{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002108113,0.001839285,0.001782503,0.004371137,0.001663098,0.001797036,0.001710995,0.001337949,0.001701434],"category_scores_gemma":[0.01252292,0.00147506,0.002271261,0.003018675,0.001098771,0.005472577,0.002680236,0.002521374,0.001029945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009183139,"about_ca_system_score_gemma":0.001767806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00410116,"about_ca_topic_score_gemma":0.008894399,"domain_scores_codex":[0.9977419,0.0008878513,0.000153474,0.0007341198,0.0003645629,0.0001181627],"domain_scores_gemma":[0.9962,0.002347955,0.0002860012,0.0005329805,0.0004714369,0.0001615673],"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":[0.0005295278,0.0002905964,0.006747219,0.0006237096,0.0006614671,0.0006268719,0.001250729,0.319558,0.01300515,0.1150449,0.008062129,0.5335999],"study_design_scores_gemma":[0.00003716352,0.00004951888,0.0006578094,0.00006449044,0.00009412441,0.0001525482,0.0001058237,0.8681103,0.00261681,0.1225593,0.005503129,0.0000490814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0101184,0.0008271072,0.9868897,0.0001515071,0.0000782435,0.00007927974,0.0002004969,0.0009084117,0.0007468697],"genre_scores_gemma":[0.2768868,0.001269284,0.717652,0.0002865409,0.0002184887,0.0005450605,0.00136901,0.0005145698,0.001258269],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004371137,"threshold_uncertainty_score":0.01114887,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008368365,0.0006309839,0.0009147078,0.006565724,0.000932851,0.001949714,0.001351113,0.0008385753,0.001476574],"category_scores_gemma":[0.02976194,0.0006723528,0.001287069,0.004403377,0.0009591386,0.00648105,0.001508527,0.0007212284,0.000678918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008263371,"about_ca_system_score_gemma":0.001496693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002323196,"about_ca_topic_score_gemma":0.00264214,"domain_scores_codex":[0.9921754,0.004461875,0.000783129,0.0005837692,0.001857261,0.0001385059],"domain_scores_gemma":[0.9799457,0.01427061,0.001161651,0.00189064,0.00244263,0.0002887046],"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":[0.0009170882,0.0005097411,0.01013933,0.002651305,0.0005293553,0.0006782254,0.003083069,0.01099293,0.0512015,0.02337325,0.005774187,0.8901501],"study_design_scores_gemma":[0.0004418173,0.002408353,0.04311363,0.00191565,0.002418895,0.01278939,0.005792365,0.5754301,0.14883,0.07674491,0.1292079,0.0009069553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.152803,0.01031087,0.8228758,0.001279276,0.0001455209,0.00155311,0.0007847701,0.001782144,0.008465605],"genre_scores_gemma":[0.2624173,0.002003517,0.731969,0.0001951193,0.00007939637,0.0005589662,0.0008779292,0.0001896818,0.001709078],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008368365,"threshold_uncertainty_score":0.04425663,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001222554,0.0009364733,0.0004847356,0.002426934,0.001636161,0.002026111,0.001152454,0.001083195,0.04726275],"category_scores_gemma":[0.008363669,0.0007373323,0.0003800434,0.003407367,0.00138918,0.001850656,0.001506328,0.001841548,0.009919518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001942228,"about_ca_system_score_gemma":0.002612661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02303498,"about_ca_topic_score_gemma":0.04077815,"domain_scores_codex":[0.9983705,0.0007405399,0.0001418207,0.0003857198,0.0002913505,0.0000700693],"domain_scores_gemma":[0.9889326,0.008053843,0.0002918736,0.00120095,0.00125989,0.0002607941],"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":[0.001935134,0.0005431491,0.01495763,0.003889013,0.0001344366,0.01006284,0.0454091,0.00644786,0.03291551,0.06951451,0.3994444,0.4147464],"study_design_scores_gemma":[0.0002841151,0.0001824005,0.02700987,0.0005165873,0.0000959659,0.005261573,0.008233287,0.009245707,0.02840481,0.009970329,0.9106283,0.0001671893],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"dataset","genre_scores_codex":[0.2826531,0.002059133,0.08646283,0.003225854,0.001526486,0.001199481,0.2939183,0.01202278,0.3169321],"genre_scores_gemma":[0.6000476,0.0007476982,0.1192456,0.0004247192,0.0002446477,0.001463887,0.2073526,0.004379741,0.06609343],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.04726275,"threshold_uncertainty_score":0.1581097,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004966058,0.003302474,0.001155328,0.001663545,0.0009108802,0.001803099,0.001718799,0.001722754,0.005175606],"category_scores_gemma":[0.02055384,0.0007330351,0.001589163,0.00125575,0.001243782,0.004438615,0.002108244,0.002938195,0.004023359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010037,"about_ca_system_score_gemma":0.003402674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007422826,"about_ca_topic_score_gemma":0.007638136,"domain_scores_codex":[0.9964521,0.0014896,0.0003367249,0.0009411033,0.0005348835,0.0002455381],"domain_scores_gemma":[0.9840218,0.009916619,0.0005228108,0.003106288,0.001848095,0.0005843085],"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":[0.00455403,0.00197714,0.009931589,0.001345762,0.000426965,0.0004508857,0.0004427402,0.04812123,0.03591022,0.002689919,0.06426332,0.8298863],"study_design_scores_gemma":[0.0008208987,0.002470979,0.01050889,0.0003309722,0.0008337043,0.0007452662,0.0007974905,0.7872038,0.1472121,0.01176678,0.03707308,0.000236039],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6103384,0.01844483,0.2422613,0.007138699,0.007318485,0.001080813,0.02091516,0.06416421,0.02833802],"genre_scores_gemma":[0.7193884,0.002041006,0.234726,0.001739344,0.000733923,0.0007416613,0.0275616,0.001265149,0.01180285],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007422826,"threshold_uncertainty_score":0.02626336,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}