{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":28,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":28,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"a762c0bd551b","filters":{"venue":"ACM Transactions on Asian and Low-Resource Language Information Processing"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01449092846415819,"gpt":0.2633936088301868,"spread":0.2489026803660286,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002173796,0.0002298555,0.0002316455,0.0003136345,0.001074135,0.0003491952,0.000498947,0.000291824,0.0000330973],"category_scores_gemma":[0.0002095281,0.0002039495,0.00009044843,0.0006906599,0.00008644745,0.0002406144,0.00002222842,0.0005122626,0.00001043698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006286272,"about_ca_system_score_gemma":0.000158653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006654391,"about_ca_topic_score_gemma":0.00003630515,"domain_scores_codex":[0.9986103,0.00002183269,0.0004152647,0.0003332378,0.0002649544,0.0003543975],"domain_scores_gemma":[0.9987023,0.0003327682,0.000211149,0.0005447629,0.0001078363,0.0001011694],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005317412,0.0001024924,0.000002145009,0.0001504495,0.00001605419,0.000006234593,0.026273,0.001172286,0.00005878264,0.005147434,0.00005741855,0.9669605],"study_design_scores_gemma":[0.008618547,0.000565529,0.0004650638,0.002843326,0.0002251423,0.0003521182,0.1508696,0.6485045,0.1091034,0.04086172,0.03441584,0.003175278],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05322408,0.00007921061,0.9385755,0.006511456,0.00007915219,0.0002932303,0.00002937347,0.0004968257,0.0007111661],"genre_scores_gemma":[0.9192349,0.000004421293,0.07755245,0.002919416,0.00006350466,0.000128753,0.00003097647,0.00001707691,0.00004847322],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9637852,"threshold_uncertainty_score":0.831682,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Hyperparameter; Arabic; Computer science; Sentiment analysis; Artificial intelligence; Machine learning; Algorithm; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.01579146721184079,"gpt":0.2740916518683625,"spread":0.2583001846565218,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000486507,0.0002171669,0.000215985,0.001129933,0.0004461105,0.001028242,0.0003820113,0.0001395683,0.00002293929],"category_scores_gemma":[0.00006588708,0.0002074624,0.0001241416,0.00150779,0.00004931716,0.002705916,0.00001975776,0.0002893596,0.000006712129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001400294,"about_ca_system_score_gemma":0.00006457428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001328639,"about_ca_topic_score_gemma":0.000002095722,"domain_scores_codex":[0.9985561,0.00007220641,0.0004937145,0.0003631896,0.0002754624,0.0002392946],"domain_scores_gemma":[0.9990209,0.00009324861,0.0002109159,0.0004774611,0.0001161265,0.00008135384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001789906,0.00005378472,0.00001778587,0.0003108402,0.0001245259,0.000001572023,0.006941827,0.04083479,0.002468273,0.0002772362,0.00001304894,0.9489384],"study_design_scores_gemma":[0.0001674295,0.00004488417,0.00004076368,0.0001492221,0.0001302474,0.00002541228,0.0009370808,0.9840153,0.01118724,0.00006079605,0.003006093,0.0002354786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00041604,0.0001852714,0.9969082,0.0007390804,0.00004375333,0.0005950091,0.00004895138,0.0008990866,0.0001645339],"genre_scores_gemma":[0.4495082,0.00002099452,0.5494493,0.0002801624,0.00002431126,0.0002675361,0.0003028241,0.00002000047,0.0001267363],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9487029,"threshold_uncertainty_score":0.9915365,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006320644909480506,"gpt":0.2400011345345139,"spread":0.2336804896250334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003363958,0.0003595604,0.0002825147,0.0004748724,0.0004738464,0.001067649,0.0007737539,0.0002066374,0.00005708016],"category_scores_gemma":[0.00003187736,0.000326484,0.0001066763,0.0007574012,0.00006035813,0.003660928,0.00003809625,0.0006756634,0.00001551599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009528218,"about_ca_system_score_gemma":0.00004993688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001557195,"about_ca_topic_score_gemma":0.000006204365,"domain_scores_codex":[0.9980242,0.000100159,0.0005855858,0.0003951213,0.0004496262,0.0004452729],"domain_scores_gemma":[0.9987193,0.00006433873,0.0002980771,0.0006553811,0.00009691306,0.0001660003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004608478,0.0000534301,0.00001534456,0.000254134,0.00001189456,0.000005080989,0.0113506,0.006626465,0.000554779,0.000112385,0.00001465913,0.9809551],"study_design_scores_gemma":[0.0007520326,0.0001149725,0.00002759383,0.0004989898,0.00002432044,0.000119882,0.00135022,0.9900193,0.005350165,0.0001152179,0.001138522,0.0004887399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02684149,0.001364319,0.9690135,0.000810699,0.0001355123,0.0004668872,0.00001415593,0.0007771547,0.0005763586],"genre_scores_gemma":[0.9381686,0.000008525964,0.05986655,0.001700868,0.00005713012,0.00001941433,0.00006700108,0.0000261181,0.00008580019],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9833929,"threshold_uncertainty_score":0.9999694,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01375791771308319,"gpt":0.2626968309772169,"spread":0.2489389132641337,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005789272,0.0001973875,0.0001523469,0.000327985,0.0008525276,0.0005619516,0.0004946513,0.0001716695,0.0001046991],"category_scores_gemma":[0.00009618451,0.0001844036,0.0000606067,0.0007340889,0.0001197871,0.002390307,0.00002382237,0.0003666255,0.0002565452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006354148,"about_ca_system_score_gemma":0.00007338056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007455498,"about_ca_topic_score_gemma":0.000005488002,"domain_scores_codex":[0.9985982,0.00009553627,0.0003876652,0.000244209,0.0003193708,0.0003550326],"domain_scores_gemma":[0.9989685,0.00004908616,0.0001798685,0.0004660046,0.0001434386,0.0001931313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002663063,0.00002658871,0.00002610321,0.00006514576,0.000008228041,0.000001766444,0.02132571,0.00004127606,0.0001777628,0.002119878,0.0000557575,0.9761251],"study_design_scores_gemma":[0.007274581,0.00167656,0.01300594,0.002138456,0.0001949817,0.0008314048,0.03869624,0.4627397,0.1870938,0.01030223,0.2716025,0.004443602],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01895288,0.0000735268,0.974395,0.002918742,0.0001487705,0.0001747228,0.00001211309,0.0004736571,0.002850567],"genre_scores_gemma":[0.9840354,0.0000037786,0.01374333,0.00172192,0.00008897152,0.00001731835,0.00003139912,0.000008987851,0.0003489027],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9716815,"threshold_uncertainty_score":0.7519762,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01008739308180225,"gpt":0.2965891003532382,"spread":0.286501707271436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002689075,0.000136614,0.0001578601,0.0002886514,0.001041162,0.00004948067,0.0001284678,0.00005311777,0.0008132469],"category_scores_gemma":[0.00001733721,0.0001537668,0.00007254873,0.0002818614,0.0000468025,0.0005199637,0.00001754757,0.0003051651,0.00001128649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001351944,"about_ca_system_score_gemma":0.00002321534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003963739,"about_ca_topic_score_gemma":0.000009367472,"domain_scores_codex":[0.9988135,0.00008720803,0.0004204768,0.0001610329,0.0002474202,0.0002703392],"domain_scores_gemma":[0.9993756,0.00006280575,0.0003082637,0.0001480096,0.00003459879,0.00007072273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004488474,0.0002347522,0.0002653691,0.0003757318,0.00005507732,0.000001717928,0.09032866,0.002184559,0.0003607508,0.00005584121,0.00004061364,0.9056481],"study_design_scores_gemma":[0.003529021,0.000524482,0.001451993,0.0001251893,0.00008179678,0.00008001198,0.9521397,0.03252032,0.001508628,0.00003690966,0.007683482,0.0003184705],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8418358,0.0002299204,0.1457562,0.0005831054,0.0001985437,0.001107581,0.0001462747,0.0001425781,0.01000002],"genre_scores_gemma":[0.997389,0.000002226432,0.0009886058,0.0002864308,0.00001864543,0.0001947685,0.0002886816,0.0000188631,0.000812806],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9053296,"threshold_uncertainty_score":0.8904483,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01738602236647154,"gpt":0.2582952664607165,"spread":0.2409092440942449,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003703457,0.0001808585,0.0001383276,0.0004514098,0.0006944394,0.0006711963,0.0005102709,0.0001243574,0.00001405217],"category_scores_gemma":[0.0001384787,0.0001708693,0.00003202312,0.0006445589,0.00008463257,0.001903529,0.00003390826,0.0002721526,0.0000850596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003169009,"about_ca_system_score_gemma":0.00006180423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001627194,"about_ca_topic_score_gemma":0.00001935791,"domain_scores_codex":[0.9986916,0.00005781652,0.000303819,0.0003165565,0.0003703797,0.0002598228],"domain_scores_gemma":[0.9990328,0.0001204396,0.0001426922,0.0005389191,0.00005663486,0.0001084993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003856083,0.00002854759,0.000004753299,0.00007862828,0.000006960895,0.000005062158,0.01442319,0.0002216473,0.000479638,0.00005496953,0.0003586452,0.9842994],"study_design_scores_gemma":[0.00139476,0.00009686001,0.00321453,0.0001616439,0.00002756908,0.00002716131,0.01849128,0.9684137,0.002841527,0.0001317508,0.004764363,0.0004349159],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05982551,0.00004334612,0.9278081,0.006329489,0.0001550354,0.0003788904,0.0001108703,0.001312421,0.004036325],"genre_scores_gemma":[0.9907244,0.00001480845,0.008207559,0.0006771252,0.00006094527,0.00002080237,0.0002315195,0.00001345745,0.00004934665],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9838645,"threshold_uncertainty_score":0.6967849,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01779395492959392,"gpt":0.2724116228654583,"spread":0.2546176679358644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002715777,0.0002070092,0.0002717394,0.0004792539,0.0006038231,0.0006147194,0.0003443814,0.00006555083,0.0002268571],"category_scores_gemma":[0.00003818132,0.0002000768,0.0002503034,0.001378209,0.0000265197,0.001032284,0.00003280245,0.0001357408,0.00003044923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000818396,"about_ca_system_score_gemma":0.0001470964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001710113,"about_ca_topic_score_gemma":0.00008948804,"domain_scores_codex":[0.9984533,0.0000458609,0.0004590089,0.0003316558,0.0003925044,0.0003176613],"domain_scores_gemma":[0.9987973,0.00006862088,0.0002746754,0.00053815,0.0001376209,0.0001836418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009600146,0.0003300722,0.0007824018,0.0002678359,0.0006969546,0.0000254439,0.03736782,0.01862528,0.001200582,0.0006663552,0.0007429473,0.9391983],"study_design_scores_gemma":[0.00355352,0.00007131267,0.001014057,0.0002032309,0.0005543367,0.0000277392,0.01634705,0.9414389,0.02609161,0.0001017758,0.009952578,0.0006439138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009837416,0.0001943958,0.9866713,0.002287678,0.00005885495,0.0001584572,0.00003836281,0.0001253368,0.0006281699],"genre_scores_gemma":[0.895964,0.000006318792,0.09920857,0.002717314,0.00004691161,0.00002625478,0.0002513081,0.00001307603,0.001766264],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9385544,"threshold_uncertainty_score":0.8158897,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01459727850774725,"gpt":0.3173217739189699,"spread":0.3027244954112226,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0004014942,0.0001704082,0.0002505168,0.0003104104,0.001543418,0.0001039644,0.00008580376,0.00005694518,0.0003088925],"category_scores_gemma":[0.000006496034,0.0001716937,0.00009543732,0.0004576021,0.00004514225,0.0002528296,0.000006759184,0.0001813522,0.000005019687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00022509,"about_ca_system_score_gemma":0.0000468259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001327671,"about_ca_topic_score_gemma":0.0001481823,"domain_scores_codex":[0.9986026,0.0001470255,0.0004691928,0.0002191979,0.0001954149,0.000366597],"domain_scores_gemma":[0.9992943,0.00008473967,0.0002460702,0.0001885599,0.00001873253,0.0001676274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004533204,0.0001649553,0.0007250716,0.0002050068,0.0001484381,0.000001723334,0.03198436,0.001626142,0.00001549808,0.00006884075,0.0001243322,0.9644823],"study_design_scores_gemma":[0.0250018,0.004972827,0.03240959,0.0004222282,0.001153466,0.0003072037,0.6801742,0.2034719,0.0001929464,0.0002475913,0.04995376,0.001692498],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4010848,0.00171557,0.5744048,0.01284725,0.0003699658,0.003226168,0.001640092,0.0004157063,0.004295681],"genre_scores_gemma":[0.9920132,0.000005619911,0.003271739,0.00309115,0.00004634976,0.0003310749,0.001081257,0.00001556392,0.00014411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9627898,"threshold_uncertainty_score":0.9997565,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01204690886698901,"gpt":0.2703067519801377,"spread":0.2582598431131487,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002517594,0.0001040274,0.0001593209,0.0003629325,0.0001608031,0.0001635228,0.0002599095,0.0001006329,0.000003520765],"category_scores_gemma":[0.0001057515,0.00009350008,0.00002777587,0.0004122428,0.00005077499,0.001336505,0.00001936299,0.0001658499,0.000003636715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001141203,"about_ca_system_score_gemma":0.00004033058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002454499,"about_ca_topic_score_gemma":0.00003496189,"domain_scores_codex":[0.9992534,0.00002233651,0.000285131,0.0001341402,0.0001110505,0.0001939348],"domain_scores_gemma":[0.999404,0.000206825,0.0001272471,0.0001942689,0.00002842758,0.00003925938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002198285,0.00001302113,0.00005538138,0.0002618306,0.000006438438,0.000002288992,0.09072652,0.0004781987,0.0001205965,0.002066212,0.000006498679,0.906241],"study_design_scores_gemma":[0.003519363,0.0003404832,0.01124212,0.002305562,0.00004772027,0.0001439638,0.2864012,0.6510721,0.006500038,0.03587526,0.001587214,0.000965006],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1325027,0.00009930104,0.8644888,0.001935247,0.00004589531,0.0001567084,0.000004542495,0.0001693108,0.000597454],"genre_scores_gemma":[0.9518368,0.0000228871,0.04746981,0.0006062727,0.000008059321,0.00002032982,0.000005000853,0.000004949999,0.00002587729],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.905276,"threshold_uncertainty_score":0.3812822,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01945753801904997,"gpt":0.2787941065836793,"spread":0.2593365685646293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004271037,0.0001825196,0.0002117593,0.001223145,0.0008273318,0.0006097253,0.0003195975,0.00008634888,0.00004703144],"category_scores_gemma":[0.0000588063,0.0001842055,0.0002073481,0.002185646,0.00003972628,0.00155316,0.00001729768,0.0001782477,0.00002042558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007495355,"about_ca_system_score_gemma":0.00006361922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001472457,"about_ca_topic_score_gemma":0.000005985881,"domain_scores_codex":[0.998552,0.00005761339,0.0004657923,0.0002807435,0.0003534287,0.000290447],"domain_scores_gemma":[0.9991941,0.0001058368,0.0002250004,0.0002760421,0.0001044395,0.00009460133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002447324,0.00003468826,0.0005024328,0.0001474528,0.0001209373,0.000001460812,0.006734354,0.3231993,0.0007517844,0.0001360017,0.00000484013,0.6683422],"study_design_scores_gemma":[0.0003552608,0.00003690609,0.001426782,0.0001526919,0.0001235253,0.000002828335,0.00863733,0.9870909,0.001668792,0.00005455187,0.0002324819,0.0002179506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07340945,0.0000402992,0.9253358,0.0005624267,0.00004827682,0.0001506887,0.000006396798,0.0002786928,0.0001680025],"genre_scores_gemma":[0.961781,0.000005350748,0.03755666,0.0003136676,0.00002953643,0.00001746605,0.000178463,0.00001129376,0.0001065997],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8883715,"threshold_uncertainty_score":0.7511683,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01515014805817039,"gpt":0.2638164520548695,"spread":0.2486663039966991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005039948,0.0002360678,0.00018564,0.0002936778,0.002088356,0.001828089,0.001115764,0.0001549045,0.000005430438],"category_scores_gemma":[0.000527277,0.0002165299,0.00007917204,0.0001586238,0.0000991492,0.002009466,0.00003799117,0.0003748836,0.000004335393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007325741,"about_ca_system_score_gemma":0.00009998801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000212658,"about_ca_topic_score_gemma":0.000005064299,"domain_scores_codex":[0.9986545,0.00003740476,0.0003848591,0.0003031407,0.0003016276,0.0003184988],"domain_scores_gemma":[0.9982789,0.00009485324,0.000424872,0.0009345651,0.0001368173,0.0001299882],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003073807,0.00004945496,0.00001247066,0.0003816616,0.000008359399,0.000001649406,0.008379301,0.0003993378,0.000153822,0.0007064222,0.00001644607,0.9898604],"study_design_scores_gemma":[0.00254028,0.0001897747,0.0002448831,0.0005837737,0.0000934493,0.00004323237,0.004423623,0.9546574,0.02883051,0.003244843,0.004017049,0.00113119],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004141963,0.0002736195,0.9951474,0.001010773,0.00006547687,0.0004572142,0.00001655446,0.0005357395,0.002079021],"genre_scores_gemma":[0.5749272,7.649986e-7,0.4244277,0.0004211371,0.000036719,0.00007934606,0.00002267829,0.00001099614,0.00007352574],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9887291,"threshold_uncertainty_score":0.9992108,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01058042370573135,"gpt":0.2460914673921367,"spread":0.2355110436864053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003312281,0.0001876979,0.000152515,0.0006510182,0.0003912392,0.0008081297,0.0002707381,0.0001133934,0.00001295936],"category_scores_gemma":[0.00007983571,0.0001810686,0.00008127868,0.0006111269,0.00003858053,0.002052461,0.00001168347,0.0003192764,0.00003506906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009278646,"about_ca_system_score_gemma":0.00004749166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002121519,"about_ca_topic_score_gemma":0.0001413285,"domain_scores_codex":[0.9987935,0.00003852598,0.0003663266,0.0002651327,0.0002320315,0.0003044747],"domain_scores_gemma":[0.9994841,0.00008947722,0.00008183216,0.0002058003,0.00005214529,0.00008660274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002707809,0.0000262021,5.832507e-7,0.000200633,0.000008429074,0.000009647951,0.02299634,0.0001261783,0.0005362112,0.00002831834,0.000008501917,0.9760319],"study_design_scores_gemma":[0.001917542,0.0001425413,0.0002537383,0.0004986962,0.00004116576,0.0002466864,0.009957486,0.8919809,0.08371741,0.0008043624,0.009770795,0.0006686566],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02820103,0.0001512265,0.9694179,0.0007022134,0.0002504069,0.0003185181,0.00001350417,0.0004833724,0.0004618494],"genre_scores_gemma":[0.9830588,0.00001016764,0.0163522,0.0003139503,0.00007184085,0.00008066469,0.00001986866,0.00001643445,0.00007614795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9753632,"threshold_uncertainty_score":0.7792813,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01066165886134542,"gpt":0.3162883851803784,"spread":0.305626726319033,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004639502,0.0001806454,0.0001536754,0.0001970967,0.002078561,0.0001775649,0.0002757068,0.00006167884,0.001278344],"category_scores_gemma":[0.00001816419,0.0001564485,0.00007456626,0.0002213086,0.00006257967,0.0004933949,0.00002147332,0.0004074516,0.00002998811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000853891,"about_ca_system_score_gemma":0.00004163592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002026589,"about_ca_topic_score_gemma":0.00002964384,"domain_scores_codex":[0.9986142,0.00007082587,0.0004496296,0.0001900342,0.0003052384,0.0003700794],"domain_scores_gemma":[0.9992027,0.0001308855,0.0002235979,0.0003195925,0.00002981335,0.00009338075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002072834,0.0000904377,0.00006928261,0.000375506,0.00003663868,0.00000649053,0.3331686,0.0003060241,0.000095966,0.00006011394,0.0003602777,0.6652234],"study_design_scores_gemma":[0.001873705,0.0002555698,0.003987469,0.0002318327,0.00007581085,0.0004375995,0.9587514,0.004033305,0.000355614,0.00006670884,0.02954024,0.0003906876],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9207551,0.00171884,0.0437499,0.02100067,0.000803379,0.002748845,0.0006596211,0.0004180032,0.008145577],"genre_scores_gemma":[0.9927125,0.000004871969,0.0006535394,0.004691253,0.00006748154,0.0003232906,0.0002033047,0.00002796105,0.001315775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6648327,"threshold_uncertainty_score":0.9996346,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00992098405943372,"gpt":0.2561712473687812,"spread":0.2462502633093475,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005080866,0.0002791135,0.0002821195,0.0006934553,0.0004034665,0.0003578201,0.0005200648,0.0001824264,0.00001316638],"category_scores_gemma":[0.00009759755,0.0002660742,0.00009702698,0.0008114404,0.00009667489,0.001710801,0.00002857333,0.0002890959,0.000004088101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003467571,"about_ca_system_score_gemma":0.00006652898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001435216,"about_ca_topic_score_gemma":0.000007853946,"domain_scores_codex":[0.9983471,0.00006148129,0.0005321371,0.0003283223,0.0003647283,0.0003662572],"domain_scores_gemma":[0.998848,0.0002036574,0.0002691637,0.0004721925,0.00008123204,0.0001257655],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000646422,0.00003897188,0.000004935459,0.001034361,0.0000144186,0.000006404345,0.02489724,0.0002738682,0.005937858,0.00004567064,0.00004760478,0.967634],"study_design_scores_gemma":[0.003757593,0.0004744074,0.0003788582,0.002339241,0.0001054261,0.00009685861,0.01951906,0.6920033,0.2749853,0.001107698,0.003944677,0.00128764],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03574217,0.0009718077,0.9598419,0.001440305,0.00003912255,0.0005568746,0.00006431842,0.001107341,0.0002361292],"genre_scores_gemma":[0.8253198,0.00001021451,0.1736526,0.0006917038,0.00003136765,0.00007772346,0.0001172078,0.00002817878,0.00007125124],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9663464,"threshold_uncertainty_score":0.9999791,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02038411021066483,"gpt":0.2964568092918321,"spread":0.2760726990811673,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0003273881,0.00016526,0.0001650364,0.0009434222,0.001321214,0.0003342747,0.0005650726,0.00008179547,0.0000338754],"category_scores_gemma":[0.00001705439,0.0001685903,0.00008992967,0.001192979,0.00004439124,0.001793781,0.00002465481,0.0002590095,0.000001051368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000146167,"about_ca_system_score_gemma":0.0003976624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001208286,"about_ca_topic_score_gemma":0.000004581122,"domain_scores_codex":[0.9988052,0.00004639618,0.0003396234,0.0002817208,0.0003204139,0.0002066864],"domain_scores_gemma":[0.9991162,0.00004752487,0.0002082005,0.0004611881,0.00008234086,0.00008453463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002760592,0.0003246267,0.00002316714,0.00005873828,0.0000351665,2.154469e-7,0.007906365,0.3866699,0.0000640668,0.001792221,0.00001294192,0.6030849],"study_design_scores_gemma":[0.0004383749,0.00004611371,0.0002169789,0.00003304036,0.00009471759,0.000009730888,0.007406992,0.9892413,0.000207778,0.001087381,0.001004789,0.0002128132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0236143,0.00006832236,0.9738256,0.001221032,0.00008966641,0.0002964278,0.00001985406,0.0001813718,0.0006834709],"genre_scores_gemma":[0.7402076,5.105506e-7,0.2584296,0.000984036,0.00001682808,0.0001622893,0.0001061999,0.000007255662,0.00008567684],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7165933,"threshold_uncertainty_score":0.9999789,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01530751449655362,"gpt":0.2482199830368645,"spread":0.2329124685403109,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001561765,0.0001590321,0.0001367931,0.00015351,0.0007031143,0.0004372928,0.0003167149,0.00008519393,0.00006238711],"category_scores_gemma":[0.0000722812,0.0001636325,0.00006580452,0.000266232,0.0000341721,0.002518214,0.00001328844,0.0001884801,0.00001565719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004322093,"about_ca_system_score_gemma":0.0001015819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006928672,"about_ca_topic_score_gemma":0.000004035342,"domain_scores_codex":[0.9988826,0.00002344787,0.0003848633,0.0002295852,0.00026163,0.0002178549],"domain_scores_gemma":[0.9993693,0.00008100276,0.0001012749,0.0002054061,0.0001001686,0.0001428947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001864894,0.00002725042,0.00001856541,0.0002049547,0.00002963881,0.000001717399,0.07419676,0.05406592,0.0004971637,0.001859869,0.00007278075,0.8690068],"study_design_scores_gemma":[0.0005826923,0.00004050602,0.0000448192,0.00005493784,0.00002223374,0.00001233605,0.008427579,0.9872597,0.0009409731,0.0001326846,0.00227234,0.0002091814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003428221,0.00002463883,0.9905109,0.004457956,0.00006385287,0.0003359934,0.00004533732,0.0002555987,0.0008775121],"genre_scores_gemma":[0.7959271,0.000002252465,0.1998628,0.003944876,0.00008433835,0.00005713858,0.00007734136,0.000009789804,0.00003432815],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9331938,"threshold_uncertainty_score":0.6672739,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08572302267729681,"gpt":0.3169815072235871,"spread":0.2312584845462903,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005098042,0.0001367244,0.0001991586,0.0005013007,0.0001247638,0.00003142219,0.0001005827,0.0001119712,0.0003026699],"category_scores_gemma":[0.00001500649,0.0001295608,0.00003043568,0.0004593761,0.00008081883,0.0010402,0.000003841318,0.0001567935,0.000012767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002381633,"about_ca_system_score_gemma":0.00008423572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006835339,"about_ca_topic_score_gemma":0.00004683729,"domain_scores_codex":[0.9986812,0.00008200697,0.0004438194,0.0001785679,0.000471715,0.0001426853],"domain_scores_gemma":[0.9992484,0.00003535765,0.0002408739,0.0002334745,0.0001509368,0.00009099852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000428802,0.0001582071,0.00004272464,0.000465572,0.00005728955,6.725975e-7,0.05985622,0.01578167,0.001122165,0.00002675724,0.00007564573,0.9219843],"study_design_scores_gemma":[0.005672049,0.0008743588,0.01973898,0.0018411,0.0004607912,0.00004883759,0.05609603,0.8976648,0.01635486,0.0006099647,0.0001104088,0.0005277616],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9636543,0.0001246044,0.03324171,0.0001769951,0.00002550502,0.0003651739,0.001018241,0.00005020188,0.00134327],"genre_scores_gemma":[0.9952586,0.00004316028,0.00250773,0.0002097039,0.0000123027,0.00003463115,0.001894413,0.0000128665,0.00002655815],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9214565,"threshold_uncertainty_score":0.5283337,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01635232293385361,"gpt":0.3468787532546184,"spread":0.3305264303207648,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005403512,0.0001702274,0.0001573419,0.0001906153,0.0001564982,0.000234498,0.0001392596,0.0003362557,0.00001001184],"category_scores_gemma":[0.0001826569,0.000142983,0.00005818143,0.0001502733,0.000113758,0.0001751787,0.0000140461,0.000498503,0.000002983338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001901657,"about_ca_system_score_gemma":0.0001028957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005341712,"about_ca_topic_score_gemma":0.00008462949,"domain_scores_codex":[0.9989467,0.00004820233,0.0004344871,0.0001876833,0.000185892,0.0001970055],"domain_scores_gemma":[0.9994522,0.00007724957,0.0001011254,0.000178308,0.00003976833,0.0001513956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001589198,0.00004453659,0.00001740097,0.0003099229,0.00001790196,0.000002196324,0.01022593,0.0003780217,0.0001397152,0.000006714177,0.0006700971,0.9880286],"study_design_scores_gemma":[0.001743311,0.0002395243,0.0004238556,0.0007967082,0.00006593455,0.0002287149,0.04494601,0.8931373,0.002097955,0.00009314089,0.05573428,0.0004932163],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4114948,0.001660387,0.5818186,0.003686492,0.0002443948,0.000381968,0.00005447208,0.0001604693,0.0004984236],"genre_scores_gemma":[0.9866408,0.0003461789,0.0110218,0.001262582,0.0001156616,0.00004402753,0.0002284636,0.00001622988,0.0003243208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9875354,"threshold_uncertainty_score":0.5830677,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01810936799937288,"gpt":0.2498349065838877,"spread":0.2317255385845149,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001961659,0.0001250345,0.0001268139,0.000172418,0.0003781751,0.000453935,0.0002162442,0.00008559749,0.00003519871],"category_scores_gemma":[0.0001623967,0.0001286444,0.00004960792,0.0003933467,0.00001881185,0.001761918,0.00001430018,0.0001665255,0.0000166337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004080317,"about_ca_system_score_gemma":0.00009435091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006834156,"about_ca_topic_score_gemma":0.00001240461,"domain_scores_codex":[0.9990836,0.00003559755,0.0003025291,0.0001970583,0.0001815382,0.0001997266],"domain_scores_gemma":[0.9992535,0.00006248552,0.0001204518,0.0003122326,0.0001714935,0.00007980039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001597155,0.00002724789,0.000005512353,0.000168835,0.000009934038,0.000002507132,0.0119927,0.0003035526,0.0007823846,0.00007902901,0.00001525233,0.9865971],"study_design_scores_gemma":[0.004518568,0.0002425705,0.0004311197,0.001210264,0.0001214,0.0003021982,0.0367815,0.8544968,0.08098397,0.002109878,0.01748868,0.001313085],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04065474,0.00008539183,0.9555414,0.001223147,0.0001367177,0.0001847479,0.000009403246,0.0002248984,0.001939491],"genre_scores_gemma":[0.9260691,0.00001196289,0.07249438,0.001090574,0.00004818619,0.00002640916,0.00006592532,0.000009279493,0.0001842269],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.985284,"threshold_uncertainty_score":0.5245965,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02179014338040878,"gpt":0.2370358633741443,"spread":0.2152457199937355,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001256767,0.0001348288,0.0001888483,0.00006026876,0.0003849574,0.0002231516,0.00008349542,0.00009981461,0.00002632549],"category_scores_gemma":[0.00001838432,0.00006579301,0.0000423731,0.0004248628,0.00003897405,0.0007961764,0.00001061835,0.0002056612,0.000003920398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001142585,"about_ca_system_score_gemma":0.000004576693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007788589,"about_ca_topic_score_gemma":0.00003683103,"domain_scores_codex":[0.9991555,0.00004141417,0.0003225181,0.0001271548,0.000162816,0.0001906301],"domain_scores_gemma":[0.9995893,0.0000697016,0.0001714923,0.00004027197,0.00005066556,0.00007861684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004506738,0.00002908924,0.0004465361,0.0001183182,0.00001399177,0.00000156602,0.006358879,0.03060007,0.00155249,0.000001651809,0.00002553884,0.9608068],"study_design_scores_gemma":[0.0004092653,0.0002179069,0.004006732,0.0002912343,0.00005666452,0.00004408877,0.03826956,0.9546523,0.0008179548,0.00001561464,0.000920119,0.0002985595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9950637,0.0002105277,0.003536651,0.0002852485,0.00004477482,0.000204138,0.00004573253,0.0001721688,0.000437081],"genre_scores_gemma":[0.9993788,0.00001824674,0.00006423787,0.00009636149,0.00006023247,0.000009760852,0.0003180008,0.000001817502,0.0000525291],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9605082,"threshold_uncertainty_score":0.296082,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00789677647571175,"gpt":0.2444467531973456,"spread":0.2365499767216339,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000217465,0.000133811,0.0001076431,0.000249141,0.0009609285,0.0003552848,0.0001958123,0.0000425507,0.00003093103],"category_scores_gemma":[0.00003252141,0.0001310705,0.00002199499,0.0004127218,0.00002783375,0.00122273,0.00001986041,0.0002441929,0.000003285339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006290303,"about_ca_system_score_gemma":0.00007758214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004236029,"about_ca_topic_score_gemma":0.00001381381,"domain_scores_codex":[0.9989455,0.00009137055,0.0002633214,0.0002327244,0.0003062012,0.0001608638],"domain_scores_gemma":[0.9993414,0.00004096441,0.0001662092,0.0003003378,0.00007898035,0.00007212943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005720541,0.00005905351,0.00004114362,0.000115985,0.00001667674,0.000004858016,0.01926615,0.1098467,0.006365239,0.001273156,0.000005831035,0.8629479],"study_design_scores_gemma":[0.001017545,0.0002242368,0.0002250804,0.0001485283,0.00002643873,0.00007499597,0.01107566,0.9772858,0.00900365,0.0003365016,0.0002470396,0.0003344943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1316766,0.00004124084,0.8667538,0.0007889306,0.0000589885,0.0001924171,0.000005952689,0.000202399,0.0002796779],"genre_scores_gemma":[0.9357948,0.000003084158,0.06332884,0.0006700696,0.00001589356,0.00005784655,0.00003949664,0.000008647084,0.00008134134],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8674391,"threshold_uncertainty_score":0.7390782,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00916648332078006,"gpt":0.2578009485067484,"spread":0.2486344651859683,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002648619,0.0002433932,0.0001791731,0.0003721497,0.0008394205,0.0009655566,0.0006416353,0.0001253736,0.00004804618],"category_scores_gemma":[0.0000777981,0.0002240189,0.00005539541,0.0005167248,0.0001629716,0.003594194,0.00003776569,0.000307651,0.00002579341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005352883,"about_ca_system_score_gemma":0.00005080636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002145399,"about_ca_topic_score_gemma":0.000005702892,"domain_scores_codex":[0.998585,0.00005184411,0.0003995179,0.0002728177,0.0003162943,0.0003745],"domain_scores_gemma":[0.9990337,0.0000570157,0.0002101583,0.0004602238,0.0000974963,0.0001413348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001525035,0.00002779811,0.000006781557,0.0001122504,0.00001123451,0.00000390815,0.03143599,0.000007909453,0.003387899,0.000426556,0.0004344261,0.96413],"study_design_scores_gemma":[0.002220419,0.0004815373,0.00003708145,0.001689972,0.00006786072,0.0003986507,0.05933669,0.04364179,0.8642846,0.005670622,0.02002742,0.002143365],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02070392,0.0008830702,0.9735418,0.001359917,0.00006903638,0.0001679711,0.00001817722,0.001052214,0.002203921],"genre_scores_gemma":[0.873732,0.00001120705,0.1232411,0.002652537,0.00007338414,0.00003620804,0.00002219495,0.00001584077,0.0002156057],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9619867,"threshold_uncertainty_score":0.9310884,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Artificial intelligence; Lexicon; Classifier (UML); Natural language processing; Stop words; WordNet; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.008482545231234899,"gpt":0.2775019277698858,"spread":0.2690193825386509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002233551,0.0001662952,0.000165875,0.0004438995,0.0004679468,0.0004649879,0.0003744334,0.00008801717,0.00002515412],"category_scores_gemma":[0.00008453734,0.0001627756,0.00007606127,0.0008793647,0.0000343875,0.003021609,0.00002092716,0.0001462626,0.00009685163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004983311,"about_ca_system_score_gemma":0.00004402112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005135483,"about_ca_topic_score_gemma":0.000003936893,"domain_scores_codex":[0.9988922,0.00002596622,0.0003610696,0.0002145278,0.0002303342,0.0002758257],"domain_scores_gemma":[0.9991809,0.00009581804,0.0001463092,0.0004045386,0.00007682318,0.00009564367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001103207,0.00001661382,0.000003549142,0.00009340399,0.00001050167,0.000001139308,0.01035379,0.01153301,0.0009565408,0.00008067015,0.0001205194,0.9768192],"study_design_scores_gemma":[0.0004053096,0.00004067515,0.00003755261,0.0001147942,0.00001739291,0.000009030949,0.003557588,0.9822392,0.01155669,0.0009964327,0.0008198371,0.0002054666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01237235,0.00001903993,0.9840189,0.001553816,0.00001975694,0.0002945182,0.00001112142,0.001196439,0.0005140427],"genre_scores_gemma":[0.8506705,0.000006215398,0.1478222,0.0009248933,0.0000272145,0.0001137228,0.00008242947,0.00001954812,0.0003333304],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9766138,"threshold_uncertainty_score":0.6637798,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Brandon University","funders":"","keywords":"Indigenous; Citation; Library science; Resource (disambiguation); Computer science; History; Media studies; Linguistics; Sociology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.006931384925798461,"gpt":0.2695800335462915,"spread":0.262648648620493,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006262507,0.0003129691,0.0002492247,0.0006780863,0.0009341878,0.0009674182,0.0009446382,0.0002253282,0.00001490012],"category_scores_gemma":[0.0005736615,0.0002534011,0.00008131701,0.001174846,0.0001072813,0.0007813571,0.00004877465,0.0006274589,0.00003650795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001123845,"about_ca_system_score_gemma":0.000179041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002035397,"about_ca_topic_score_gemma":0.00001952315,"domain_scores_codex":[0.9978934,0.00005929109,0.0005449829,0.0003533094,0.0006544863,0.000494516],"domain_scores_gemma":[0.9986129,0.0003730107,0.0002806495,0.0004196319,0.0002083038,0.0001054613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008889597,0.00006163547,0.000004870178,0.0003377497,0.000009440481,0.000008244889,0.03484808,0.00749348,0.00001683099,0.0001628958,0.004107906,0.95286],"study_design_scores_gemma":[0.005298902,0.000697108,0.0004301008,0.00315907,0.0001087158,0.00008212976,0.04582416,0.4729711,0.005030174,0.005263482,0.4588657,0.002269394],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002699916,0.0009727873,0.9786423,0.004109897,0.00509364,0.002007171,0.0001285914,0.002463699,0.003882017],"genre_scores_gemma":[0.8123484,0.00003944378,0.1221261,0.00591021,0.05766582,0.0005136843,0.0004218952,0.0001409452,0.0008335751],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9505906,"threshold_uncertainty_score":0.9999918,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.02492786121120636,"gpt":0.3015296854222537,"spread":0.2766018242110473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003980144,0.0002846362,0.0002452006,0.0004651659,0.0007436999,0.0001904554,0.0001629797,0.0003125178,0.0002530668],"category_scores_gemma":[0.00006627426,0.0002899216,0.000136153,0.0004845497,0.00009651168,0.0007403725,0.00000872948,0.0003836677,0.0001164485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008188726,"about_ca_system_score_gemma":0.0000484824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003476518,"about_ca_topic_score_gemma":0.00007006337,"domain_scores_codex":[0.9983976,0.0001368593,0.0005693124,0.0003198353,0.0001659424,0.0004104416],"domain_scores_gemma":[0.9990672,0.0001011144,0.0002692718,0.0002784364,0.0001630338,0.0001208946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003857825,0.0002275251,0.00001746695,0.0001784655,0.00007325157,0.000001184923,0.0231492,0.0004330715,0.00007659546,0.00009056804,0.0003885154,0.9749784],"study_design_scores_gemma":[0.0511312,0.001850752,0.01705679,0.006358848,0.001155072,0.0003085972,0.6144007,0.1799063,0.005531927,0.003853118,0.1143945,0.004052117],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02504982,0.0001770031,0.9655694,0.000711745,0.0003759025,0.0009657624,0.0001191711,0.0003389464,0.006692292],"genre_scores_gemma":[0.9027346,0.00001862352,0.0868605,0.004489466,0.0002144863,0.0004529339,0.0008309901,0.00005433942,0.004344037],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9709263,"threshold_uncertainty_score":0.9999553,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.005748411853017093,"gpt":0.2307737058908388,"spread":0.2250252940378217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002472473,0.0002428711,0.0002099243,0.0004652705,0.0005517892,0.0009099712,0.000417811,0.00008085258,0.00001693169],"category_scores_gemma":[0.00004368199,0.0002173727,0.00003932681,0.0004297072,0.00006257922,0.001422773,0.00003151516,0.0002812117,0.000008599008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003864958,"about_ca_system_score_gemma":0.00007625517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001978154,"about_ca_topic_score_gemma":0.000003630306,"domain_scores_codex":[0.9985735,0.00007143783,0.000424,0.0003528463,0.0002995335,0.00027872],"domain_scores_gemma":[0.9991003,0.00008891781,0.00009443161,0.0004677429,0.00005766716,0.0001909157],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007260322,0.0001023241,0.000004399563,0.0002871466,0.00000973949,0.000003146618,0.005830551,0.001899835,0.0001315522,0.000458278,0.0001500535,0.9910504],"study_design_scores_gemma":[0.001732634,0.0001008589,0.0003989243,0.0005243962,0.00003528757,0.00004120888,0.001673437,0.9781325,0.002849063,0.0002993394,0.01376477,0.0004475872],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003924785,0.0001910796,0.9906307,0.001369098,0.00003637658,0.0003349844,0.0001091963,0.000218749,0.003185048],"genre_scores_gemma":[0.841041,0.000004148892,0.1546967,0.003769673,0.00002337933,0.00006011467,0.00024004,0.00001298066,0.0001519452],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9906028,"threshold_uncertainty_score":0.8864201,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008931613069448478,"gpt":0.258806147771992,"spread":0.2498745347025435,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002899342,0.0001198619,0.0001727683,0.0003720685,0.0003023683,0.0001577213,0.0002462437,0.0000819447,0.000009781435],"category_scores_gemma":[0.0001984231,0.0001086896,0.00003136668,0.0004335673,0.00007562357,0.0008408841,0.0000271343,0.0002239095,0.00001014177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001192333,"about_ca_system_score_gemma":0.00003251297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002490387,"about_ca_topic_score_gemma":0.000008165291,"domain_scores_codex":[0.9991325,0.00005135727,0.0003005732,0.0001461714,0.0001634015,0.000205984],"domain_scores_gemma":[0.9993811,0.0001758243,0.0001480578,0.0002008124,0.00003691662,0.00005724264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005842149,0.00001059632,0.00007243292,0.0002376454,0.000009798128,0.000004611893,0.04658587,0.0005958241,0.0004608695,0.00009357107,0.000005217305,0.9519177],"study_design_scores_gemma":[0.001384313,0.0001890073,0.006990924,0.0006249518,0.00003763261,0.0001965358,0.07907327,0.8978823,0.01148994,0.0004229536,0.001269761,0.0004383911],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6099085,0.0001356193,0.3878973,0.0006125123,0.00004153312,0.0001037665,0.000001668943,0.0004461702,0.0008529053],"genre_scores_gemma":[0.9848313,0.00001348944,0.0148589,0.0001951109,0.000008838507,0.000008077011,0.000003669177,0.000005393832,0.00007519734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9514793,"threshold_uncertainty_score":0.4432234,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.006695338832000711,"gpt":0.2708147697501971,"spread":0.2641194309181965,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002463104,0.0001758069,0.0001649278,0.0004629463,0.0005605098,0.0006799541,0.0002569303,0.00010439,0.00000750345],"category_scores_gemma":[0.0001780941,0.000160089,0.00004872849,0.0004966844,0.00003379295,0.001771854,0.00002238303,0.0003044301,0.000001711103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003418254,"about_ca_system_score_gemma":0.00005098546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001519629,"about_ca_topic_score_gemma":0.00001015707,"domain_scores_codex":[0.9989762,0.00004636529,0.0003346815,0.0002548822,0.0001726457,0.0002152076],"domain_scores_gemma":[0.9992488,0.000151813,0.0001534028,0.0003020885,0.00007688363,0.00006701644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003763684,0.0000158348,0.000132239,0.0002294412,0.00001117569,8.451866e-7,0.01269745,0.009403499,0.0002311088,0.0001005295,0.00001802137,0.9771222],"study_design_scores_gemma":[0.001640206,0.00004540207,0.004228877,0.0005468004,0.00003100529,0.00001879864,0.007666362,0.9793787,0.002168478,0.0004871892,0.003422219,0.0003659464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08615807,0.0001158162,0.9098367,0.002483874,0.00007921662,0.0002615328,0.000002935097,0.0002144469,0.0008474075],"genre_scores_gemma":[0.9546114,0.000005558942,0.04340715,0.001473248,0.00003630748,0.00005391401,0.00002814532,0.000008864467,0.0003753612],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9767563,"threshold_uncertainty_score":0.6556813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}