{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003354956,0.0001752986,0.0001561267,0.0002591698,0.0004511579,0.0003208282,0.0003116002,0.00008019723,0.0009817021],"category_scores_gemma":[0.0001273608,0.0001177184,0.00007788528,0.0004919469,0.00006249766,0.003151315,0.00001710969,0.000342033,0.0001243052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003964705,"about_ca_system_score_gemma":0.00006170812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001036953,"about_ca_topic_score_gemma":0.00007604838,"domain_scores_codex":[0.9988343,0.0000231844,0.0004619655,0.0001232554,0.0003353154,0.0002220345],"domain_scores_gemma":[0.9991446,0.00003926715,0.0003199191,0.0002790419,0.000203199,0.0000140054],"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":[0.0002836374,0.00006352485,0.00003219782,0.0005750537,0.00005173611,0.000002868356,0.01255932,0.01610903,0.003393807,0.0008769428,0.0001044784,0.9659474],"study_design_scores_gemma":[0.007584304,0.0002029015,0.0006678219,0.001326949,0.0006096705,0.0001869457,0.08311146,0.449708,0.3634859,0.004707424,0.08616626,0.002242381],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1952685,0.0001485313,0.7640629,0.007205166,0.0005842921,0.001288666,0.00006473,0.000479915,0.03089736],"genre_scores_gemma":[0.9849736,0.000001687843,0.01233269,0.002251895,0.0001837482,0.000006743799,0.00003128585,0.00001612369,0.0002021888],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.963705,"threshold_uncertainty_score":0.9999315,"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0005105416,0.0003217124,0.0002493483,0.0006433399,0.0005811251,0.001512895,0.0008725502,0.0002604815,0.00003115084],"category_scores_gemma":[0.0001444182,0.0003120543,0.000121749,0.0007839467,0.00008449572,0.01842866,0.00001755685,0.0003977772,0.0000398557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001919868,"about_ca_system_score_gemma":0.0002036884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000788875,"about_ca_topic_score_gemma":0.00001484149,"domain_scores_codex":[0.9976605,0.00004766566,0.0009193224,0.0002727475,0.0006336929,0.0004660343],"domain_scores_gemma":[0.998332,0.000155142,0.0004115057,0.0006220259,0.0003745766,0.0001047714],"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":[0.0001288922,0.00005608483,0.000002890393,0.0003234555,0.00001075369,0.00000302338,0.01013303,0.003244778,0.0003827674,0.007259111,0.0001157085,0.9783395],"study_design_scores_gemma":[0.003546647,0.0003615831,0.0001817345,0.000401652,0.00008405549,0.0001493169,0.003851819,0.8500168,0.06670504,0.07057296,0.00256038,0.001567957],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008244744,0.0004000313,0.9938797,0.0007069206,0.0001736563,0.000686216,0.0001788215,0.00134691,0.001803231],"genre_scores_gemma":[0.5235724,0.000002592331,0.4754806,0.0004600415,0.0000459971,0.00006370942,0.0003110505,0.00001384807,0.00004969025],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9767715,"threshold_uncertainty_score":0.9999332,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002478751,0.0001833391,0.0001490357,0.0004468889,0.000352691,0.000743264,0.0006222255,0.0001273844,0.00002029565],"category_scores_gemma":[0.00005323513,0.0001831405,0.00009500488,0.0004534997,0.00002210227,0.01255356,0.00001692909,0.0002010901,0.00005445665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001013642,"about_ca_system_score_gemma":0.0001338854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006265198,"about_ca_topic_score_gemma":0.0000145029,"domain_scores_codex":[0.9985428,0.00002069635,0.0005874255,0.0001539545,0.0003917551,0.0003033742],"domain_scores_gemma":[0.9989148,0.00004103365,0.0002501284,0.0005352602,0.0001941861,0.00006459453],"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":[0.00003705802,0.00003426076,0.000001556149,0.0001407323,0.000008817244,7.252523e-7,0.0166693,0.04016806,0.0001417996,0.005880951,0.00006011988,0.9368566],"study_design_scores_gemma":[0.001428849,0.00007171695,0.00005477922,0.00009262866,0.0000230998,0.00002513424,0.004315624,0.9766793,0.009512666,0.005394189,0.001982189,0.0004197795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003629196,0.0000335685,0.9890388,0.0006710191,0.000234231,0.0003834928,0.00003379357,0.0004863176,0.005489633],"genre_scores_gemma":[0.8519548,0.000001350626,0.1472263,0.0005027414,0.00006801238,0.00004080264,0.0001085197,0.000008121058,0.00008937676],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9365113,"threshold_uncertainty_score":0.9101031,"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003092504,0.0001965617,0.0001721297,0.0003905043,0.0003546037,0.0001282772,0.0002745867,0.0002153073,0.002473338],"category_scores_gemma":[0.0000643409,0.00019613,0.00009766153,0.0003669185,0.0001274443,0.0009433875,0.000005496179,0.0004568652,0.00167696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009399211,"about_ca_system_score_gemma":0.00001952643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005185265,"about_ca_topic_score_gemma":0.00001949192,"domain_scores_codex":[0.9986643,0.0001147444,0.0004149275,0.0002258799,0.0002910892,0.0002891013],"domain_scores_gemma":[0.9989678,0.00005216921,0.0001967641,0.000533687,0.0001267344,0.0001228824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002095059,0.0002012404,0.00001314216,0.00002145841,0.00004977798,0.000001654462,0.05256954,0.00002511926,0.00005886096,0.0003140917,0.1259055,0.8206301],"study_design_scores_gemma":[0.003042119,0.0003893274,0.0008470437,0.00005041136,0.00005028278,0.0001010396,0.1062859,0.0001465918,0.0003482174,0.0003445194,0.8879212,0.0004733013],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008709221,0.0001070775,0.6312363,0.01207111,0.1103375,0.0006598141,0.0001011355,0.001383423,0.2353945],"genre_scores_gemma":[0.9789878,0.000003406199,0.001590849,0.005855899,0.01246651,0.00008847483,0.0000844114,0.00002673009,0.0008959454],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9702786,"threshold_uncertainty_score":0.9991003,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002510062,0.0002329326,0.0002020924,0.0003323086,0.0006035449,0.0005964686,0.0005390585,0.0001028038,0.0001406461],"category_scores_gemma":[0.00005832271,0.0002010975,0.0001155034,0.0006760423,0.00004985222,0.003724453,0.00000919282,0.0002051287,0.00006414239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001266672,"about_ca_system_score_gemma":0.0001527359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001302027,"about_ca_topic_score_gemma":0.00004445101,"domain_scores_codex":[0.9985703,0.00004005507,0.0003847983,0.0002428687,0.0003417632,0.0004202345],"domain_scores_gemma":[0.9989516,0.0001020082,0.0002125881,0.0004548551,0.0001449832,0.0001339912],"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":[0.0000513798,0.00004333752,0.000002657861,0.00004908973,0.00001837175,0.000003685921,0.004878422,0.004076049,0.00004718399,0.00006096145,0.00003073988,0.9907381],"study_design_scores_gemma":[0.001687179,0.0002139163,0.0001941792,0.0004691613,0.0001046727,0.0005417122,0.007811497,0.9742826,0.005775776,0.0002508177,0.007864279,0.000804249],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01013616,0.00005112241,0.9830914,0.002909842,0.00008829872,0.0004252736,0.00001262115,0.0003696737,0.002915606],"genre_scores_gemma":[0.5533249,0.000001867766,0.444677,0.001759896,0.00008511516,0.00005446177,0.000005640035,0.00001568876,0.00007540989],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9899338,"threshold_uncertainty_score":0.820052,"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005022583,0.0003916114,0.0002913578,0.001619813,0.0004686042,0.001354966,0.001008382,0.0002017012,0.00009113858],"category_scores_gemma":[0.0002777856,0.0003786315,0.00008295239,0.002170739,0.00004543888,0.01233741,0.00004233009,0.0007964059,0.0003064132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004744255,"about_ca_system_score_gemma":0.0001617134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001455221,"about_ca_topic_score_gemma":0.00010304,"domain_scores_codex":[0.9973599,0.00006902211,0.0008709073,0.0003892722,0.0007553814,0.0005554875],"domain_scores_gemma":[0.998489,0.00003876141,0.0004162924,0.000698194,0.0002473815,0.0001103768],"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":[0.00006886438,0.00006019523,0.00000600417,0.0001364317,0.000003633473,0.000008790757,0.01904001,0.001307479,0.0002996872,0.000464489,0.001089322,0.9775151],"study_design_scores_gemma":[0.01044026,0.001932004,0.004867257,0.007487044,0.0001708859,0.00119476,0.07610893,0.3036185,0.3763128,0.007958246,0.2005707,0.009338639],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005351335,0.0003737488,0.9747399,0.008305392,0.0008217883,0.0008372576,0.00001765469,0.00168977,0.007863156],"genre_scores_gemma":[0.7323985,0.000002491514,0.263295,0.001920546,0.001822534,0.0001012032,0.0001191752,0.00002437354,0.0003161988],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9681765,"threshold_uncertainty_score":0.9998665,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}