{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017254103,0.003045057,0.98818713,0.0012676676,0.00010571864,0.0001032351,0.00035642562,0.0005521297,0.0046571707],"genre_scores_gemma":[0.24201608,0.008206056,0.7339955,0.0012844715,0.0012571277,0.0014361087,0.0023095133,0.00033347728,0.009161644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99334806,0.0039762533,0.00040875314,0.00085522863,0.0012252646,0.00018639292],"domain_scores_gemma":[0.9853462,0.012093166,0.0005664745,0.0010956906,0.0007728639,0.00012555478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069538113,0.0017643084,0.001620971,0.003011188,0.0011100797,0.0038692846,0.0029164904,0.002469426,0.00589927],"category_scores_gemma":[0.023158943,0.0008761336,0.0025633983,0.0035118556,0.0026599031,0.008618252,0.0020198452,0.004085399,0.0023749436],"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":[0.000065841676,0.000088461195,0.0004947205,0.00029847742,0.00012761174,0.00021422897,0.00038687835,0.08311794,0.00045560751,0.85053825,0.005026866,0.05918516],"study_design_scores_gemma":[0.000018631838,0.000021411232,0.0000849099,0.00004503776,0.00003228945,0.00006863752,0.000038384656,0.28212473,0.00021429709,0.70905864,0.0082678795,0.000025212505],"about_ca_topic_score_codex":0.0058086836,"about_ca_topic_score_gemma":0.004097866,"teacher_disagreement_score":0.0069538113,"about_ca_system_score_codex":0.0029200937,"about_ca_system_score_gemma":0.0019395652,"threshold_uncertainty_score":0.03677571},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038930932,0.0014682588,0.99129665,0.00044836756,0.00010034733,0.00016307377,0.000256553,0.0013606228,0.0010130305],"genre_scores_gemma":[0.31193283,0.0039788326,0.67111474,0.0009181272,0.0008314403,0.0021889664,0.0030232635,0.0008937448,0.0051180655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9893519,0.006758378,0.0006463814,0.001008171,0.0019691407,0.00026594347],"domain_scores_gemma":[0.9831176,0.011672894,0.0011419146,0.0020508685,0.0018993072,0.00011741098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01093543,0.0019273307,0.0020915251,0.0033353376,0.0010002394,0.0022549091,0.0026221666,0.0019548547,0.0040180315],"category_scores_gemma":[0.02368716,0.0010173658,0.002663944,0.004964612,0.0015108975,0.0057662628,0.0017057176,0.0023086711,0.004110179],"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":[0.00063704577,0.00038823852,0.0026442688,0.0009888009,0.0006410162,0.00035344835,0.0005833211,0.40438482,0.0066293823,0.14353588,0.015639707,0.423574],"study_design_scores_gemma":[0.00004511391,0.0001167858,0.00035402263,0.000021394584,0.000060774597,0.00014545806,0.00004308364,0.936632,0.0012116797,0.056485657,0.004835965,0.000048157886],"about_ca_topic_score_codex":0.0049704784,"about_ca_topic_score_gemma":0.00472648,"teacher_disagreement_score":0.01093543,"about_ca_system_score_codex":0.0021179656,"about_ca_system_score_gemma":0.0019304518,"threshold_uncertainty_score":0.057832778},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02006167,0.00065542135,0.9724515,0.0004839221,0.00013184018,0.00063422736,0.00022500938,0.002897225,0.0024592604],"genre_scores_gemma":[0.14573993,0.00048610815,0.8421952,0.00021913627,0.00027744067,0.0006955568,0.000977222,0.00013950154,0.009269829],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99702376,0.00044990165,0.0003237382,0.00070129137,0.0012931176,0.00020813788],"domain_scores_gemma":[0.99678963,0.0009061506,0.00021993637,0.00041055714,0.0015406866,0.00013297035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030611327,0.0011807301,0.0015917146,0.006864253,0.0013005815,0.0021407756,0.0028028481,0.0022502474,0.0041958555],"category_scores_gemma":[0.006267951,0.00081469025,0.001995893,0.0039739795,0.0007111098,0.004685097,0.0014879693,0.0010256838,0.0024320544],"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":[0.00044792856,0.000579199,0.0031022134,0.00041677858,0.00015323698,0.00028773808,0.00038021474,0.007713335,0.06475657,0.008577355,0.008687339,0.9048981],"study_design_scores_gemma":[0.00077942543,0.0011894207,0.008990231,0.000057805515,0.0005864327,0.002342354,0.00025286246,0.8632965,0.085111514,0.0134231625,0.02360171,0.00036862],"about_ca_topic_score_codex":0.0047750906,"about_ca_topic_score_gemma":0.0043718116,"teacher_disagreement_score":0.006864253,"about_ca_system_score_codex":0.001019684,"about_ca_system_score_gemma":0.0026653633,"threshold_uncertainty_score":0.01618898},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048257492,0.0003738667,0.9390619,0.00011905158,0.00013234346,0.000119829114,0.00022176887,0.0077335034,0.003980236],"genre_scores_gemma":[0.43938503,0.00021270156,0.5507238,0.00007555175,0.000054590455,0.00014995497,0.0004314309,0.00021027004,0.008756616],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99986017,0.000028612665,0.000011180501,0.000054245233,0.00003551401,0.0000102511585],"domain_scores_gemma":[0.9998646,0.000053999785,0.000008399937,0.000021397358,0.000040505573,0.000011173696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034959553,0.00050685863,0.00033428433,0.00023046015,0.00028200852,0.00029790789,0.00037649806,0.00037571267,0.0031995985],"category_scores_gemma":[0.0004937756,0.00017685337,0.00034441374,0.00018208669,0.0001973003,0.00029798175,0.00023236159,0.00049076544,0.0010081673],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006035802,0.00009878544,0.00088262896,0.00029491234,0.00014507188,0.00072116405,0.00024339171,0.096055925,0.38201004,0.0059301797,0.0033247198,0.50968957],"study_design_scores_gemma":[0.00007208055,0.0003220079,0.0012897771,0.000020455433,0.00009903763,0.00046148163,0.000044207965,0.8405184,0.14095454,0.0017575679,0.014418744,0.000041803043],"about_ca_topic_score_codex":0.002199576,"about_ca_topic_score_gemma":0.0039235577,"teacher_disagreement_score":0.0031995985,"about_ca_system_score_codex":0.00025617197,"about_ca_system_score_gemma":0.0003117111,"threshold_uncertainty_score":0.0107037425},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009117304,0.0810715,0.03955011,0.044743717,0.70071304,0.00038138885,0.0012027854,0.001061981,0.13036375],"genre_scores_gemma":[0.0053715967,0.060242906,0.012450931,0.0190413,0.7206356,0.0002912904,0.0021589992,0.0011241486,0.17868324],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99794215,0.00038562785,0.00023507538,0.0004967509,0.0007853514,0.00015497106],"domain_scores_gemma":[0.9925211,0.0033899082,0.00031578427,0.0007336051,0.0021797905,0.0008598457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023724998,0.0017146016,0.0024695024,0.0037841666,0.00196325,0.0064348155,0.001983743,0.003422572,0.09189083],"category_scores_gemma":[0.007285249,0.0008302227,0.0023037207,0.0036356605,0.0016441185,0.008157807,0.002613167,0.0075060646,0.04324466],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026708034,0.000062602994,0.00015510326,0.0004407278,0.00003503314,0.00009898211,0.00006813504,0.00017661227,0.0003563995,0.010173377,0.9300941,0.058312178],"study_design_scores_gemma":[0.000009563313,0.00003391718,0.0003723381,0.0002063692,0.000027135762,0.00028864457,0.00004764814,0.0004398241,0.00013503236,0.011276842,0.9871486,0.000014101052],"about_ca_topic_score_codex":0.0008782181,"about_ca_topic_score_gemma":0.0014402714,"teacher_disagreement_score":0.09189083,"about_ca_system_score_codex":0.0016243398,"about_ca_system_score_gemma":0.0015043812,"threshold_uncertainty_score":0.3074054},"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":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000118501914,0.0040609012,0.00011801594,0.39661464,0.59230715,0.000021669151,0.00010472308,0.00004451669,0.0066098594],"genre_scores_gemma":[0.003080555,0.004176886,0.00014358718,0.36372486,0.5971306,0.00007342855,0.0000653216,0.000117503994,0.03148713],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946312,0.0008925151,0.00046644697,0.0010149681,0.002181841,0.00081307144],"domain_scores_gemma":[0.9805995,0.00824009,0.00093783723,0.00079419266,0.0072094686,0.0022188858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007786576,0.0012795896,0.0011638447,0.0027724272,0.0050039105,0.010666858,0.0029205421,0.022877952,0.023894936],"category_scores_gemma":[0.04176634,0.00070828066,0.0016736592,0.0017170446,0.0037086639,0.005916109,0.0032919184,0.027892148,0.01264724],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009253294,0.0000037415502,0.000020876178,0.000048308862,0.000003374328,0.00009443131,0.00006210694,0.000009853612,0.00002541223,0.0013767186,0.9966272,0.0017187399],"study_design_scores_gemma":[0.000011665734,0.0000064720502,0.00015814601,0.0002598845,0.000010699883,0.00011340742,0.00018916502,0.00004389132,0.00008408897,0.0016184333,0.9974898,0.000014310546],"about_ca_topic_score_codex":0.0038686523,"about_ca_topic_score_gemma":0.005274752,"teacher_disagreement_score":0.023894936,"about_ca_system_score_codex":0.0060335738,"about_ca_system_score_gemma":0.0060084723,"threshold_uncertainty_score":0.079936504},"labels":[],"label_agreement":null}]}