682},"labels":[],"label_agreement":null},{"id":"W4200314022","doi":"10.1145/3487057","title":"Joined Type Length Encoding for Nested Named Entity Recognition","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Named-entity recognition; Encoding (memory); Leverage (statistics); Artificial intelligence; Sequence (biology); Pattern recognition (psychology); Natural language processing; Task (project management); Genetics","score_opus":0.018109367999372884,"score_gpt":0.24983490658388774,"score_spread":0.23172553858451486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200314022","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":[0.040654745,0.00008539183,0.95554143,0.0012231475,0.00013671773,0.00018474787,0.000009403246,0.00022489835,0.0019394908],"genre_scores_gemma":[0.9260691,0.000011962895,0.07249438,0.0010905738,0.00004818619,0.00002640916,0.00006592532,0.0000092794935,0.00018422693],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990836,0.000035597546,0.00030252914,0.0001970583,0.00018153817,0.00019972656],"domain_scores_gemma":[0.9992535,0.00006248552,0.00012045177,0.0003122326,0.00017149346,0.00007980039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019616589,0.0001250345,0.00012681395,0.00017241802,0.0003781751,0.00045393498,0.00021624418,0.000085597494,0.000035198707],"category_scores_gemma":[0.00016239674,0.00012864437,0.00004960792,0.00039334665,0.000018811852,0.0017619183,0.000014300179,0.00016652553,0.000016633696],"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":[0.000015971553,0.000027247886,0.000005512353,0.00016883502,0.000009934038,0.0000025071324,0.011992704,0.00030355263,0.0007823846,0.000079029014,0.000015252334,0.98659706],"study_design_scores_gemma":[0.004518568,0.00024257055,0.00043111973,0.0012102642,0.00012139997,0.00030219817,0.036781497,0.8544968,0.080983974,0.0021098775,0.017488677,0.0013130853],"about_ca_topic_score_codex":0.0000068341565,"about_ca_topic_score_gemma":0.000012404606,"teacher_disagreement_score":0.985284,"about_ca_system_score_codex":0.000040803166,"about_ca_system_score_gemma":0.000094350915,"threshold_uncertainty_score":0.5245965},"labels":[],"label_agreement":null},{"id":"W4210357218","doi":"10.1145/3506701","title":"Fuzzy Contrast Set Based Deep Attention Network for Lexical Analysis and Mental Health Treatment","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Mental Health via Writing","field":"Psychology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Contrast (vision); Mental health; Artificial intelligence; Computer science; Feature (linguistics); Machine learning; Set (abstract data type); The Internet; Fuzzy logic; Data mining; Psychology; Psychiatry; World Wide Web; Linguistics","score_opus":0.014597278507747249,"score_gpt":0.3173217739189699,"score_spread":0.30272449541122265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210357218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4010848,0.0017155699,0.5744048,0.01284725,0.00036996583,0.0032261675,0.0016400919,0.00041570634,0.004295681],"genre_scores_gemma":[0.99201316,0.0000056199106,0.0032717385,0.0030911497,0.000046349764,0.00033107493,0.0010812574,0.000015563919,0.00014410997],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99860257,0.0001470255,0.0004691928,0.00021919794,0.00019541489,0.000366597],"domain_scores_gemma":[0.9992943,0.00008473967,0.00024607024,0.00018855986,0.000018732531,0.00016762735],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00040149418,0.00017040818,0.00025051675,0.0003104104,0.0015434182,0.00010396442,0.00008580376,0.00005694518,0.0003088925],"category_scores_gemma":[0.000006496034,0.00017169365,0.00009543732,0.00045760212,0.00004514225,0.00025282963,0.0000067591836,0.00018135224,0.0000050196873],"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":[0.0004533204,0.00016495533,0.00072507164,0.00020500683,0.00014843812,0.0000017233343,0.03198436,0.001626142,0.000015498077,0.000068840745,0.00012433216,0.9644823],"study_design_scores_gemma":[0.025001798,0.0049728267,0.032409593,0.00042222824,0.0011534657,0.00030720368,0.68017423,0.20347185,0.00019294642,0.0002475913,0.04995376,0.0016924985],"about_ca_topic_score_codex":0.00013276709,"about_ca_topic_score_gemma":0.00014818227,"teacher_disagreement_score":0.96278983,"about_ca_system_score_codex":0.00022508997,"about_ca_system_score_gemma":0.0000468259,"threshold_uncertainty_score":0.99975646},"labels":[],"label_agreement":null},{"id":"W4210718628","doi":"10.1145/3508373","title":"Find Supports for the Post about Mental Issues: More Than Semantic Matching","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Mental Health via Writing","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Science Foundation of Jiangxi Province; National Natural Science Foundation of China","keywords":"Computer science; Feature (linguistics); Mental health; Matching (statistics); Graph; Task (project management); Semantic matching; Semantic feature; Context (archaeology); Information retrieval; Artificial intelligence; Natural language processing; Machine learning; Theoretical computer science; Psychology; Psychiatry; Medicine","score_opus":0.010661658861345421,"score_gpt":0.31628838518037844,"score_spread":0.30562672631903304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210718628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92075515,0.0017188399,0.043749902,0.021000668,0.000803379,0.0027488447,0.00065962115,0.00041800318,0.008145577],"genre_scores_gemma":[0.9927125,0.000004871969,0.0006535394,0.0046912534,0.00006748154,0.00032329065,0.00020330472,0.000027961054,0.0013157747],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9986142,0.000070825874,0.00044962956,0.00019003419,0.0003052384,0.00037007945],"domain_scores_gemma":[0.9992027,0.00013088553,0.00022359792,0.00031959245,0.000029813353,0.00009338075],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046395024,0.00018064537,0.00015367537,0.00019709667,0.002078561,0.00017756491,0.00027570679,0.00006167884,0.0012783438],"category_scores_gemma":[0.000018164186,0.00015644851,0.00007456626,0.00022130861,0.00006257967,0.0004933949,0.000021473319,0.0004074516,0.00002998811],"study_design_candidate":"qualitative","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":[0.0002072834,0.0000904377,0.00006928261,0.00037550603,0.000036638685,0.00000649053,0.33316857,0.00030602407,0.000095965996,0.00006011394,0.00036027769,0.6652234],"study_design_scores_gemma":[0.0018737048,0.00025556984,0.0039874692,0.00023183267,0.00007581085,0.00043759955,0.95875144,0.004033305,0.00035561397,0.00006670884,0.029540237,0.00039068758],"about_ca_topic_score_codex":0.00020265888,"about_ca_topic_score_gemma":0.000029643836,"teacher_disagreement_score":0.6648327,"about_ca_system_score_codex":0.0000853891,"about_ca_system_score_gemma":0.000041635918,"threshold_uncertainty_score":0.9996346},"labels":[],"label_agreement":null},{"id":"W4210778341","doi":"10.1145/3474555","title":"Generating Factoid Questions with Question Type Enhanced Representation and Attention-based Copy Mechanism","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Mechanism (biology); Representation (politics); Interrogative; Benchmark (surveying); Encoder; Quality (philosophy); Exploit; Artificial intelligence; Key (lock); Focus (optics); Mode (computer interface); Natural language processing; Linguistics; Human–computer interaction","score_opus":0.00789677647571175,"score_gpt":0.2444467531973456,"score_spread":0.23654997672163386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210778341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13167663,0.000041240837,0.86675376,0.00078893057,0.0000589885,0.00019241708,0.0000059526888,0.00020239904,0.00027967792],"genre_scores_gemma":[0.9357948,0.0000030841582,0.06332884,0.0006700696,0.000015893564,0.000057846548,0.00003949664,0.000008647084,0.000081341335],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894553,0.00009137055,0.00026332142,0.00023272439,0.00030620123,0.00016086375],"domain_scores_gemma":[0.99934137,0.000040964413,0.00016620915,0.00030033782,0.00007898035,0.000072129435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021746496,0.00013381097,0.00010764308,0.00024914104,0.0009609285,0.00035528484,0.00019581233,0.000042550695,0.000030931034],"category_scores_gemma":[0.000032521413,0.0001310705,0.000021994987,0.0004127218,0.00002783375,0.0012227297,0.000019860412,0.00024419292,0.000003285339],"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":[0.000057205405,0.000059053513,0.000041143623,0.000115985036,0.00001667674,0.0000048580164,0.019266147,0.10984674,0.0063652387,0.0012731556,0.000005831035,0.86294794],"study_design_scores_gemma":[0.0010175453,0.00022423682,0.00022508042,0.00014852831,0.000026438733,0.000074995965,0.011075661,0.9772858,0.00900365,0.00033650157,0.0002470396,0.00033449428],"about_ca_topic_score_codex":0.00004236029,"about_ca_topic_score_gemma":0.000013813807,"teacher_disagreement_score":0.8674391,"about_ca_system_score_codex":0.000062903026,"about_ca_system_score_gemma":0.00007758214,"threshold_uncertainty_score":0.7390782},"labels":[],"label_agreement":null},{"id":"W4285387971","doi":"10.1145/3534562","title":"A Decision Model for Ranking Asian Higher Education Institutes Using an NLP-Based Text Analysis Approach","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Multiple-criteria decision analysis; Ranking (information retrieval); Centroid; Identification (biology); Selection (genetic algorithm); Computer science; Rank (graph theory); TOPSIS; Higher education; Artificial intelligence; Function (biology); Decision analysis; Decision model; Machine learning; Data mining; Operations research; Mathematics; Statistics; Political science","score_opus":0.02038411021066483,"score_gpt":0.2964568092918321,"score_spread":0.27607269908116727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285387971","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":[0.023614304,0.00006832236,0.9738256,0.0012210325,0.00008966641,0.0002964278,0.000019854058,0.00018137175,0.00068347086],"genre_scores_gemma":[0.7402076,5.105506e-7,0.2584296,0.000984036,0.000016828084,0.00016228933,0.00010619986,0.0000072556622,0.00008567684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880517,0.00004639618,0.00033962337,0.00028172083,0.00032041394,0.00020668635],"domain_scores_gemma":[0.9991162,0.000047524867,0.0002082005,0.0004611881,0.00008234086,0.00008453463],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00032738814,0.00016526003,0.00016503636,0.0009434222,0.0013212145,0.00033427472,0.00056507264,0.00008179547,0.0000338754],"category_scores_gemma":[0.000017054388,0.00016859033,0.00008992967,0.0011929793,0.000044391243,0.0017937806,0.000024654813,0.00025900954,0.0000010513681],"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":[0.000027605922,0.00032462674,0.000023167137,0.00005873828,0.000035166497,2.1544687e-7,0.007906365,0.38666993,0.0000640668,0.0017922205,0.000012941921,0.6030849],"study_design_scores_gemma":[0.0004383749,0.000046113713,0.00021697888,0.00003304036,0.00009471759,0.0000097308875,0.0074069924,0.9892413,0.00020777801,0.0010873809,0.0010047891,0.00021281316],"about_ca_topic_score_codex":0.000012082859,"about_ca_topic_score_gemma":0.0000045811216,"teacher_disagreement_score":0.7165933,"about_ca_system_score_codex":0.00014616699,"about_ca_system_score_gemma":0.0003976624,"threshold_uncertainty_score":0.9999789},"labels":[],"label_agreement":null},{"id":"W4288050564","doi":"10.1145/3551890","title":"Explainable Deep Attention Active Learning for Sentimental Analytics of Mental Disorder","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Mental Health via Writing","field":"Psychology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Artificial intelligence; Computer science; Machine learning; Set (abstract data type); Mental health; Task (project management); Vocabulary; Deep learning; Class (philosophy); Fuzzy logic; Psychology; Psychiatry; Engineering","score_opus":0.01008739308180225,"score_gpt":0.2965891003532382,"score_spread":0.286501707271436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288050564","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8418358,0.00022992038,0.1457562,0.00058310543,0.00019854371,0.0011075806,0.00014627472,0.00014257806,0.010000017],"genre_scores_gemma":[0.99738896,0.0000022264323,0.0009886058,0.00028643076,0.000018645425,0.00019476851,0.00028868156,0.000018863102,0.000812806],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9988135,0.000087208035,0.00042047683,0.0001610329,0.00024742025,0.00027033922],"domain_scores_gemma":[0.9993756,0.000062805746,0.00030826373,0.0001480096,0.000034598794,0.00007072273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026890755,0.000136614,0.0001578601,0.0002886514,0.0010411624,0.00004948067,0.00012846783,0.000053117772,0.0008132469],"category_scores_gemma":[0.000017337208,0.00015376683,0.000072548726,0.0002818614,0.0000468025,0.0005199637,0.00001754757,0.00030516513,0.000011286488],"study_design_candidate":"qualitative","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":[0.00044884742,0.00023475224,0.00026536908,0.00037573185,0.00005507732,0.0000017179276,0.090328656,0.002184559,0.0003607508,0.00005584121,0.00004061364,0.9056481],"study_design_scores_gemma":[0.0035290208,0.00052448205,0.0014519928,0.0001251893,0.00008179678,0.00008001198,0.9521397,0.032520317,0.001508628,0.000036909663,0.0076834825,0.00031847053],"about_ca_topic_score_codex":0.000039637394,"about_ca_topic_score_gemma":0.000009367472,"teacher_disagreement_score":0.9053296,"about_ca_system_score_codex":0.00013519435,"about_ca_system_score_gemma":0.00002321534,"threshold_uncertainty_score":0.89044833},"labels":[],"label_agreement":null},{"id":"W4317042660","doi":"10.1145/3578708","title":"Fast and Accurate Framework for Ontology Matching in Web of Things","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Cluster analysis; Ontology; Data mining; Information retrieval; Matching (statistics); Web of Things; Semantic Web; Interoperability; The Internet; Artificial intelligence; World Wide Web; Mathematics","score_opus":0.012046908866989009,"score_gpt":0.2703067519801377,"score_spread":0.2582598431131487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317042660","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1325027,0.00009930104,0.86448884,0.001935247,0.000045895315,0.00015670843,0.000004542495,0.00016931082,0.00059745397],"genre_scores_gemma":[0.9518368,0.0000228871,0.047469806,0.00060627266,0.000008059321,0.00002032982,0.0000050008525,0.0000049499986,0.000025877285],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992534,0.000022336506,0.00028513095,0.00013414015,0.00011105051,0.00019393477],"domain_scores_gemma":[0.99940395,0.00020682502,0.00012724713,0.00019426888,0.000028427581,0.000039259376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025175943,0.00010402736,0.00015932089,0.00036293248,0.00016080315,0.00016352275,0.00025990952,0.00010063287,0.000003520765],"category_scores_gemma":[0.000105751475,0.00009350008,0.000027775874,0.0004122428,0.000050774994,0.001336505,0.000019362986,0.00016584987,0.000003636715],"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":[0.000021982847,0.000013021127,0.00005538138,0.00026183057,0.0000064384376,0.000002288992,0.090726525,0.00047819872,0.00012059649,0.0020662118,0.000006498679,0.906241],"study_design_scores_gemma":[0.0035193628,0.00034048324,0.0112421205,0.0023055617,0.000047720274,0.00014396377,0.28640118,0.6510721,0.006500038,0.035875265,0.0015872142,0.000965006],"about_ca_topic_score_codex":0.000024544992,"about_ca_topic_score_gemma":0.000034961886,"teacher_disagreement_score":0.905276,"about_ca_system_score_codex":0.000011412034,"about_ca_system_score_gemma":0.00004033058,"threshold_uncertainty_score":0.38128224},"labels":[],"label_agreement":null},{"id":"W4317434601","doi":"10.1145/3580496","title":"Emotional Intelligence Attention Unsupervised Learning Using Lexicon Analysis for Irony-based Advertising","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Irony; Artificial intelligence; Natural language processing; Classifier (UML); Social media; Machine learning; Lexicon; Word embedding; Embedding; Linguistics; World Wide Web","score_opus":0.019457538019049973,"score_gpt":0.27879410658367926,"score_spread":0.2593365685646293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317434601","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07340945,0.000040299205,0.92533576,0.0005624267,0.000048276816,0.0001506887,0.0000063967977,0.0002786928,0.00016800252],"genre_scores_gemma":[0.96178097,0.0000053507483,0.037556656,0.00031366755,0.000029536433,0.000017466047,0.00017846296,0.0000112937605,0.00010659968],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855196,0.000057613386,0.00046579234,0.00028074352,0.00035342874,0.000290447],"domain_scores_gemma":[0.9991941,0.00010583676,0.00022500037,0.00027604206,0.00010443953,0.00009460133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004271037,0.00018251958,0.00021175932,0.0012231447,0.0008273318,0.0006097253,0.00031959752,0.00008634888,0.00004703144],"category_scores_gemma":[0.000058806298,0.00018420552,0.00020734809,0.0021856457,0.000039726285,0.0015531599,0.000017297682,0.00017824775,0.000020425585],"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":[0.00002447324,0.000034688255,0.0005024328,0.00014745278,0.00012093732,0.0000014608116,0.006734354,0.32319933,0.00075178436,0.00013600168,0.0000048401303,0.66834223],"study_design_scores_gemma":[0.00035526077,0.00003690609,0.0014267815,0.00015269194,0.00012352526,0.0000028283346,0.00863733,0.9870909,0.0016687918,0.000054551867,0.00023248189,0.00021795061],"about_ca_topic_score_codex":0.000014724569,"about_ca_topic_score_gemma":0.000005985881,"teacher_disagreement_score":0.8883715,"about_ca_system_score_codex":0.000074953554,"about_ca_system_score_gemma":0.00006361922,"threshold_uncertainty_score":0.7511683},"labels":[],"label_agreement":null},{"id":"W4317504322","doi":"10.1145/3580495","title":"Filtering and Extended Vocabulary based Translation for Low-resource Language Pair of Sanskrit-Hindi","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sanskrit; Computer science; Machine translation; Hindi; Natural language processing; Artificial intelligence; Vocabulary; Transformer; Sentence; Phrase; Language translation; Linguistics; Engineering","score_opus":0.00992098405943372,"score_gpt":0.2561712473687812,"score_spread":0.2462502633093475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317504322","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":[0.035742175,0.0009718077,0.9598419,0.0014403054,0.00003912255,0.00055687455,0.000064318425,0.0011073411,0.00023612923],"genre_scores_gemma":[0.82531977,0.000010214512,0.17365257,0.00069170375,0.000031367646,0.00007772346,0.00011720785,0.000028178783,0.00007125124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983471,0.00006148129,0.00053213706,0.0003283223,0.00036472833,0.0003662572],"domain_scores_gemma":[0.99884796,0.00020365736,0.00026916366,0.00047219254,0.000081232036,0.00012576545],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050808664,0.0002791135,0.0002821195,0.00069345534,0.0004034665,0.00035782007,0.0005200648,0.00018242636,0.000013166383],"category_scores_gemma":[0.00009759755,0.0002660742,0.000097026976,0.0008114404,0.00009667489,0.0017108007,0.000028573335,0.00028909586,0.000004088101],"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":[0.000064642205,0.000038971884,0.0000049354594,0.0010343606,0.000014418595,0.0000064043447,0.024897238,0.00027386815,0.0059378585,0.000045670637,0.00004760478,0.967634],"study_design_scores_gemma":[0.003757593,0.00047440737,0.00037885815,0.0023392413,0.0001054261,0.00009685861,0.019519057,0.69200325,0.27498528,0.001107698,0.003944677,0.0012876402],"about_ca_topic_score_codex":0.000014352163,"about_ca_topic_score_gemma":0.000007853946,"teacher_disagreement_score":0.9663464,"about_ca_system_score_codex":0.000034675708,"about_ca_system_score_gemma":0.00006652898,"threshold_uncertainty_score":0.99997914},"labels":[],"label_agreement":null},{"id":"W4365451534","doi":"10.1145/3592604","title":"Semi-Supervised Lexicon-Aware Embedding for News Article Time Estimation","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Artificial intelligence; Lexicon; Classifier (UML); Natural language processing; Stop words; WordNet; Machine learning","score_opus":0.008482545231234899,"score_gpt":0.2775019277698858,"score_spread":0.26901938253865093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365451534","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":[0.012372353,0.000019039928,0.9840189,0.0015538157,0.00001975694,0.00029451816,0.000011121425,0.0011964391,0.00051404274],"genre_scores_gemma":[0.85067046,0.0000062153977,0.14782217,0.0009248933,0.0000272145,0.000113722774,0.00008242947,0.000019548123,0.00033333036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889225,0.000025966216,0.00036106963,0.00021452784,0.00023033425,0.00027582573],"domain_scores_gemma":[0.99918085,0.00009581804,0.0001463092,0.00040453862,0.000076823184,0.00009564367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022335512,0.00016629524,0.00016587501,0.00044389945,0.0004679468,0.0004649879,0.0003744334,0.00008801717,0.000025154115],"category_scores_gemma":[0.000084537336,0.00016277564,0.00007606127,0.00087936467,0.000034387504,0.003021609,0.000020927157,0.00014626261,0.00009685163],"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":[0.000011032067,0.000016613816,0.0000035491416,0.000093403985,0.00001050167,0.0000011393082,0.0103537915,0.01153301,0.0009565408,0.00008067015,0.00012051938,0.9768192],"study_design_scores_gemma":[0.00040530963,0.000040675146,0.00003755261,0.000114794166,0.000017392911,0.000009030949,0.0035575877,0.98223925,0.01155669,0.0009964327,0.0008198371,0.00020546658],"about_ca_topic_score_codex":0.0000051354828,"about_ca_topic_score_gemma":0.000003936893,"teacher_disagreement_score":0.97661376,"about_ca_system_score_codex":0.00004983311,"about_ca_system_score_gemma":0.000044021122,"threshold_uncertainty_score":0.6637798},"labels":[],"label_agreement":null},{"id":"W4375949401","doi":"10.1145/3591208","title":"Editorial for the Special Issue on Computational Linguistics Processing in Low-Resource Indigenous Languages","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brandon University","funders":"","keywords":"Indigenous; Citation; Library science; Resource (disambiguation); Computer science; History; Media studies; Linguistics; Sociology; Philosophy","score_opus":0.006931384925798461,"score_gpt":0.2695800335462915,"score_spread":0.26264864862049303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375949401","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":[0.0026999163,0.0009727873,0.9786423,0.0041098967,0.00509364,0.0020071708,0.00012859143,0.0024636986,0.0038820172],"genre_scores_gemma":[0.81234837,0.000039443777,0.12212605,0.0059102103,0.05766582,0.0005136843,0.00042189518,0.0001409452,0.00083357515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978934,0.00005929109,0.0005449829,0.0003533094,0.0006544863,0.00049451605],"domain_scores_gemma":[0.99861294,0.0003730107,0.00028064952,0.00041963186,0.00020830384,0.000105461324],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006262507,0.00031296906,0.00024922471,0.0006780863,0.00093418785,0.0009674182,0.0009446382,0.00022532824,0.000014900117],"category_scores_gemma":[0.0005736615,0.00025340114,0.00008131701,0.0011748463,0.00010728125,0.0007813571,0.00004877465,0.00062745885,0.00003650795],"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":[0.00008889597,0.00006163547,0.0000048701777,0.00033774966,0.000009440481,0.000008244889,0.034848075,0.00749348,0.000016830993,0.0001628958,0.004107906,0.95286],"study_design_scores_gemma":[0.0052989023,0.000697108,0.00043010083,0.00315907,0.000108715794,0.00008212976,0.04582416,0.47297105,0.0050301743,0.0052634818,0.45886573,0.0022693935],"about_ca_topic_score_codex":0.000020353975,"about_ca_topic_score_gemma":0.000019523153,"teacher_disagreement_score":0.9505906,"about_ca_system_score_codex":0.00011238454,"about_ca_system_score_gemma":0.00017904097,"threshold_uncertainty_score":0.99999183},"labels":[],"label_agreement":null},{"id":"W4382024628","doi":"10.1145/3605778","title":"SER: Performance Evaluation of CNN Model Along with an Overview of Available Indic Speech Datasets, and Transition of Classifiers From Traditional to Modern Era","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Convolutional neural network; Transfer of learning; Benchmark (surveying); Machine learning; Field (mathematics); Artificial neural network; Speech recognition; Natural language processing","score_opus":0.08572302267729681,"score_gpt":0.3169815072235871,"score_spread":0.23125848454629028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382024628","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9636543,0.00012460444,0.033241708,0.0001769951,0.00002550502,0.0003651739,0.0010182412,0.00005020188,0.0013432703],"genre_scores_gemma":[0.9952586,0.00004316028,0.0025077297,0.00020970393,0.000012302699,0.000034631154,0.0018944128,0.000012866498,0.000026558146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986812,0.00008200697,0.0004438194,0.00017856793,0.00047171503,0.00014268533],"domain_scores_gemma":[0.9992484,0.00003535765,0.00024087392,0.00023347448,0.00015093679,0.000090998525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005098042,0.0001367244,0.00019915856,0.00050130073,0.00012476381,0.00003142219,0.00010058266,0.00011197123,0.0003026699],"category_scores_gemma":[0.00001500649,0.00012956081,0.000030435682,0.00045937608,0.000080818834,0.0010401998,0.000003841318,0.0001567935,0.000012767004],"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":[0.00042880198,0.00015820713,0.000042724638,0.000465572,0.000057289548,6.725975e-7,0.05985622,0.015781669,0.001122165,0.000026757245,0.00007564573,0.92198426],"study_design_scores_gemma":[0.005672049,0.0008743588,0.019738978,0.0018410998,0.0004607912,0.000048837588,0.05609603,0.89766484,0.016354863,0.0006099647,0.00011040881,0.0005277616],"about_ca_topic_score_codex":0.000068353394,"about_ca_topic_score_gemma":0.00004683729,"teacher_disagreement_score":0.9214565,"about_ca_system_score_codex":0.000023816334,"about_ca_system_score_gemma":0.00008423572,"threshold_uncertainty_score":0.52833366},"labels":[],"label_agreement":null},{"id":"W4386607605","doi":"10.1145/3615864","title":"Semi-Automatic Building and Learning of a Multilingual Ontology","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Ontology; Natural language processing; Context (archaeology); Artificial intelligence; Relevance (law); Information retrieval; Ambiguity; Task (project management); Arabic; Linguistics; Programming language","score_opus":0.008931613069448478,"score_gpt":0.258806147771992,"score_spread":0.24987453470254353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386607605","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6099085,0.0001356193,0.3878973,0.00061251235,0.000041533116,0.00010376647,0.0000016689432,0.00044617025,0.0008529053],"genre_scores_gemma":[0.98483133,0.000013489439,0.014858896,0.00019511092,0.000008838507,0.000008077011,0.0000036691774,0.0000053938315,0.00007519734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991325,0.000051357274,0.00030057316,0.00014617144,0.0001634015,0.000205984],"domain_scores_gemma":[0.9993811,0.00017582426,0.00014805779,0.00020081238,0.000036916623,0.000057242643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028993416,0.00011986191,0.00017276825,0.00037206852,0.00030236834,0.00015772134,0.0002462437,0.0000819447,0.000009781435],"category_scores_gemma":[0.00019842312,0.00010868961,0.000031366682,0.00043356733,0.00007562357,0.0008408841,0.000027134301,0.00022390948,0.00001014177],"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":[0.000005842149,0.00001059632,0.00007243292,0.00023764539,0.000009798128,0.000004611893,0.046585873,0.0005958241,0.0004608695,0.00009357107,0.0000052173054,0.9519177],"study_design_scores_gemma":[0.0013843131,0.00018900727,0.0069909235,0.00062495185,0.000037632613,0.0001965358,0.07907327,0.89788234,0.011489938,0.0004229536,0.0012697614,0.00043839111],"about_ca_topic_score_codex":0.00002490387,"about_ca_topic_score_gemma":0.000008165291,"teacher_disagreement_score":0.9514793,"about_ca_system_score_codex":0.000011923326,"about_ca_system_score_gemma":0.000032512973,"threshold_uncertainty_score":0.44322336},"labels":[],"label_agreement":null},{"id":"W4386803063","doi":"10.1145/3623396","title":"Multimodal Religiously Hateful Social Media Memes Classification Based on Textual and Image Data","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Social media; Computer science; Artificial intelligence; Image (mathematics); Natural language processing; Information retrieval; Pattern recognition (psychology); Linguistics; World Wide Web","score_opus":0.017386022366471538,"score_gpt":0.2582952664607165,"score_spread":0.24090924409424494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386803063","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059825506,0.000043346117,0.9278081,0.006329489,0.00015503539,0.0003788904,0.00011087032,0.001312421,0.0040363255],"genre_scores_gemma":[0.99072444,0.000014808446,0.008207559,0.00067712524,0.000060945265,0.000020802374,0.00023151953,0.000013457453,0.000049346654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986916,0.00005781652,0.000303819,0.00031655646,0.0003703797,0.0002598228],"domain_scores_gemma":[0.9990328,0.00012043963,0.00014269218,0.0005389191,0.00005663486,0.000108499335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037034572,0.00018085854,0.00013832764,0.0004514098,0.0006944394,0.0006711963,0.00051027094,0.00012435738,0.000014052168],"category_scores_gemma":[0.00013847866,0.00017086932,0.000032023123,0.00064455887,0.00008463257,0.0019035286,0.00003390826,0.0002721526,0.000085059604],"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":[0.000038560833,0.000028547587,0.000004753299,0.000078628276,0.000006960895,0.000005062158,0.01442319,0.00022164734,0.00047963802,0.000054969532,0.00035864516,0.9842994],"study_design_scores_gemma":[0.0013947597,0.00009686001,0.0032145304,0.0001616439,0.000027569084,0.000027161312,0.018491285,0.96841365,0.0028415266,0.0001317508,0.0047643627,0.0004349159],"about_ca_topic_score_codex":0.000016271939,"about_ca_topic_score_gemma":0.00001935791,"teacher_disagreement_score":0.9838645,"about_ca_system_score_codex":0.000031690088,"about_ca_system_score_gemma":0.00006180423,"threshold_uncertainty_score":0.69678485},"labels":[],"label_agreement":null},{"id":"W4387460482","doi":"10.1145/3626524","title":"Handwritten Odia Digit Recognition using Learning Systems: A Comparison of Neural Networks and Support Vector Machine Models","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Python (programming language); Artificial intelligence; Scripting language; Support vector machine; Convolutional neural network; Deep learning; Artificial neural network; Machine learning; Classifier (UML); Natural language processing; Programming language","score_opus":0.021790143380408775,"score_gpt":0.23703586337414426,"score_spread":0.21524571999373548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387460482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99506366,0.00021052771,0.0035366511,0.0002852485,0.00004477482,0.000204138,0.000045732526,0.00017216876,0.000437081],"genre_scores_gemma":[0.9993788,0.000018246741,0.000064237865,0.00009636149,0.000060232465,0.000009760852,0.00031800076,0.0000018175024,0.0000525291],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915546,0.000041414165,0.00032251814,0.00012715482,0.00016281597,0.00019063012],"domain_scores_gemma":[0.99958926,0.0000697016,0.00017149228,0.000040271974,0.000050665563,0.00007861684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001256767,0.00013482876,0.00018884825,0.00006026876,0.00038495738,0.0002231516,0.00008349542,0.00009981461,0.000026325493],"category_scores_gemma":[0.000018384324,0.000065793014,0.000042373103,0.00042486278,0.000038974053,0.00079617643,0.00001061835,0.00020566123,0.0000039203983],"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":[0.000045067383,0.000029089242,0.00044653605,0.000118318225,0.000013991775,0.0000015660202,0.006358879,0.030600075,0.0015524904,0.0000016518092,0.000025538844,0.9608068],"study_design_scores_gemma":[0.0004092653,0.00021790685,0.0040067323,0.0002912343,0.00005666452,0.000044088767,0.03826956,0.9546523,0.0008179548,0.000015614642,0.000920119,0.00029855946],"about_ca_topic_score_codex":0.00007788589,"about_ca_topic_score_gemma":0.000036831032,"teacher_disagreement_score":0.9605082,"about_ca_system_score_codex":0.000011425846,"about_ca_system_score_gemma":0.0000045766933,"threshold_uncertainty_score":0.296082},"labels":[],"label_agreement":null},{"id":"W4390880298","doi":"10.1145/3638285","title":"Arabic Sentiment Analysis for ChatGPT Using Machine Learning Classification Algorithms: A Hyperparameter Optimization Technique","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hyperparameter; Arabic; Computer science; Sentiment analysis; Artificial intelligence; Machine learning; Algorithm; Natural language processing","score_opus":0.015791467211840795,"score_gpt":0.27409165186836254,"score_spread":0.25830018465652177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390880298","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":[0.00041604,0.00018527145,0.99690825,0.0007390804,0.00004375333,0.00059500907,0.00004895138,0.0008990866,0.00016453394],"genre_scores_gemma":[0.44950816,0.000020994521,0.54944927,0.0002801624,0.000024311263,0.00026753615,0.00030282408,0.00002000047,0.00012673634],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855614,0.00007220641,0.00049371447,0.00036318955,0.00027546237,0.00023929462],"domain_scores_gemma":[0.9990209,0.000093248615,0.00021091591,0.00047746114,0.000116126546,0.00008135384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048650702,0.0002171669,0.00021598497,0.0011299326,0.00044611047,0.0010282424,0.00038201132,0.00013956828,0.000022939292],"category_scores_gemma":[0.000065887085,0.00020746245,0.00012414165,0.0015077898,0.000049317157,0.002705916,0.000019757761,0.00028935962,0.000006712129],"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":[0.000017899061,0.000053784715,0.00001778587,0.0003108402,0.0001245259,0.0000015720227,0.0069418265,0.04083479,0.0024682733,0.00027723625,0.000013048943,0.9489384],"study_design_scores_gemma":[0.00016742948,0.000044884175,0.00004076368,0.00014922206,0.00013024743,0.000025412275,0.0009370808,0.98401535,0.011187241,0.000060796054,0.003006093,0.00023547858],"about_ca_topic_score_codex":0.000013286393,"about_ca_topic_score_gemma":0.0000020957225,"teacher_disagreement_score":0.94870293,"about_ca_system_score_codex":0.00014002937,"about_ca_system_score_gemma":0.000064574284,"threshold_uncertainty_score":0.9915365},"labels":[],"label_agreement":null},{"id":"W4392619616","doi":"10.1145/3651159","title":"DeepMedFeature: An Accurate Feature Extraction and Drug-Drug Interaction Model for Clinical Text in Medical Informatics","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Artificial intelligence; Informatics; Drug; Convolution (computer science); Feature extraction; F1 score; Feature vector; Mechanism (biology); Machine learning; Natural language processing; Artificial neural network; Medicine; Pharmacology","score_opus":0.016352322933853608,"score_gpt":0.3468787532546184,"score_spread":0.3305264303207648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392619616","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41149482,0.0016603866,0.5818186,0.0036864923,0.0002443948,0.000381968,0.000054472075,0.00016046934,0.00049842364],"genre_scores_gemma":[0.98664075,0.0003461789,0.011021801,0.001262582,0.00011566156,0.00004402753,0.00022846358,0.000016229877,0.00032432078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989467,0.00004820233,0.00043448707,0.00018768328,0.00018589204,0.00019700552],"domain_scores_gemma":[0.9994522,0.00007724957,0.000101125355,0.00017830801,0.000039768332,0.00015139556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005403512,0.00017022739,0.0001573419,0.00019061526,0.00015649821,0.00023449796,0.00013925959,0.00033625573,0.0000100118405],"category_scores_gemma":[0.00018265689,0.00014298297,0.000058181427,0.00015027329,0.00011375797,0.00017517869,0.000014046096,0.000498503,0.0000029833377],"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":[0.00015891981,0.000044536595,0.00001740097,0.0003099229,0.000017901963,0.0000021963244,0.0102259265,0.00037802174,0.0001397152,0.000006714177,0.0006700971,0.98802865],"study_design_scores_gemma":[0.0017433108,0.00023952428,0.00042385558,0.0007967082,0.00006593455,0.00022871485,0.044946007,0.89313734,0.0020979554,0.000093140894,0.05573428,0.0004932163],"about_ca_topic_score_codex":0.000005341712,"about_ca_topic_score_gemma":0.000084629486,"teacher_disagreement_score":0.9875354,"about_ca_system_score_codex":0.00001901657,"about_ca_system_score_gemma":0.00010289571,"threshold_uncertainty_score":0.58306766},"labels":[],"label_agreement":null},{"id":"W4396671072","doi":"10.1145/3657635","title":"A Hybrid Deep BiLSTM-CNN for Hate Speech Detection in Multi-social media","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Computer science; Social media; Voice activity detection; Artificial intelligence; Speech recognition; Natural language processing; Speech processing; World Wide Web","score_opus":0.010580423705731345,"score_gpt":0.24609146739213666,"score_spread":0.23551104368640532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396671072","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028201032,0.00015122653,0.96941787,0.00070221344,0.00025040694,0.00031851805,0.000013504166,0.0004833724,0.00046184935],"genre_scores_gemma":[0.98305875,0.00001016764,0.016352205,0.00031395027,0.00007184085,0.000080664686,0.000019868658,0.000016434447,0.000076147946],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987935,0.000038525985,0.00036632663,0.00026513272,0.00023203153,0.00030447473],"domain_scores_gemma":[0.9994841,0.00008947722,0.00008183216,0.00020580027,0.000052145286,0.00008660274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033122808,0.00018769791,0.00015251504,0.00065101817,0.0003912392,0.0008081297,0.00027073815,0.000113393406,0.000012959362],"category_scores_gemma":[0.000079835714,0.00018106861,0.00008127868,0.00061112695,0.000038580525,0.002052461,0.0000116834735,0.00031927644,0.000035069057],"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":[0.000027078095,0.000026202104,5.832507e-7,0.00020063302,0.000008429074,0.000009647951,0.022996342,0.00012617827,0.00053621124,0.00002831834,0.000008501917,0.9760319],"study_design_scores_gemma":[0.0019175421,0.00014254129,0.00025373828,0.0004986962,0.000041165764,0.0002466864,0.009957486,0.89198095,0.08371741,0.0008043624,0.009770795,0.0006686566],"about_ca_topic_score_codex":0.00002121519,"about_ca_topic_score_gemma":0.00014132852,"teacher_disagreement_score":0.9753632,"about_ca_system_score_codex":0.00009278646,"about_ca_system_score_gemma":0.000047491656,"threshold_uncertainty_score":0.7792813},"labels":[],"label_agreement":null},{"id":"W4407974294","doi":"10.1145/3720542","title":"A Hybrid Statistical and Rule-based Approach to Extremely Low-resource Machine Transliteration","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Transliteration; Computer science; Artificial intelligence; Rule-based system; Resource (disambiguation); Natural language processing; Machine learning; Data mining","score_opus":0.005748411853017093,"score_gpt":0.23077370589083876,"score_spread":0.22502529403782168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407974294","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":[0.0039247847,0.0001910796,0.9906307,0.0013690976,0.000036376583,0.0003349844,0.0001091963,0.00021874896,0.0031850482],"genre_scores_gemma":[0.841041,0.0000041488925,0.15469672,0.0037696734,0.00002337933,0.000060114668,0.00024004003,0.000012980656,0.00015194518],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985735,0.00007143783,0.00042399997,0.00035284628,0.0002995335,0.00027872],"domain_scores_gemma":[0.9991003,0.00008891781,0.00009443161,0.0004677429,0.000057667163,0.00019091567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024724726,0.00024287109,0.00020992433,0.0004652705,0.00055178924,0.00090997125,0.00041781098,0.00008085258,0.000016931688],"category_scores_gemma":[0.00004368199,0.0002173727,0.000039326813,0.00042970723,0.000062579216,0.0014227731,0.000031515156,0.00028121166,0.000008599008],"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":[0.00007260322,0.000102324135,0.000004399563,0.00028714657,0.0000097394895,0.0000031466177,0.0058305515,0.0018998346,0.00013155222,0.00045827797,0.00015005354,0.99105036],"study_design_scores_gemma":[0.001732634,0.000100858866,0.00039892428,0.0005243962,0.00003528757,0.000041208885,0.0016734373,0.9781325,0.002849063,0.00029933942,0.013764773,0.00044758717],"about_ca_topic_score_codex":0.000019781535,"about_ca_topic_score_gemma":0.0000036303063,"teacher_disagreement_score":0.9906028,"about_ca_system_score_codex":0.000038649578,"about_ca_system_score_gemma":0.00007625517,"threshold_uncertainty_score":0.88642013},"labels":[],"label_agreement":null},{"id":"W4413060628","doi":"10.1145/3748316","title":"Inner-character and Inner-word Features Based Representation Learning for Chinese Word Embedding","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; Natural Science Foundation of Sichuan Province; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Pinyin; Computer science; Artificial intelligence; Natural language processing; Word (group theory); Character (mathematics); Word embedding; Feature (linguistics); Similarity (geometry); Chinese characters; Speech recognition; Embedding; Linguistics; Mathematics","score_opus":0.006695338832000711,"score_gpt":0.27081476975019714,"score_spread":0.26411943091819645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413060628","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086158074,0.000115816154,0.9098367,0.0024838743,0.00007921662,0.00026153275,0.0000029350974,0.0002144469,0.0008474075],"genre_scores_gemma":[0.9546114,0.0000055589417,0.04340715,0.001473248,0.00003630748,0.000053914013,0.000028145325,0.0000088644665,0.00037536124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897623,0.00004636529,0.0003346815,0.0002548822,0.00017264567,0.00021520765],"domain_scores_gemma":[0.9992488,0.00015181304,0.00015340283,0.00030208853,0.000076883625,0.00006701644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024631043,0.00017580688,0.00016492781,0.0004629463,0.0005605098,0.0006799541,0.0002569303,0.00010438998,0.00000750345],"category_scores_gemma":[0.0001780941,0.00016008901,0.000048728485,0.0004966844,0.000033792945,0.0017718544,0.000022383032,0.00030443014,0.0000017111031],"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":[0.000037636837,0.000015834805,0.000132239,0.00022944124,0.000011175689,8.451866e-7,0.01269745,0.009403499,0.00023110885,0.00010052949,0.000018021372,0.97712225],"study_design_scores_gemma":[0.0016402061,0.000045402074,0.004228877,0.0005468004,0.00003100529,0.000018798637,0.0076663624,0.9793787,0.002168478,0.00048718916,0.0034222188,0.0003659464],"about_ca_topic_score_codex":0.000015196288,"about_ca_topic_score_gemma":0.000010157075,"teacher_disagreement_score":0.9767563,"about_ca_system_score_codex":0.000034182543,"about_ca_system_score_gemma":0.000050985458,"threshold_uncertainty_score":0.6556813},"labels":[],"label_agreement":null},{"id":"W7117239698","doi":"10.1145/3786588","title":"MSDA-Net: Multi-source Domain Adaptive Network for Multi-modal Emotion Recognition","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Feature (linguistics); Pattern recognition (psychology); Emotion recognition; Feature extraction; Domain (mathematical analysis); Feature learning; Joint (building)","score_opus":0.024927861211206364,"score_gpt":0.3015296854222537,"score_spread":0.27660182421104734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117239698","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":[0.025049822,0.00017700306,0.9655694,0.000711745,0.0003759025,0.0009657624,0.00011917111,0.00033894638,0.0066922917],"genre_scores_gemma":[0.90273464,0.000018623517,0.0868605,0.004489466,0.0002144863,0.00045293392,0.00083099015,0.000054339416,0.004344037],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9983976,0.0001368593,0.0005693124,0.00031983532,0.00016594243,0.00041044157],"domain_scores_gemma":[0.99906725,0.00010111441,0.00026927184,0.00027843638,0.00016303376,0.000120894605],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039801444,0.00028463616,0.00024520064,0.00046516585,0.0007436999,0.00019045542,0.00016297969,0.0003125178,0.0002530668],"category_scores_gemma":[0.00006627426,0.00028992162,0.00013615302,0.0004845497,0.00009651168,0.00074037246,0.00000872948,0.00038366774,0.00011644854],"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":[0.00038578254,0.0002275251,0.000017466946,0.0001784655,0.00007325157,0.0000011849232,0.023149196,0.0004330715,0.00007659546,0.00009056804,0.0003885154,0.9749784],"study_design_scores_gemma":[0.051131196,0.0018507519,0.017056791,0.0063588484,0.0011550722,0.00030859717,0.61440074,0.17990632,0.0055319266,0.0038531178,0.1143945,0.0040521165],"about_ca_topic_score_codex":0.000034765177,"about_ca_topic_score_gemma":0.00007006337,"teacher_disagreement_score":0.9709263,"about_ca_system_score_codex":0.00008188726,"about_ca_system_score_gemma":0.000048482405,"threshold_uncertainty_score":0.9999553},"labels":[],"label_agreement":null}]}