{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":6,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":6,"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","author_layer_release":"2026-06-26"},"query_hash":"420a2879abd6","filters":{"venue":"ACM Transactions on Asian Language Information Processing"}},"results":[{"id":"W2008624036","doi":"10.1145/1105696.1105702","title":"Proposal of two-stage patent retrieval method considering the claim structure","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Intellectual Property and Patents","field":"Business, Management and Accounting","cited_by":58,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"McGill University","keywords":"Computer science; Information retrieval; Weighting; Term (time); Term Discrimination; Task (project management); Document retrieval; Precision and recall; Query expansion; Data mining; Stage (stratigraphy); Search engine; Concept search; Web search query","authors":[{"name":"Hisao Mase","is_ca":false},{"name":"Tadataka Matsubayashi","is_ca":false},{"name":"Yuichi Ogawa","is_ca":false},{"name":"Makoto Iwayama","is_ca":false},{"name":"Tadaaki Oshio","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0557659944039868,"gpt":0.2680346933608375,"spread":0.2122686989568507,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003061133,0.00118073,0.001591715,0.006864253,0.001300581,0.002140776,0.002802848,0.002250247,0.004195855],"category_scores_gemma":[0.006267951,0.0008146903,0.001995893,0.00397398,0.0007111098,0.004685097,0.001487969,0.001025684,0.002432054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001019684,"about_ca_system_score_gemma":0.002665363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004775091,"about_ca_topic_score_gemma":0.004371812,"domain_scores_codex":[0.9970238,0.0004499017,0.0003237382,0.0007012914,0.001293118,0.0002081379],"domain_scores_gemma":[0.9967896,0.0009061506,0.0002199364,0.0004105571,0.001540687,0.0001329704],"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":[0.0004479286,0.000579199,0.003102213,0.0004167786,0.000153237,0.0002877381,0.0003802147,0.007713335,0.06475657,0.008577355,0.008687339,0.9048981],"study_design_scores_gemma":[0.0007794254,0.001189421,0.008990231,0.00005780552,0.0005864327,0.002342354,0.0002528625,0.8632965,0.08511151,0.01342316,0.02360171,0.00036862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02006167,0.0006554213,0.9724515,0.0004839221,0.0001318402,0.0006342274,0.0002250094,0.002897225,0.00245926],"genre_scores_gemma":[0.1457399,0.0004861082,0.8421952,0.0002191363,0.0002774407,0.0006955568,0.000977222,0.0001395015,0.009269829],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006864253,"threshold_uncertainty_score":0.01618898,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2001023236","doi":"10.1145/1236181.1236184","title":"Statistical query translation models for cross-language information retrieval","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":29,"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":"","keywords":"Computer science; Cross-language information retrieval; Natural language processing; Query expansion; Artificial intelligence; Machine translation; Query language; RDF query language; Translation (biology); Dependency (UML); Query optimization; Context (archaeology); Information retrieval; Web query classification; Web search query; Search engine","authors":[{"name":"Jianfeng Gao","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true},{"name":"Ming Zhou","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01185437753511291,"gpt":0.2911378651152146,"spread":0.2792834875801017,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01093543,0.001927331,0.002091525,0.003335338,0.001000239,0.002254909,0.002622167,0.001954855,0.004018032],"category_scores_gemma":[0.02368716,0.001017366,0.002663944,0.004964612,0.001510898,0.005766263,0.001705718,0.002308671,0.004110179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002117966,"about_ca_system_score_gemma":0.001930452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004970478,"about_ca_topic_score_gemma":0.00472648,"domain_scores_codex":[0.9893519,0.006758378,0.0006463814,0.001008171,0.001969141,0.0002659435],"domain_scores_gemma":[0.9831176,0.01167289,0.001141915,0.002050868,0.001899307,0.000117411],"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":[0.0006370458,0.0003882385,0.002644269,0.0009888009,0.0006410162,0.0003534484,0.0005833211,0.4043848,0.006629382,0.1435359,0.01563971,0.423574],"study_design_scores_gemma":[0.00004511391,0.0001167858,0.0003540226,0.00002139458,0.0000607746,0.0001454581,0.00004308364,0.936632,0.00121168,0.05648566,0.004835965,0.00004815789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003893093,0.001468259,0.9912966,0.0004483676,0.0001003473,0.0001630738,0.000256553,0.001360623,0.001013031],"genre_scores_gemma":[0.3119328,0.003978833,0.6711147,0.0009181272,0.0008314403,0.002188966,0.003023264,0.0008937448,0.005118066],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01093543,"threshold_uncertainty_score":0.05783278,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1963912989","doi":"10.1145/1236181.1236183","title":"Inferential language models for information retrieval","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"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":"","keywords":"Computer science; Inference; Language model; Smoothing; Term (time); Natural language processing; Artificial intelligence; Query language; Machine learning; Information retrieval; Data mining","authors":[{"name":"Jian‐Yun Nie","is_ca":true},{"name":"Guihong Cao","is_ca":true},{"name":"Jing Bai","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01074942129375895,"gpt":0.2498861546723253,"spread":0.2391367333785664,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006953811,0.001764308,0.001620971,0.003011188,0.00111008,0.003869285,0.00291649,0.002469426,0.00589927],"category_scores_gemma":[0.02315894,0.0008761336,0.002563398,0.003511856,0.002659903,0.008618252,0.002019845,0.004085399,0.002374944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002920094,"about_ca_system_score_gemma":0.001939565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005808684,"about_ca_topic_score_gemma":0.004097866,"domain_scores_codex":[0.9933481,0.003976253,0.0004087531,0.0008552286,0.001225265,0.0001863929],"domain_scores_gemma":[0.9853462,0.01209317,0.0005664745,0.001095691,0.0007728639,0.0001255548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006584168,0.00008846119,0.0004947205,0.0002984774,0.0001276117,0.000214229,0.0003868784,0.08311794,0.0004556075,0.8505383,0.005026866,0.05918516],"study_design_scores_gemma":[0.00001863184,0.00002141123,0.0000849099,0.00004503776,0.00003228945,0.00006863752,0.00003838466,0.2821247,0.0002142971,0.7090586,0.008267879,0.0000252125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00172541,0.003045057,0.9881871,0.001267668,0.0001057186,0.0001032351,0.0003564256,0.0005521297,0.004657171],"genre_scores_gemma":[0.2420161,0.008206056,0.7339955,0.001284471,0.001257128,0.001436109,0.002309513,0.0003334773,0.009161644],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006953811,"threshold_uncertainty_score":0.03677571,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2088228840","doi":"10.1145/2605292","title":"TALIP Perspectives, Guest Editorial Commentary","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Deception detection and forensic psychology","field":"Psychology","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Deception; Task (project management); Computer science; Epistemology; Cognitive science; Artificial intelligence; Psychology; Linguistics; Data science; Social psychology; Philosophy","authors":[{"name":"Victoria L. Rubin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008144383124305822,"gpt":0.2941624507820755,"spread":0.2860180676577697,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007786576,0.00127959,0.001163845,0.002772427,0.005003911,0.01066686,0.002920542,0.02287795,0.02389494],"category_scores_gemma":[0.04176634,0.0007082807,0.001673659,0.001717045,0.003708664,0.005916109,0.003291918,0.02789215,0.01264724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006033574,"about_ca_system_score_gemma":0.006008472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003868652,"about_ca_topic_score_gemma":0.005274752,"domain_scores_codex":[0.9946312,0.0008925151,0.000466447,0.001014968,0.002181841,0.0008130714],"domain_scores_gemma":[0.9805995,0.00824009,0.0009378372,0.0007941927,0.007209469,0.002218886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009253294,0.00000374155,0.00002087618,0.00004830886,0.000003374328,0.00009443131,0.00006210694,0.000009853612,0.00002541223,0.001376719,0.9966272,0.00171874],"study_design_scores_gemma":[0.00001166573,0.00000647205,0.000158146,0.0002598845,0.00001069988,0.0001134074,0.000189165,0.00004389132,0.00008408897,0.001618433,0.9974898,0.00001431055],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0001185019,0.004060901,0.0001180159,0.3966146,0.5923072,0.00002166915,0.0001047231,0.00004451669,0.006609859],"genre_scores_gemma":[0.003080555,0.004176886,0.0001435872,0.3637249,0.5971306,0.00007342855,0.0000653216,0.000117504,0.03148713],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.02389494,"threshold_uncertainty_score":0.0799365,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2024218073","doi":"10.1145/1066078.1066081","title":"A speech synthesizer for Persian text using a neural network with a smooth ergodic HMM","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Preprocessor; Speech recognition; Speech synthesis; Hidden Markov model; Artificial neural network; Intelligibility (philosophy); Natural language processing; Artificial intelligence; Active listening; Language model; Time delay neural network","authors":[{"name":"Faramarz Hendessi","is_ca":false},{"name":"A. Ghayoori","is_ca":false},{"name":"T. Aaron Gulliver","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01561256109669238,"gpt":0.2520033667490014,"spread":0.236390805652309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003495955,0.0005068586,0.0003342843,0.0002304602,0.0002820085,0.0002979079,0.0003764981,0.0003757127,0.003199599],"category_scores_gemma":[0.0004937756,0.0001768534,0.0003444137,0.0001820867,0.0001973003,0.0002979818,0.0002323616,0.0004907654,0.001008167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000256172,"about_ca_system_score_gemma":0.0003117111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002199576,"about_ca_topic_score_gemma":0.003923558,"domain_scores_codex":[0.9998602,0.00002861267,0.0000111805,0.00005424523,0.00003551401,0.00001025116],"domain_scores_gemma":[0.9998646,0.00005399979,0.000008399937,0.00002139736,0.00004050557,0.0000111737],"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":[0.0006035802,0.00009878544,0.000882629,0.0002949123,0.0001450719,0.000721164,0.0002433917,0.09605592,0.38201,0.00593018,0.00332472,0.5096896],"study_design_scores_gemma":[0.00007208055,0.0003220079,0.001289777,0.00002045543,0.00009903763,0.0004614816,0.00004420797,0.8405184,0.1409545,0.001757568,0.01441874,0.00004180304],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04825749,0.0003738667,0.9390619,0.0001190516,0.0001323435,0.0001198291,0.0002217689,0.007733503,0.003980236],"genre_scores_gemma":[0.439385,0.0002127016,0.5507238,0.00007555175,0.00005459045,0.000149955,0.0004314309,0.00021027,0.008756616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003199599,"threshold_uncertainty_score":0.01070374,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2067372181","doi":"10.1145/1236181.1236182","title":"Introduction to special issue on reasoning in natural language information processing","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Natural Language Processing Techniques","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":"Université de Montréal","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Artificial intelligence; Natural language processing; Question answering; Perspective (graphical); Heuristic; Natural language; Reasoning system; Analytic reasoning; Opportunistic reasoning; Model-based reasoning; Natural language understanding; Natural (archaeology); Knowledge representation and reasoning","authors":[{"name":"Dawei Song","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.003288075048748674,"gpt":0.2430932816653218,"spread":0.2398052066165732,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023725,0.001714602,0.002469502,0.003784167,0.00196325,0.006434815,0.001983743,0.003422572,0.09189083],"category_scores_gemma":[0.007285249,0.0008302227,0.002303721,0.003635661,0.001644118,0.008157807,0.002613167,0.007506065,0.04324466],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00162434,"about_ca_system_score_gemma":0.001504381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008782181,"about_ca_topic_score_gemma":0.001440271,"domain_scores_codex":[0.9979421,0.0003856278,0.0002350754,0.0004967509,0.0007853514,0.0001549711],"domain_scores_gemma":[0.9925211,0.003389908,0.0003157843,0.0007336051,0.002179791,0.0008598457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002670803,0.00006260299,0.0001551033,0.0004407278,0.00003503314,0.00009898211,0.00006813504,0.0001766123,0.0003563995,0.01017338,0.9300941,0.05831218],"study_design_scores_gemma":[0.000009563313,0.00003391718,0.0003723381,0.0002063692,0.00002713576,0.0002886446,0.00004764814,0.0004398241,0.0001350324,0.01127684,0.9871486,0.00001410105],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0009117304,0.0810715,0.03955011,0.04474372,0.700713,0.0003813888,0.001202785,0.001061981,0.1303637],"genre_scores_gemma":[0.005371597,0.06024291,0.01245093,0.0190413,0.7206356,0.0002912904,0.002158999,0.001124149,0.1786832],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.09189083,"threshold_uncertainty_score":0.3074054,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}