{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":4,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":4,"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":"7aa4c1c33ff6","filters":{"venue":"Journal of Natural Language Processing"}},"results":[{"id":"W2062246499","doi":"10.5715/jnlp.18.217","title":"Construction of Context Models for Word Sense Disambiguation","year":2011,"lang":"en","type":"article","venue":"Journal of Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"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":"Ministry of Education, Culture, Sports, Science and Technology","keywords":"Word-sense disambiguation; Word (group theory); Context (archaeology); Computer science; SemEval; Natural language processing; Linguistics; Artificial intelligence; History; Philosophy; Engineering","authors":[{"name":"Bernard Brosseau-Villeneuve","is_ca":true},{"name":"Noriko Kando","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02621211769329632,"gpt":0.2813093315516963,"spread":0.2550972138584,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005316641,0.0001570301,0.0003200879,0.0002823622,0.00008839907,0.00008653772,0.0004988497,0.0001001153,0.000003774301],"category_scores_gemma":[0.0002552972,0.0001187841,0.0001490577,0.0003597434,0.00008645147,0.002131446,0.00007288844,0.0003024684,2.869781e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006375062,"about_ca_system_score_gemma":0.0001502797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000170653,"about_ca_topic_score_gemma":0.000003735924,"domain_scores_codex":[0.9986148,0.0000483753,0.0006028604,0.0001827346,0.0003453591,0.0002059086],"domain_scores_gemma":[0.9976553,0.00008036972,0.001143714,0.0001826008,0.0008743394,0.0000637304],"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":[0.0001388565,0.00004730574,0.00002940822,0.0001682275,0.00002385317,0.00003023537,0.007970262,0.000009205583,0.01196671,0.005955367,0.00004736537,0.9736132],"study_design_scores_gemma":[0.002449863,0.0006277328,0.0001717179,0.002045569,0.0001675798,0.002456646,0.004624233,0.3913395,0.4457316,0.1494942,0.00008308125,0.0008082292],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03052673,0.04804249,0.920532,0.000150797,0.0003692677,0.0001635881,0.000002676048,0.00009890672,0.0001135019],"genre_scores_gemma":[0.5448838,0.00001000661,0.4549477,0.00006422441,0.000065623,0.000001717925,8.72706e-7,0.000007824378,0.00001826402],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.972805,"threshold_uncertainty_score":0.4843874,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2073971205","doi":"10.5715/jnlp.7.2_117","title":"The Exploration and Analysis of Using Multiple Thesaurus Types for Query Expansion in Information Retrieval.","year":2000,"lang":"en","type":"article","venue":"Journal of Natural Language Processing","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Japan Society for the Promotion of Science; York University","keywords":"Thesaurus; Information retrieval; Query expansion; Computer science; Natural language processing","authors":[{"name":"Rila Mandala","is_ca":false},{"name":"Takenobu Tokunaga","is_ca":false},{"name":"Hozumi Tanaka","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01703092278076369,"gpt":0.2835799331783141,"spread":0.2665490103975505,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004536537,0.00004690725,0.0001389502,0.0001986447,0.00007938487,0.0001156018,0.0001531947,0.00002987615,6.313993e-7],"category_scores_gemma":[0.0002902063,0.00002724167,0.00004625464,0.0004733515,0.00002048309,0.001746273,0.00001564193,0.00008002204,6.347137e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001998016,"about_ca_system_score_gemma":0.00004321973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001755488,"about_ca_topic_score_gemma":0.00002805796,"domain_scores_codex":[0.9994,0.00002849307,0.0003003112,0.00004556661,0.0001473706,0.00007831249],"domain_scores_gemma":[0.9993079,0.0001845757,0.0002871261,0.00006493103,0.0001428714,0.00001259914],"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":[0.0001410084,0.000009395417,0.001023126,0.00003292625,0.00003500334,0.000002481503,0.008465014,0.002128173,0.003348301,0.00004506623,0.000003232796,0.9847662],"study_design_scores_gemma":[0.0003244581,0.00003523249,0.008118277,0.00008900955,0.00006440552,0.00001462586,0.002093854,0.9853246,0.003574008,0.0002603047,0.00004608859,0.00005510151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9353224,0.009309198,0.05494,0.0002867505,0.00006551068,0.00005716801,5.337313e-7,0.000006497432,0.0000119439],"genre_scores_gemma":[0.980897,0.0001072173,0.01893175,0.00003585362,0.00001983928,3.015379e-7,9.094335e-7,0.000001296603,0.000005848379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9847112,"threshold_uncertainty_score":0.1266006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2316254469","doi":"10.5715/jnlp.17.2_51","title":"A Written Child Corpus with Editing History Tags","year":2010,"lang":"en","type":"article","venue":"Journal of Natural Language 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":false},"ca_institutions":"Intecsea (Canada)","funders":"","keywords":"Computer science; Natural language processing; Linguistics; World Wide Web; Information retrieval; History; Philosophy","authors":[{"name":"Ryo Nagata","is_ca":true},{"name":"Ayako Kawai","is_ca":true},{"name":"Koji Suda","is_ca":true},{"name":"Junichi Kakegawa","is_ca":true},{"name":"Koichiro Morihiro","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004839098735990272,"gpt":0.2313415337313832,"spread":0.2265024349953929,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006635141,0.0002726386,0.000371312,0.0003844858,0.0001898049,0.0003040561,0.001524964,0.0001472595,0.00001976055],"category_scores_gemma":[0.0003650337,0.000182855,0.0001182855,0.0004497603,0.0001277564,0.002364086,0.0001801602,0.002195275,0.000002686671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001715174,"about_ca_system_score_gemma":0.0003330278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001779208,"about_ca_topic_score_gemma":0.00002581058,"domain_scores_codex":[0.9979836,0.00004578967,0.0005056824,0.0003076037,0.0007487096,0.0004085575],"domain_scores_gemma":[0.9977173,0.00007003354,0.001072267,0.0003404196,0.0006321551,0.0001677769],"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":[0.00008025634,0.0001032352,0.0003545549,0.0002025116,0.00004386772,0.001629265,0.005829729,0.000002600742,0.1287799,0.00158527,0.001525313,0.8598635],"study_design_scores_gemma":[0.012862,0.003445345,0.003199936,0.01294799,0.0007277786,0.155046,0.004870796,0.09261376,0.5845659,0.01121703,0.1104291,0.008074293],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1962743,0.4994326,0.2824314,0.00798324,0.006666013,0.0005510348,0.000003971514,0.001847621,0.0048098],"genre_scores_gemma":[0.631804,0.000006393414,0.366722,0.0005383111,0.0007648815,0.000001674834,9.269324e-7,0.00002095888,0.0001408414],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8517892,"threshold_uncertainty_score":0.9537499,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3166208174","doi":"10.5715/jnlp.28.350","title":"The Effectiveness of Data Augmentation by Removing Unimportant sentence","year":2021,"lang":"en","type":"article","venue":"Journal of Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Tokyo Metropolitan University; Institute for Catastrophic Loss Reduction","keywords":"Pointer (user interface); Computer science; Generator (circuit theory); Sentence; Natural language processing; Programming language; Artificial intelligence; Physics","authors":[{"name":"Tomohito Ouchi","is_ca":false},{"name":"Masayoshi Tabuse","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01711823828179371,"gpt":0.3082740527003838,"spread":0.2911558144185901,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001557391,0.00006730867,0.0001376373,0.00003351466,0.0001121365,0.0001625354,0.0008955447,0.00002416335,8.082385e-7],"category_scores_gemma":[0.0003183104,0.00004312297,0.00003466017,0.0002595547,0.00002407271,0.001222563,0.000259256,0.000228646,1.534254e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005318563,"about_ca_system_score_gemma":0.0002969134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001138826,"about_ca_topic_score_gemma":0.000004924314,"domain_scores_codex":[0.9988203,0.0001859004,0.0003466935,0.0001538,0.0003706686,0.000122662],"domain_scores_gemma":[0.9985362,0.0003268273,0.0004617805,0.0003318399,0.0003108521,0.00003245011],"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":[0.00004810722,0.00003293247,0.0004974919,0.0002166573,0.00003548094,0.0002380857,0.001162541,0.0001064442,0.406725,0.000366596,0.00005360396,0.5905171],"study_design_scores_gemma":[0.001539769,0.00008929973,0.003729446,0.002576143,0.00007747539,0.002038607,0.006483342,0.6586515,0.3227194,0.001267633,0.0004554942,0.0003719504],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4151407,0.06788053,0.5158572,0.0004976267,0.0004770703,0.00005338022,0.000002436814,0.00001567386,0.00007539454],"genre_scores_gemma":[0.9532664,0.00004738568,0.04653893,0.00004817953,0.00005703338,1.98525e-7,0.000003326014,0.000003963195,0.00003456314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.658545,"threshold_uncertainty_score":0.1758504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}