{"meta":{"query_hash":"420a2879abd6","filters":{"venue":"ACM Transactions on Asian Language Information Processing"},"cohort_total":6,"direct_labels_cover":0,"predictions_cover":6,"exported":6,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/420a2879abd6","api":"https://metacan.xera.ac/api/v1/cohort?venue=ACM+Transactions+on+Asian+Language+Information+Processing"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.010749421293758955,"score_gpt":0.24988615467232533,"score_spread":0.2391367333785664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963912989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036291962,0.000033568496,0.98903877,0.00067101914,0.00023423103,0.0003834928,0.00003379357,0.0004863176,0.005489633],"genre_scores_gemma":[0.85195476,0.0000013506258,0.1472263,0.00050274143,0.00006801238,0.000040802635,0.000108519715,0.000008121058,0.000089376765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985428,0.000020696354,0.0005874255,0.00015395452,0.00039175508,0.00030337417],"domain_scores_gemma":[0.9989148,0.00004103365,0.00025012836,0.00053526025,0.0001941861,0.000064594526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024787514,0.00018333906,0.00014903571,0.00044688885,0.00035269096,0.00074326404,0.00062222546,0.00012738437,0.000020295653],"category_scores_gemma":[0.000053235126,0.00018314047,0.00009500488,0.0004534997,0.00002210227,0.012553564,0.000016929094,0.00020109011,0.000054456654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037058016,0.000034260756,0.0000015561487,0.00014073234,0.000008817244,7.252523e-7,0.0166693,0.04016806,0.00014179955,0.0058809514,0.00006011988,0.9368566],"study_design_scores_gemma":[0.0014288486,0.00007171695,0.000054779215,0.00009262866,0.000023099798,0.000025134243,0.004315624,0.9766793,0.009512666,0.0053941887,0.0019821895,0.0004197795],"about_ca_topic_score_codex":0.000062651976,"about_ca_topic_score_gemma":0.000014502903,"teacher_disagreement_score":0.9365113,"about_ca_system_score_codex":0.00010136415,"about_ca_system_score_gemma":0.00013388545,"threshold_uncertainty_score":0.9101031},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.011854377535112912,"score_gpt":0.2911378651152146,"score_spread":0.2792834875801017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001023236","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00082447444,0.00040003133,0.99387974,0.0007069206,0.00017365628,0.000686216,0.00017882146,0.0013469104,0.0018032307],"genre_scores_gemma":[0.52357244,0.0000025923312,0.4754806,0.00046004154,0.0000459971,0.00006370942,0.00031105053,0.000013848071,0.000049690254],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976605,0.00004766566,0.0009193224,0.0002727475,0.0006336929,0.00046603434],"domain_scores_gemma":[0.99833196,0.00015514197,0.00041150567,0.00062202587,0.0003745766,0.00010477144],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0005105416,0.00032171237,0.0002493483,0.00064333994,0.0005811251,0.0015128949,0.0008725502,0.0002604815,0.000031150837],"category_scores_gemma":[0.00014441821,0.00031205433,0.00012174897,0.0007839467,0.000084495725,0.018428659,0.000017556853,0.00039777724,0.0000398557],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012889216,0.000056084828,0.0000028903935,0.00032345546,0.000010753686,0.0000030233798,0.010133035,0.003244778,0.00038276738,0.007259111,0.00011570854,0.9783395],"study_design_scores_gemma":[0.0035466475,0.00036158305,0.00018173453,0.000401652,0.00008405549,0.00014931688,0.0038518189,0.85001683,0.06670504,0.07057296,0.0025603797,0.0015679571],"about_ca_topic_score_codex":0.000078887504,"about_ca_topic_score_gemma":0.000014841495,"teacher_disagreement_score":0.97677153,"about_ca_system_score_codex":0.00019198681,"about_ca_system_score_gemma":0.00020368835,"threshold_uncertainty_score":0.9999332},"labels":[],"label_agreement":null},{"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.0557659944039868,"score_gpt":0.2680346933608375,"score_spread":0.21226869895685072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008624036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19526845,0.00014853131,0.7640629,0.007205166,0.00058429205,0.0012886664,0.00006473,0.000479915,0.030897358],"genre_scores_gemma":[0.9849736,0.0000016878425,0.01233269,0.0022518954,0.0001837482,0.0000067437986,0.00003128585,0.000016123691,0.0002021888],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883425,0.000023184399,0.00046196545,0.0001232554,0.00033531542,0.00022203453],"domain_scores_gemma":[0.99914455,0.00003926715,0.00031991914,0.00027904188,0.00020319902,0.000014005402],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033549557,0.00017529864,0.00015612671,0.0002591698,0.0004511579,0.00032082823,0.00031160025,0.00008019723,0.0009817021],"category_scores_gemma":[0.00012736078,0.00011771838,0.00007788528,0.00049194694,0.00006249766,0.0031513155,0.000017109694,0.00034203305,0.00012430518],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028363743,0.00006352485,0.000032197822,0.0005750537,0.000051736108,0.0000028683555,0.012559318,0.016109034,0.0033938072,0.0008769428,0.00010447839,0.9659474],"study_design_scores_gemma":[0.007584304,0.0002029015,0.0006678219,0.0013269488,0.00060967053,0.00018694566,0.083111465,0.44970798,0.36348587,0.0047074244,0.08616626,0.0022423805],"about_ca_topic_score_codex":0.000103695325,"about_ca_topic_score_gemma":0.00007604838,"teacher_disagreement_score":0.963705,"about_ca_system_score_codex":0.00003964705,"about_ca_system_score_gemma":0.00006170812,"threshold_uncertainty_score":0.9999315},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.015612561096692375,"score_gpt":0.2520033667490014,"score_spread":0.23639080565230905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024218073","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010136163,0.00005112241,0.9830914,0.0029098424,0.000088298715,0.00042527355,0.000012621152,0.00036967374,0.0029156057],"genre_scores_gemma":[0.55332494,0.0000018677658,0.444677,0.0017598956,0.00008511516,0.000054461772,0.0000056400354,0.000015688764,0.00007540989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857026,0.000040055067,0.00038479827,0.00024286866,0.00034176317,0.00042023446],"domain_scores_gemma":[0.99895155,0.00010200816,0.00021258809,0.00045485512,0.00014498318,0.00013399124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025100625,0.00023293258,0.00020209241,0.0003323086,0.00060354493,0.0005964686,0.00053905847,0.00010280376,0.00014064614],"category_scores_gemma":[0.000058322712,0.00020109753,0.00011550345,0.0006760423,0.000049852224,0.0037244526,0.00000919282,0.00020512867,0.00006414239],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051379797,0.000043337517,0.0000026578607,0.00004908973,0.000018371753,0.000003685921,0.004878422,0.0040760487,0.00004718399,0.000060961447,0.000030739884,0.9907381],"study_design_scores_gemma":[0.0016871786,0.0002139163,0.0001941792,0.00046916128,0.000104672734,0.0005417122,0.0078114974,0.97428256,0.005775776,0.0002508177,0.007864279,0.000804249],"about_ca_topic_score_codex":0.000013020274,"about_ca_topic_score_gemma":0.000044451008,"teacher_disagreement_score":0.98993385,"about_ca_system_score_codex":0.00012666718,"about_ca_system_score_gemma":0.00015273593,"threshold_uncertainty_score":0.82005197},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.003288075048748674,"score_gpt":0.24309328166532185,"score_spread":0.23980520661657317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067372181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053513353,0.00037374877,0.9747399,0.008305392,0.0008217883,0.0008372576,0.000017654693,0.0016897697,0.0078631565],"genre_scores_gemma":[0.73239845,0.0000024915141,0.263295,0.001920546,0.0018225337,0.00010120319,0.000119175216,0.000024373543,0.0003161988],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99735993,0.00006902211,0.00087090733,0.00038927223,0.0007553814,0.00055548747],"domain_scores_gemma":[0.998489,0.00003876141,0.0004162924,0.00069819397,0.00024738145,0.00011037677],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005022583,0.00039161136,0.0002913578,0.0016198133,0.00046860415,0.0013549658,0.0010083822,0.00020170122,0.00009113858],"category_scores_gemma":[0.00027778564,0.00037863152,0.00008295239,0.002170739,0.00004543888,0.012337408,0.00004233009,0.0007964059,0.0003064132],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068864385,0.000060195227,0.0000060041702,0.00013643167,0.0000036334734,0.0000087907565,0.019040007,0.0013074786,0.00029968718,0.00046448899,0.0010893221,0.9775151],"study_design_scores_gemma":[0.0104402555,0.0019320037,0.0048672566,0.007487044,0.00017088589,0.00119476,0.07610893,0.30361846,0.37631282,0.007958246,0.2005707,0.009338639],"about_ca_topic_score_codex":0.00014552215,"about_ca_topic_score_gemma":0.00010304004,"teacher_disagreement_score":0.9681765,"about_ca_system_score_codex":0.0004744255,"about_ca_system_score_gemma":0.00016171341,"threshold_uncertainty_score":0.99986655},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.008144383124305822,"score_gpt":0.29416245078207554,"score_spread":0.2860180676577697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088228840","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008709221,0.000107077525,0.63123626,0.012071107,0.110337466,0.0006598141,0.00010113553,0.0013834231,0.23539452],"genre_scores_gemma":[0.97898775,0.0000034061989,0.0015908494,0.005855899,0.012466507,0.00008847483,0.0000844114,0.000026730086,0.00089594536],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866426,0.00011474445,0.0004149275,0.0002258799,0.00029108918,0.00028910127],"domain_scores_gemma":[0.99896777,0.000052169205,0.00019676411,0.000533687,0.00012673445,0.00012288238],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00030925043,0.00019656167,0.00017212972,0.00039050428,0.00035460375,0.00012827721,0.0002745867,0.00021530734,0.0024733383],"category_scores_gemma":[0.0000643409,0.00019613004,0.000097661534,0.00036691845,0.0001274443,0.0009433875,0.000005496179,0.0004568652,0.0016769603],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020950592,0.00020124044,0.000013142158,0.000021458407,0.000049777977,0.000001654462,0.05256954,0.000025119263,0.00005886096,0.0003140917,0.12590551,0.8206301],"study_design_scores_gemma":[0.0030421189,0.00038932735,0.0008470437,0.000050411363,0.000050282775,0.00010103962,0.10628593,0.00014659177,0.00034821738,0.00034451936,0.8879212,0.00047330133],"about_ca_topic_score_codex":0.000051852647,"about_ca_topic_score_gemma":0.00001949192,"teacher_disagreement_score":0.97027856,"about_ca_system_score_codex":0.00009399211,"about_ca_system_score_gemma":0.000019526426,"threshold_uncertainty_score":0.9991003},"labels":[],"label_agreement":null}]}