{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027332187,0.0009841961,0.9607783,0.00032247795,0.00011950693,0.00016398435,0.00026590296,0.005452445,0.0045809764],"genre_scores_gemma":[0.22868027,0.0006846948,0.7622442,0.00042715733,0.00015338777,0.00023352377,0.0014387305,0.0007743921,0.0053637372],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99832636,0.00045064115,0.0001673919,0.0005269001,0.0004479648,0.00008067101],"domain_scores_gemma":[0.9989593,0.00022099243,0.0001815753,0.00019266186,0.0004012409,0.000044172484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092286186,0.0013031437,0.0007375966,0.0028406573,0.0008682159,0.0007436069,0.0011655266,0.00089403114,0.0034554505],"category_scores_gemma":[0.0029675753,0.00049868535,0.000995458,0.0036130869,0.00045211564,0.0026608987,0.0014199938,0.0013783441,0.0030771464],"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":[0.00021112734,0.00034786828,0.0021738713,0.00042132012,0.00016564054,0.00029322947,0.0006194194,0.05071463,0.092423186,0.012662328,0.009412607,0.8305548],"study_design_scores_gemma":[0.00007171965,0.00025271287,0.0023185217,0.000036365447,0.00023066935,0.0004944015,0.0002695934,0.9049009,0.045455914,0.016511748,0.029373245,0.0000842583],"about_ca_topic_score_codex":0.0039874255,"about_ca_topic_score_gemma":0.0073790336,"teacher_disagreement_score":0.0039874255,"about_ca_system_score_codex":0.0004947456,"about_ca_system_score_gemma":0.0015802295,"threshold_uncertainty_score":0.011559665},"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":"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":[0.27230534,0.00091908226,0.70188504,0.00053734274,0.00006360601,0.00085396087,0.002438542,0.008368419,0.012628701],"genre_scores_gemma":[0.558216,0.00072819553,0.42632696,0.00028713877,0.000096267075,0.00041597313,0.009966584,0.0007309787,0.0032319785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990109,0.00021765864,0.00011696941,0.0003412673,0.0002442394,0.000068933216],"domain_scores_gemma":[0.9969855,0.0013967538,0.00025113733,0.00081269623,0.00047425926,0.00007968773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078163494,0.0010448701,0.0007370647,0.0036301678,0.0005391437,0.0011936488,0.00135007,0.0006573736,0.0030725144],"category_scores_gemma":[0.005436913,0.0007088809,0.0012622386,0.0024482463,0.0006769381,0.0028379734,0.0019988585,0.0010078067,0.0017019211],"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":[0.0002627692,0.00047353157,0.011105793,0.0007540233,0.00021753438,0.0020017775,0.001645694,0.020035774,0.14222673,0.014664645,0.010117649,0.79649407],"study_design_scores_gemma":[0.00019527136,0.000760098,0.027483955,0.00023240148,0.0006779254,0.0062768427,0.0018243828,0.69529957,0.09870922,0.10718038,0.061186936,0.00017302742],"about_ca_topic_score_codex":0.0013093736,"about_ca_topic_score_gemma":0.00450177,"teacher_disagreement_score":0.0036301678,"about_ca_system_score_codex":0.0004732434,"about_ca_system_score_gemma":0.00070535217,"threshold_uncertainty_score":0.010278523},"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":"other","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":[0.20126367,0.0054930933,0.08116202,0.005533899,0.0115134,0.0019263963,0.10671379,0.03727564,0.54911804],"genre_scores_gemma":[0.6812867,0.0021701043,0.09899853,0.00070820807,0.0017320581,0.0009151732,0.04878244,0.002649119,0.16275764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953679,0.0009856735,0.00070858625,0.00078389567,0.0017526443,0.00040130038],"domain_scores_gemma":[0.97443193,0.0063085305,0.0044708056,0.0061397534,0.007569179,0.0010797523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029042235,0.0013072336,0.0005584363,0.009752351,0.0022600451,0.004161596,0.0007413141,0.0010577716,0.08837211],"category_scores_gemma":[0.033642072,0.00026479294,0.00038356576,0.006656724,0.00071925326,0.0025677374,0.0024693508,0.00078603474,0.05125925],"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":[0.0008544648,0.00011700492,0.021399599,0.0013121594,0.00005910128,0.00064138084,0.0021809516,0.0021264695,0.006325555,0.013614195,0.19740245,0.7539667],"study_design_scores_gemma":[0.0000677564,0.00014577784,0.026989339,0.00063491514,0.000058263136,0.0022018864,0.0022826532,0.022568192,0.023447655,0.019366957,0.9020669,0.00016976323],"about_ca_topic_score_codex":0.0007378662,"about_ca_topic_score_gemma":0.0008996131,"teacher_disagreement_score":0.08837211,"about_ca_system_score_codex":0.0008603069,"about_ca_system_score_gemma":0.0012181683,"threshold_uncertainty_score":0.29563415},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03970216,0.0005108735,0.9510797,0.00013823312,0.000084577696,0.00005974155,0.00017182257,0.006079283,0.002173571],"genre_scores_gemma":[0.6053345,0.0004832689,0.38591716,0.00016397596,0.00007108618,0.00021057198,0.0013126218,0.0004806114,0.0060262172],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947757,0.0001644809,0.000044009834,0.00015709987,0.000104791885,0.000052032614],"domain_scores_gemma":[0.99897254,0.00051313126,0.000107950815,0.00016130324,0.00022341557,0.000021739106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006718987,0.00085177744,0.00066554593,0.00041986076,0.0002670654,0.0005302611,0.0009454533,0.000536689,0.0020943775],"category_scores_gemma":[0.0023413852,0.00028572517,0.00056329457,0.0005404521,0.00029509325,0.0011215423,0.0006336065,0.0009080397,0.0013668832],"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":[0.00039714455,0.00017804216,0.0007125206,0.0003101395,0.00016247296,0.00040183272,0.00018009706,0.4202937,0.056901526,0.0056110076,0.004195207,0.5106563],"study_design_scores_gemma":[0.000011763191,0.000060729926,0.00013373133,0.0000074849586,0.000025021991,0.00005504137,0.000012285479,0.98150796,0.015253255,0.0018713013,0.0010520881,0.000009321801],"about_ca_topic_score_codex":0.004412966,"about_ca_topic_score_gemma":0.007189263,"teacher_disagreement_score":0.004412966,"about_ca_system_score_codex":0.00053215167,"about_ca_system_score_gemma":0.00068516383,"threshold_uncertainty_score":0.008774579},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01301014,0.00025018444,0.98500174,0.00012241577,0.00005036099,0.000048279417,0.00016132185,0.0005361019,0.00081939634],"genre_scores_gemma":[0.52839667,0.000548618,0.4601647,0.00047108947,0.00012831828,0.0004368111,0.0019444752,0.00040828227,0.0075010182],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933845,0.00026116986,0.000034205408,0.00020158292,0.00010609572,0.000058441172],"domain_scores_gemma":[0.99876,0.0008895738,0.00005521728,0.00008757309,0.00016073903,0.000046852998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012016314,0.0010104914,0.0007156623,0.00036207022,0.00030556647,0.00047876526,0.0010076895,0.0008556173,0.0026686518],"category_scores_gemma":[0.004075896,0.00047554707,0.0009804509,0.00041839547,0.0005427188,0.0012396189,0.000976488,0.0019260176,0.0009880954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003651009,0.00013563519,0.00158494,0.00020696467,0.00014379506,0.00015559077,0.00037150382,0.6071214,0.02582523,0.020832255,0.0044273203,0.3388302],"study_design_scores_gemma":[0.0000063375123,0.000019101217,0.00010845392,0.0000051689817,0.0000070058277,0.000014639142,0.000010417191,0.99399996,0.0020897086,0.0032658956,0.00046638955,0.00000705167],"about_ca_topic_score_codex":0.004023741,"about_ca_topic_score_gemma":0.0065778526,"teacher_disagreement_score":0.004023741,"about_ca_system_score_codex":0.0005058578,"about_ca_system_score_gemma":0.00088338624,"threshold_uncertainty_score":0.008927524},"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":"dataset","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":[0.28434804,0.0028196583,0.091714695,0.0028596343,0.0025403935,0.0037018366,0.5133112,0.0112988185,0.08740575],"genre_scores_gemma":[0.17979854,0.0007699857,0.13039318,0.00053644174,0.0004301823,0.0039422717,0.6633475,0.0019245632,0.01885733],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984596,0.00039253882,0.00026983302,0.00034527972,0.0004124779,0.0001203901],"domain_scores_gemma":[0.9917964,0.002206992,0.0005252098,0.0010619917,0.0038449622,0.00056448067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016058191,0.00093334937,0.0005776467,0.0035659047,0.0016086877,0.0010590764,0.0010333094,0.00070307136,0.017072646],"category_scores_gemma":[0.0069185295,0.00050714397,0.0005140655,0.004691625,0.0007026363,0.0016731262,0.0014409065,0.0015185557,0.0062789735],"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":[0.00084628514,0.0009935794,0.016415002,0.0043000374,0.00013770843,0.0027784011,0.008181942,0.0032124855,0.06703721,0.011459311,0.56461406,0.32002398],"study_design_scores_gemma":[0.00033303953,0.00045169983,0.10650397,0.00049487303,0.00014361138,0.0026613656,0.004207536,0.019300198,0.03690002,0.0055717435,0.8231493,0.0002826296],"about_ca_topic_score_codex":0.009724562,"about_ca_topic_score_gemma":0.022023302,"teacher_disagreement_score":0.017072646,"about_ca_system_score_codex":0.0009266409,"about_ca_system_score_gemma":0.0018400345,"threshold_uncertainty_score":0.057113707},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034676336,0.00039648003,0.9528126,0.0008442618,0.000108060914,0.000441342,0.00024071455,0.0008836703,0.0095965145],"genre_scores_gemma":[0.8699888,0.00047234423,0.116421066,0.0001624773,0.00007219065,0.00039847946,0.00033809047,0.000112508904,0.012034094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739325,0.00075670163,0.00015709476,0.0004910907,0.0008066816,0.00039514678],"domain_scores_gemma":[0.99516606,0.0018836159,0.0005579721,0.0009105293,0.0010461768,0.00043568696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026856882,0.000721938,0.0011502282,0.001150614,0.0019810295,0.0023103433,0.0019258242,0.0016841944,0.008388017],"category_scores_gemma":[0.008004418,0.0004520499,0.00074781064,0.0010884379,0.0019579942,0.004706777,0.0037599602,0.0015509408,0.0012515414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008135884,0.0003400382,0.003087609,0.0005933087,0.00011201332,0.0011770839,0.0012114145,0.43713215,0.019036109,0.36123982,0.0072262846,0.16803065],"study_design_scores_gemma":[0.000079348734,0.0001382943,0.00026073237,0.000053081236,0.00003924943,0.00016852844,0.00014422426,0.87420917,0.0036833894,0.11395511,0.0072295684,0.00003926714],"about_ca_topic_score_codex":0.0041693393,"about_ca_topic_score_gemma":0.0049187304,"teacher_disagreement_score":0.008388017,"about_ca_system_score_codex":0.0016350799,"about_ca_system_score_gemma":0.004192219,"threshold_uncertainty_score":0.028060675},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027949568,0.00070561393,0.9529697,0.00038022455,0.00037229687,0.00011056041,0.003713106,0.00939299,0.00440595],"genre_scores_gemma":[0.38518113,0.00061426824,0.5876678,0.0005548647,0.00016986187,0.0003116973,0.01587435,0.001047186,0.00857878],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99907243,0.00023329428,0.000146859,0.00028614252,0.00018653879,0.00007477348],"domain_scores_gemma":[0.99690956,0.0009438737,0.00025219895,0.0011654947,0.0006500544,0.00007887022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011306454,0.0007697615,0.0005367663,0.0012778364,0.00038364055,0.00090205553,0.00130523,0.00091230596,0.004609697],"category_scores_gemma":[0.00605398,0.0002723511,0.00065677334,0.0013993077,0.00055895495,0.005321773,0.0013617533,0.0013366401,0.00329912],"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":[0.00064731686,0.00014699483,0.0061008716,0.0005161803,0.0000982777,0.00052137405,0.00053094584,0.05363701,0.03197392,0.043069478,0.021815035,0.8409426],"study_design_scores_gemma":[0.00006163494,0.00030139266,0.0031623777,0.00020552507,0.00013256921,0.0008205065,0.00028270157,0.7432603,0.07871496,0.09117325,0.08169733,0.00018745637],"about_ca_topic_score_codex":0.0018988965,"about_ca_topic_score_gemma":0.0036632437,"teacher_disagreement_score":0.004609697,"about_ca_system_score_codex":0.0005532678,"about_ca_system_score_gemma":0.000830068,"threshold_uncertainty_score":0.015420973},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22814189,0.0016547797,0.7602321,0.0011166313,0.00022991087,0.00017803635,0.0004547781,0.0014355896,0.0065562623],"genre_scores_gemma":[0.9339008,0.00034181683,0.059765138,0.0002600641,0.00007444994,0.00011956611,0.0004170208,0.000026790709,0.005094387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997769,0.00004583654,0.000016248969,0.00007647307,0.000043743166,0.00004088689],"domain_scores_gemma":[0.9997334,0.00013200872,0.000026717926,0.000017932469,0.00007373651,0.00001620555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042061132,0.00061356166,0.0004981744,0.0008322837,0.000401402,0.00067507225,0.00091182673,0.0008178564,0.00243951],"category_scores_gemma":[0.0012945536,0.00021182133,0.00072939036,0.0005246861,0.0003198067,0.0010556469,0.00060449046,0.0009161357,0.00039393877],"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":[0.0005469011,0.0005770287,0.009124928,0.00015542505,0.00024885955,0.00037466438,0.00025123966,0.30455363,0.016717272,0.008389597,0.0046986593,0.65436184],"study_design_scores_gemma":[0.000005321187,0.000044773922,0.00068095216,0.0000065186223,0.000026396117,0.000031571355,0.000017137601,0.9950873,0.0013048571,0.0024995226,0.00028988792,0.0000056713143],"about_ca_topic_score_codex":0.007025667,"about_ca_topic_score_gemma":0.0073598768,"teacher_disagreement_score":0.007025667,"about_ca_system_score_codex":0.00095892383,"about_ca_system_score_gemma":0.0006214701,"threshold_uncertainty_score":0.013969541},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6524201,0.0027648683,0.2918897,0.0074946815,0.0004907499,0.00074027496,0.012125262,0.006989219,0.025085144],"genre_scores_gemma":[0.92655957,0.0004338795,0.05904784,0.0006538389,0.000077413686,0.000104004626,0.0070043034,0.00009042019,0.006028763],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996376,0.00008270484,0.000026128331,0.00015224925,0.000054402135,0.000046899266],"domain_scores_gemma":[0.9991424,0.00040692618,0.00010937437,0.00012579325,0.00014968078,0.000065807275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005646201,0.0007639177,0.00032430567,0.0011490806,0.00038150136,0.00083743583,0.0009529514,0.0013676423,0.0036732699],"category_scores_gemma":[0.0039475644,0.00018951131,0.0006340155,0.0007264578,0.00037632274,0.00259598,0.00083909923,0.0009163774,0.0012665368],"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":[0.0012418838,0.0009918375,0.07349237,0.0008907429,0.00023713298,0.0011440775,0.0013929864,0.03786025,0.031836726,0.0129376035,0.04726824,0.79070616],"study_design_scores_gemma":[0.00007023315,0.0002947902,0.038146544,0.00014906778,0.00023367643,0.00073556206,0.0008275034,0.87658024,0.017848529,0.040169906,0.024879623,0.00006426575],"about_ca_topic_score_codex":0.008580718,"about_ca_topic_score_gemma":0.017078511,"teacher_disagreement_score":0.008580718,"about_ca_system_score_codex":0.00073903997,"about_ca_system_score_gemma":0.00074864976,"threshold_uncertainty_score":0.017061532},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04187302,0.00085410726,0.93568355,0.00084911817,0.00019561387,0.00045133627,0.0012382811,0.014339479,0.004515533],"genre_scores_gemma":[0.3499547,0.0005422931,0.63196343,0.00066137564,0.00016847019,0.00046666473,0.006057566,0.00087162416,0.009313925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987758,0.00043605757,0.000083698054,0.00038864888,0.0002419049,0.00007385989],"domain_scores_gemma":[0.99622524,0.002168415,0.00018626619,0.0007350556,0.00056978024,0.00011527595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016531212,0.0013484624,0.0009124598,0.0015880223,0.00046980538,0.0013239938,0.0017581827,0.0015936814,0.007825831],"category_scores_gemma":[0.0090687005,0.00044044337,0.0013452023,0.0009524807,0.00068039156,0.0043839095,0.0022334165,0.001905284,0.0026344927],"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":[0.0003672537,0.00029664428,0.0025752385,0.00066468614,0.00011384455,0.00037884252,0.0009665802,0.015132063,0.039756883,0.012712245,0.02034951,0.90668607],"study_design_scores_gemma":[0.00016413844,0.00037328765,0.0027179962,0.00009116985,0.00024071055,0.00095349795,0.00053473125,0.854339,0.07209875,0.040297605,0.028087385,0.0001016854],"about_ca_topic_score_codex":0.002415364,"about_ca_topic_score_gemma":0.0034511823,"teacher_disagreement_score":0.007825831,"about_ca_system_score_codex":0.00084385637,"about_ca_system_score_gemma":0.0011166784,"threshold_uncertainty_score":0.02617997},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050042056,0.00035569683,0.9338324,0.0019639218,0.00009915917,0.001118864,0.00212719,0.000539395,0.009921282],"genre_scores_gemma":[0.47656432,0.0004936728,0.5130173,0.0003419441,0.00007909295,0.0019405765,0.0023877479,0.00005110025,0.0051242164],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958823,0.0019192954,0.0004984095,0.0006558157,0.00078483316,0.0002594023],"domain_scores_gemma":[0.9958799,0.00281155,0.00034262304,0.00006899592,0.00077455596,0.00012237899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004989222,0.0014165295,0.0013050099,0.004941963,0.0013067555,0.003600526,0.0018842125,0.0015069849,0.0056427913],"category_scores_gemma":[0.0066011753,0.0005041756,0.0018450482,0.0039811884,0.00068382453,0.0026898126,0.0013548726,0.0013487455,0.00090469327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032311236,0.00044052416,0.006032669,0.00076899625,0.00024501132,0.000816667,0.0008138013,0.8262942,0.0024656295,0.036394216,0.005142816,0.1202624],"study_design_scores_gemma":[0.000036962127,0.00006728201,0.00064629456,0.000046304514,0.00005620507,0.00004379251,0.0003110955,0.9839401,0.00048698948,0.012713115,0.0016247145,0.000027128033],"about_ca_topic_score_codex":0.017158993,"about_ca_topic_score_gemma":0.01669472,"teacher_disagreement_score":0.017158993,"about_ca_system_score_codex":0.0039002225,"about_ca_system_score_gemma":0.004382955,"threshold_uncertainty_score":0.034118235},"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":"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":[0.12292883,0.0019529772,0.8664831,0.0012805788,0.00016165123,0.00013680292,0.00076042954,0.0035566527,0.002738954],"genre_scores_gemma":[0.91164666,0.0004902289,0.08274436,0.00044530936,0.0001496914,0.00013774236,0.0015001225,0.00011488649,0.0027709994],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997092,0.00009910942,0.000019099369,0.00007241181,0.000057388694,0.000042726842],"domain_scores_gemma":[0.999302,0.00044768583,0.00006480306,0.0000621989,0.000099050645,0.000024333896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008001686,0.00072612934,0.0005208937,0.00073606474,0.00025241717,0.00069378165,0.00091528456,0.000732878,0.0018015244],"category_scores_gemma":[0.002300781,0.00025629267,0.0007283478,0.000512644,0.0003547477,0.0010535236,0.000877467,0.0013805387,0.0003899747],"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":[0.0004455043,0.00048768308,0.0052487883,0.00020017546,0.00020764218,0.00022237073,0.00036006403,0.32527253,0.019505827,0.0059328075,0.008015136,0.63410157],"study_design_scores_gemma":[0.0000047289814,0.000021769085,0.00042620258,0.000005065194,0.000009018016,0.000009418201,0.000015034563,0.99398816,0.0014609499,0.0036792082,0.00037642565,0.0000040419272],"about_ca_topic_score_codex":0.0030440253,"about_ca_topic_score_gemma":0.004687699,"teacher_disagreement_score":0.0030440253,"about_ca_system_score_codex":0.0006950546,"about_ca_system_score_gemma":0.00039572793,"threshold_uncertainty_score":0.0060526133},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009845404,0.0001879625,0.9969819,0.00012526053,0.000036970563,0.00009150694,0.00013444148,0.0006057559,0.00085168396],"genre_scores_gemma":[0.06290907,0.0007552626,0.9325481,0.00010680789,0.000070109214,0.00030056085,0.0013982457,0.00014639508,0.0017653625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956631,0.00082302553,0.0003807539,0.00075381296,0.0020724272,0.00030686072],"domain_scores_gemma":[0.9979873,0.0005397334,0.00024601445,0.0006015946,0.0005278661,0.00009745656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003278491,0.0010280473,0.00172139,0.005120692,0.0017578313,0.0037383456,0.0032145295,0.001853092,0.0023027994],"category_scores_gemma":[0.010320182,0.00087942183,0.0030171745,0.005334978,0.0011995889,0.0067073978,0.004923148,0.002348175,0.0018926626],"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":[0.00009560771,0.00014799598,0.00225123,0.00048901263,0.0002096038,0.00081743894,0.00042329216,0.23287708,0.0053684083,0.47479126,0.012717831,0.2698112],"study_design_scores_gemma":[0.000011143512,0.000022352424,0.0003524314,0.00006158086,0.00003172506,0.00027509386,0.00015852276,0.824606,0.0019326166,0.15258396,0.019927911,0.000036681457],"about_ca_topic_score_codex":0.01179456,"about_ca_topic_score_gemma":0.0115600135,"teacher_disagreement_score":0.01179456,"about_ca_system_score_codex":0.002276333,"about_ca_system_score_gemma":0.0033342394,"threshold_uncertainty_score":0.023451805},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21498524,0.001722895,0.7646698,0.0011297383,0.00024787564,0.00035858987,0.001075168,0.0067851753,0.009025529],"genre_scores_gemma":[0.8691035,0.00039588724,0.115753725,0.00060862256,0.0002698509,0.0003100836,0.0040185493,0.00026820326,0.009271572],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935824,0.00016080403,0.000047892914,0.00022942496,0.000116496994,0.000087081724],"domain_scores_gemma":[0.99864286,0.00079800835,0.00009517662,0.0001343718,0.0002786464,0.000050942283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085989595,0.0011784581,0.0009607135,0.0020136337,0.00062758656,0.0011555721,0.0013988741,0.0010670014,0.0023085559],"category_scores_gemma":[0.0034484053,0.00054109487,0.001236955,0.0013246937,0.00065990887,0.0015221649,0.0011503838,0.0018609592,0.0010242693],"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":[0.0004148555,0.0008430748,0.0063109766,0.00021716184,0.00027057537,0.00042644472,0.00038276016,0.17447418,0.014549912,0.006223287,0.016435698,0.77945113],"study_design_scores_gemma":[0.000018120541,0.000034129036,0.00092686823,0.000007965191,0.000028817254,0.00003512842,0.000031891832,0.99149656,0.0017073791,0.004795455,0.0009063827,0.000011289424],"about_ca_topic_score_codex":0.008736108,"about_ca_topic_score_gemma":0.012114542,"teacher_disagreement_score":0.008736108,"about_ca_system_score_codex":0.0011769588,"about_ca_system_score_gemma":0.0009190658,"threshold_uncertainty_score":0.017370522},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13471554,0.00076250505,0.85515475,0.00017616802,0.00019675975,0.00015978981,0.00033328286,0.003235278,0.005265936],"genre_scores_gemma":[0.5433568,0.00048707615,0.44112548,0.00017924933,0.00008660204,0.0002136454,0.0026110525,0.0003487521,0.011591369],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996331,0.00008793104,0.00002889885,0.0001351415,0.00007468477,0.00004012702],"domain_scores_gemma":[0.99960643,0.00013711999,0.000029016497,0.00007172816,0.00013702732,0.000018675397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047447512,0.0006355652,0.0005959225,0.0006878676,0.0005542416,0.00058344775,0.00053598307,0.0004566738,0.0028818673],"category_scores_gemma":[0.0012418122,0.00018869757,0.0006970569,0.00065228634,0.0003485652,0.000979682,0.0006324204,0.00060094835,0.0016646802],"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":[0.00039949222,0.00022990865,0.0017171397,0.00040571133,0.00008049883,0.0006683163,0.00054531934,0.026735995,0.17400932,0.008978787,0.005261214,0.78096825],"study_design_scores_gemma":[0.000061377476,0.00066350255,0.003380689,0.000039254246,0.00012836793,0.0012979363,0.00035361652,0.81358033,0.15226378,0.008518704,0.019653529,0.000058916583],"about_ca_topic_score_codex":0.0041163554,"about_ca_topic_score_gemma":0.007836582,"teacher_disagreement_score":0.0041163554,"about_ca_system_score_codex":0.00032270345,"about_ca_system_score_gemma":0.00084529613,"threshold_uncertainty_score":0.009640753},"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":"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":[0.10436615,0.0011315994,0.8849159,0.00023751688,0.00014308761,0.00009971507,0.0006960435,0.006000882,0.002409088],"genre_scores_gemma":[0.80184245,0.0004614616,0.18666731,0.00019727078,0.00016956878,0.00021828598,0.004064748,0.00039944917,0.005979405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994986,0.00013218945,0.00004653546,0.00015358687,0.000111333364,0.000057673566],"domain_scores_gemma":[0.9982822,0.0007222213,0.00023305907,0.0002131442,0.0004956228,0.00005378819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075264095,0.0009812256,0.0008390005,0.0011806941,0.00023938199,0.00068094593,0.0010459372,0.00062806555,0.0012990407],"category_scores_gemma":[0.0036653797,0.00041440222,0.0005864601,0.000918639,0.0003938693,0.0019709058,0.00076038437,0.00094522006,0.0015045876],"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":[0.00058166956,0.0004323059,0.0039687515,0.00026893523,0.00017927255,0.00021431166,0.00022583727,0.21333718,0.03447475,0.004160315,0.007841494,0.73431516],"study_design_scores_gemma":[0.000008515519,0.000047753456,0.00048433585,0.000007001823,0.000012535088,0.000039884704,0.00002205371,0.9920656,0.004489966,0.0021097802,0.000700831,0.00001171257],"about_ca_topic_score_codex":0.0037312966,"about_ca_topic_score_gemma":0.006727579,"teacher_disagreement_score":0.0037312966,"about_ca_system_score_codex":0.00056818774,"about_ca_system_score_gemma":0.0006847917,"threshold_uncertainty_score":0.007419169},"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":"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":[0.00007725993,0.001486748,0.00043386163,0.02485135,0.96783495,0.00003610352,0.00018233414,0.00014973016,0.0049476237],"genre_scores_gemma":[0.00077989773,0.003250552,0.00046086215,0.011086048,0.94402534,0.000052087056,0.00029608415,0.0003576083,0.03969152],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963875,0.0004304699,0.00043957512,0.0005589951,0.0018580956,0.00032542198],"domain_scores_gemma":[0.97578377,0.0049108453,0.0009302303,0.0008947844,0.013935143,0.003545202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00430154,0.0019294057,0.0021619094,0.003105465,0.0026096883,0.008520373,0.0021588872,0.0046295356,0.11819914],"category_scores_gemma":[0.019330889,0.000718132,0.002230681,0.0015946939,0.0015216917,0.005633582,0.0018195638,0.0078731375,0.062038574],"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":[0.000013643531,0.000006352714,0.000024396888,0.00009980474,0.0000062869713,0.000030891628,0.000012294193,0.000013249187,0.00006588869,0.00027723433,0.99541074,0.004039177],"study_design_scores_gemma":[0.00001301836,0.000014050493,0.00017781799,0.00017605671,0.000014826909,0.00009249716,0.000056352084,0.00008978549,0.00009770458,0.0008079111,0.9984491,0.000010938027],"about_ca_topic_score_codex":0.0011154903,"about_ca_topic_score_gemma":0.0028108922,"teacher_disagreement_score":0.11819914,"about_ca_system_score_codex":0.002082961,"about_ca_system_score_gemma":0.0038697936,"threshold_uncertainty_score":0.39541554},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5933324,0.12185067,0.15674129,0.004071919,0.006118437,0.000861749,0.044819932,0.021354668,0.050848994],"genre_scores_gemma":[0.7914215,0.024988787,0.06765884,0.0011712444,0.00062917254,0.0006182543,0.09245226,0.0008931669,0.020166757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828076,0.00029286585,0.00024472518,0.00043197506,0.00058388314,0.00016587145],"domain_scores_gemma":[0.9986463,0.0004515803,0.00008878755,0.00017158012,0.0005788627,0.00006292066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028100903,0.00239515,0.0010152338,0.0020252736,0.0005547035,0.001265948,0.0015262803,0.0011415265,0.0028295924],"category_scores_gemma":[0.0061717085,0.00026628005,0.00094643526,0.0012180279,0.00035438957,0.0017346399,0.00086499425,0.0011054934,0.002248568],"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":[0.0016868919,0.0003926778,0.020663729,0.0024406419,0.0007672532,0.00039511648,0.00016038681,0.071994096,0.012009834,0.0013136844,0.08001074,0.8081649],"study_design_scores_gemma":[0.00014356223,0.0022590172,0.03950679,0.0011574624,0.00092364295,0.0012197971,0.00077386794,0.8279526,0.0653303,0.0035748468,0.056928333,0.0002297713],"about_ca_topic_score_codex":0.018293833,"about_ca_topic_score_gemma":0.017885681,"teacher_disagreement_score":0.018293833,"about_ca_system_score_codex":0.0011552728,"about_ca_system_score_gemma":0.0010049313,"threshold_uncertainty_score":0.03637469},"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":"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":[0.029050447,0.00012008087,0.96077913,0.00026629167,0.00006130015,0.000258399,0.0013061349,0.005393641,0.0027645375],"genre_scores_gemma":[0.13178875,0.00019876711,0.8597918,0.00011000553,0.000029329478,0.00021755166,0.005541423,0.0005964458,0.0017259712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976221,0.0005724189,0.0002542192,0.00073800934,0.0006936839,0.000119541895],"domain_scores_gemma":[0.9952923,0.0022440432,0.00029486127,0.0006824494,0.0013409818,0.00014546358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022107163,0.0009227721,0.00065213867,0.0031831535,0.0012238806,0.0017159521,0.0012614736,0.000798612,0.0029883306],"category_scores_gemma":[0.008169081,0.00058027584,0.0016260054,0.001609217,0.0008159512,0.004614009,0.003361072,0.0016609028,0.0018269783],"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":[0.00020114167,0.0004480955,0.008588881,0.0011154654,0.00024242658,0.00084358687,0.0024807395,0.023939908,0.065004565,0.03198661,0.017763017,0.8473856],"study_design_scores_gemma":[0.000053504664,0.00022406386,0.0063895998,0.00033355757,0.0002447475,0.0009786083,0.0033025101,0.7097864,0.10279201,0.08038501,0.09536686,0.0001430621],"about_ca_topic_score_codex":0.0057414696,"about_ca_topic_score_gemma":0.009888213,"teacher_disagreement_score":0.0057414696,"about_ca_system_score_codex":0.0010299373,"about_ca_system_score_gemma":0.0034520763,"threshold_uncertainty_score":0.01169157},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90055966,0.0040229564,0.037599392,0.0010972965,0.00082398107,0.0005935307,0.020940244,0.004982363,0.029380633],"genre_scores_gemma":[0.9162321,0.0010686252,0.037512828,0.00024591672,0.00038612532,0.0003009907,0.03114645,0.00014724661,0.012959754],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969673,0.000041062693,0.000019391206,0.00009210022,0.000084274456,0.000066427194],"domain_scores_gemma":[0.9994797,0.00013485223,0.00006674205,0.00009499946,0.0001615921,0.0000622074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039497172,0.0011662657,0.00044100484,0.0027797325,0.0004161962,0.0007381795,0.0004936059,0.00081381743,0.0025093262],"category_scores_gemma":[0.0015684263,0.000099198885,0.0006030067,0.0010193246,0.0003617711,0.0011371874,0.0007944582,0.00058443623,0.0016601699],"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":[0.0015260831,0.0008505678,0.052754745,0.0014557433,0.00032889258,0.001872505,0.000928374,0.014451615,0.065616935,0.0020647992,0.062265497,0.7958842],"study_design_scores_gemma":[0.00008559525,0.0007608027,0.18212324,0.000501811,0.00038488946,0.0025644314,0.006563695,0.6083951,0.11300614,0.0041301376,0.081298,0.00018607246],"about_ca_topic_score_codex":0.0035850247,"about_ca_topic_score_gemma":0.007591673,"teacher_disagreement_score":0.0035850247,"about_ca_system_score_codex":0.00041553754,"about_ca_system_score_gemma":0.0002698108,"threshold_uncertainty_score":0.008394539},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5258593,0.041372407,0.39933565,0.001821525,0.001416863,0.00031963867,0.0011702662,0.005451874,0.023252523],"genre_scores_gemma":[0.904706,0.006121155,0.081848845,0.00020035858,0.00018939562,0.00010808989,0.0011402884,0.00009096787,0.0055949246],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989957,0.00017725959,0.00009265263,0.00018583414,0.0004699553,0.000078600875],"domain_scores_gemma":[0.9982761,0.00086658675,0.00015072282,0.00008886829,0.000570863,0.00004677647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015188197,0.00085845345,0.00087446644,0.0014747321,0.00023852008,0.0014765974,0.0009098107,0.0008748198,0.0014453998],"category_scores_gemma":[0.0034659721,0.0002407039,0.0005315061,0.0012403713,0.0002451207,0.0019293148,0.0005015793,0.00074535666,0.0005230857],"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":[0.00081564434,0.00037531857,0.0105688805,0.00068222726,0.0003476697,0.00013898806,0.00009615796,0.1897396,0.004746904,0.0021378943,0.004644032,0.7857067],"study_design_scores_gemma":[0.0000143317875,0.00028285553,0.003538018,0.00007275119,0.00005616133,0.0000628272,0.00006886242,0.9879651,0.004757318,0.0010403595,0.0021122803,0.000029164998],"about_ca_topic_score_codex":0.009277633,"about_ca_topic_score_gemma":0.006115963,"teacher_disagreement_score":0.009277633,"about_ca_system_score_codex":0.0009596884,"about_ca_system_score_gemma":0.0005847666,"threshold_uncertainty_score":0.01844728},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12963678,0.00036114594,0.8644687,0.0005839446,0.0001071838,0.0002879691,0.00037523612,0.0017981188,0.0023809732],"genre_scores_gemma":[0.55516,0.00016743093,0.4409763,0.0002238276,0.00008358755,0.00050996855,0.0011330192,0.00020688708,0.0015390657],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918014,0.0003972112,0.000075420045,0.00016763319,0.00011169067,0.00006791647],"domain_scores_gemma":[0.998467,0.00081241503,0.00018989522,0.00012319758,0.0003643456,0.00004313216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003154666,0.0012808663,0.0007850646,0.0014942852,0.00056443043,0.0012725136,0.00075647724,0.00093152496,0.0015662281],"category_scores_gemma":[0.0079274345,0.00033706528,0.0009212659,0.0009741232,0.00041081308,0.0011114415,0.0007308442,0.0013974034,0.00086588814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042421615,0.00033444885,0.013668723,0.00024976142,0.0002023552,0.00022592142,0.0005629411,0.54319954,0.0146813635,0.006004201,0.008912541,0.411534],"study_design_scores_gemma":[0.000006905645,0.000020548807,0.00069435313,0.00000931684,0.000008104768,0.000013426603,0.000056533936,0.9963701,0.0010338912,0.0013344708,0.00044650835,0.0000058783276],"about_ca_topic_score_codex":0.0030503874,"about_ca_topic_score_gemma":0.0031250818,"teacher_disagreement_score":0.003154666,"about_ca_system_score_codex":0.0007869232,"about_ca_system_score_gemma":0.00083013915,"threshold_uncertainty_score":0.016683638},"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":"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":[0.07792418,0.004488471,0.87929296,0.0022409172,0.0004914761,0.0003781079,0.013634348,0.018798074,0.0027514088],"genre_scores_gemma":[0.55864143,0.0027557039,0.4016631,0.0011182677,0.00029997213,0.0006881921,0.02363595,0.00038625367,0.010811146],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997441,0.000048264574,0.000034420056,0.0000758722,0.000061012084,0.00003629728],"domain_scores_gemma":[0.99969757,0.00015195001,0.000032853877,0.00003402032,0.000066034765,0.000017612654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059735926,0.00084987504,0.00068745663,0.0010766268,0.0002152934,0.0005590567,0.00097331754,0.0010441542,0.0029910353],"category_scores_gemma":[0.0016358545,0.00026827815,0.0009739176,0.0009982787,0.00019785302,0.0013794143,0.0007677681,0.0013704541,0.0018267429],"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":[0.0006162754,0.000411297,0.0051649148,0.0004547529,0.00018158667,0.00051496015,0.00014243864,0.07662385,0.018832006,0.003505772,0.03228579,0.8612664],"study_design_scores_gemma":[0.000035322963,0.00015869865,0.0016935847,0.00003294793,0.000048611382,0.0002433689,0.000024563078,0.9772406,0.0061400756,0.0055389153,0.008823728,0.000019622352],"about_ca_topic_score_codex":0.005755677,"about_ca_topic_score_gemma":0.008267957,"teacher_disagreement_score":0.005755677,"about_ca_system_score_codex":0.00071831315,"about_ca_system_score_gemma":0.0011156491,"threshold_uncertainty_score":0.01144433},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39737535,0.005791165,0.5646153,0.0016026505,0.0011245748,0.00021266757,0.0026737894,0.012366098,0.014238305],"genre_scores_gemma":[0.92050105,0.00080909074,0.061191462,0.0005738267,0.000107066604,0.00009543939,0.002928373,0.00011461042,0.013679037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972063,0.000029463094,0.000012355376,0.00009239891,0.000062849256,0.000082233346],"domain_scores_gemma":[0.99971753,0.000055071017,0.0000315852,0.000034162334,0.00012945103,0.00003218673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005428717,0.0012840426,0.0006057702,0.0007749434,0.00036052646,0.00060258585,0.0012456059,0.0009085321,0.0020614453],"category_scores_gemma":[0.0010019802,0.00036613725,0.0005078377,0.0005648836,0.00025261627,0.0014146926,0.00096093956,0.0011126259,0.0012804015],"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":[0.00069695176,0.000687507,0.012057646,0.00029749895,0.00030924525,0.00059914065,0.00022613606,0.10784007,0.042789284,0.0022421787,0.021511463,0.8107429],"study_design_scores_gemma":[0.00001036567,0.000096738026,0.0017491713,0.000021747786,0.000039111314,0.00007130872,0.00003519312,0.9877331,0.007903759,0.00096799963,0.0013555165,0.000016090531],"about_ca_topic_score_codex":0.013378076,"about_ca_topic_score_gemma":0.023328036,"teacher_disagreement_score":0.013378076,"about_ca_system_score_codex":0.00083648,"about_ca_system_score_gemma":0.00092203345,"threshold_uncertainty_score":0.02660042},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011737227,0.00043916257,0.9760543,0.00032132945,0.000089599715,0.00011515302,0.000444331,0.0088704275,0.0019284291],"genre_scores_gemma":[0.14058004,0.00035818602,0.8498511,0.00048087674,0.0001713339,0.0003271618,0.0030181685,0.0006744171,0.00453875],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9959306,0.00093112036,0.00039102812,0.0010563914,0.0015392597,0.00015160165],"domain_scores_gemma":[0.99266785,0.0027215884,0.00036038907,0.002482222,0.0016367034,0.00013128805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024751213,0.0010568253,0.0014634689,0.0028666405,0.000791579,0.0025591285,0.0034819613,0.0013211904,0.0026186907],"category_scores_gemma":[0.010418058,0.0005567497,0.0010841081,0.0040851803,0.0015064484,0.003204772,0.0023089184,0.002456186,0.0049341912],"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":[0.00027247082,0.0003201584,0.002150466,0.00022923763,0.00013978551,0.00035356445,0.00030510672,0.08076621,0.025499452,0.015290992,0.010202179,0.86447036],"study_design_scores_gemma":[0.000065441076,0.00015162445,0.00064990076,0.00002460691,0.00005231472,0.00042533092,0.0000946471,0.93447083,0.026024114,0.02658449,0.011403231,0.000053510357],"about_ca_topic_score_codex":0.0035547568,"about_ca_topic_score_gemma":0.0059404694,"teacher_disagreement_score":0.0035547568,"about_ca_system_score_codex":0.00070720987,"about_ca_system_score_gemma":0.0024083068,"threshold_uncertainty_score":0.013089895},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09279989,0.0012683265,0.90074706,0.00031222307,0.00015617095,0.000089067915,0.0006776812,0.0019658655,0.0019837713],"genre_scores_gemma":[0.8096068,0.001291546,0.17573471,0.00022737183,0.00018881902,0.00025797426,0.00477657,0.00019849358,0.0077176844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955684,0.00009982144,0.000039052855,0.0001703793,0.0000793573,0.000054442473],"domain_scores_gemma":[0.99952054,0.00014328968,0.000047187077,0.00010358348,0.0001532299,0.0000321297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004026518,0.0011884577,0.0007506169,0.00091390294,0.0003005513,0.0005149595,0.00083741394,0.00048326945,0.0018379075],"category_scores_gemma":[0.0015443653,0.00026396816,0.00077052996,0.001630798,0.00040574413,0.0023822722,0.0009714679,0.0011489562,0.00090944796],"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":[0.0001711837,0.0002080612,0.0034349652,0.00021261047,0.00012064775,0.000108234104,0.00020066876,0.074397966,0.014162626,0.010067125,0.010495007,0.8864209],"study_design_scores_gemma":[0.000014343927,0.00009720097,0.0008987217,0.000011113808,0.000034263314,0.000057902696,0.000050440958,0.98532087,0.0038984297,0.007786679,0.0018100444,0.000019997644],"about_ca_topic_score_codex":0.0037890018,"about_ca_topic_score_gemma":0.006093041,"teacher_disagreement_score":0.0037890018,"about_ca_system_score_codex":0.00041508404,"about_ca_system_score_gemma":0.0008894226,"threshold_uncertainty_score":0.007533908},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04602083,0.0014155029,0.9424433,0.00044644685,0.00028630192,0.00013360345,0.0008737618,0.0053633256,0.0030168982],"genre_scores_gemma":[0.61270714,0.00093847484,0.3662476,0.0007212554,0.00019698271,0.0005208534,0.004750101,0.00036857714,0.013549059],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997427,0.00006912649,0.000012251408,0.000105302715,0.000040413517,0.000030231397],"domain_scores_gemma":[0.9996741,0.00012457336,0.000030406214,0.00005631339,0.000092093214,0.000022538517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008609918,0.0013172695,0.000621362,0.0005841124,0.0002813216,0.0005384196,0.001363426,0.000995274,0.0023284669],"category_scores_gemma":[0.0016676045,0.0003087246,0.00077153504,0.00048614072,0.00031304412,0.0011066466,0.0010134397,0.0015756884,0.0010625573],"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":[0.00056491746,0.00042971328,0.0028152731,0.00022477274,0.00033568646,0.00019953148,0.000108592176,0.22731584,0.022778723,0.0038283495,0.020943923,0.7204547],"study_design_scores_gemma":[0.000017050208,0.00007994142,0.00073655567,0.000009898536,0.000023270115,0.000046911042,0.0000187418,0.9898543,0.0039368137,0.0032381075,0.0020229626,0.000015422453],"about_ca_topic_score_codex":0.002369458,"about_ca_topic_score_gemma":0.0051750513,"teacher_disagreement_score":0.002369458,"about_ca_system_score_codex":0.0005080468,"about_ca_system_score_gemma":0.00041051558,"threshold_uncertainty_score":0.007789433},"labels":[],"label_agreement":null}]}