{"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"},"query_hash":"a68eee857730","filters":{"venue":"NLPRS"}},"results":[{"id":"W21176108","doi":"10.1111/j.1742-7843.2010.00655.x","title":"Topic Segmentation : A First Stage to Dialog-Based Information Extraction.","year":2001,"lang":"en","type":"article","venue":"NLPRS","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":14,"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":"Segmentation; Computer science; Dialog box; Information extraction; Artificial intelligence; Natural language processing; Hidden Markov model; Speech recognition; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.01560239395001572,"gpt":0.2559230316549126,"spread":0.2403206377048969,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001342639,0.00006818425,0.00006517817,0.0001252136,0.00009503608,0.0001592043,0.0002081798,0.00003764338,0.00004749193],"category_scores_gemma":[0.00004780735,0.00006594975,0.00002920237,0.0003100448,0.000005663912,0.0009579367,0.00002525087,0.0000421647,0.0006059164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007993913,"about_ca_system_score_gemma":0.00005119465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002786723,"about_ca_topic_score_gemma":0.0002028893,"domain_scores_codex":[0.999366,0.00002168935,0.0001686728,0.0001160564,0.0001730361,0.0001545383],"domain_scores_gemma":[0.9995131,0.00004132325,0.00006035895,0.0002451214,0.00005157715,0.00008848574],"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":[0.0001780777,0.000308931,0.05855392,0.0001807123,0.00004167074,0.0000834123,0.009978795,0.02494933,0.004743864,0.0332701,0.04504798,0.8226632],"study_design_scores_gemma":[0.002497779,0.0004934343,0.09473743,0.00005511299,0.000009473125,0.00003068786,0.0003447152,0.06232436,0.01296625,0.00113621,0.8247082,0.0006963631],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06396384,0.00001187654,0.9249165,0.001730771,0.0009396325,0.0002965266,0.000003849647,0.0001759837,0.007961003],"genre_scores_gemma":[0.9838353,0.000002771791,0.01378002,0.00163407,0.0001108571,0.00005809334,0.00002181913,0.000003237478,0.0005538319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9198714,"threshold_uncertainty_score":0.7788031,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W74649020","doi":"","title":"Efficient Parsing for Word Structure.","year":2001,"lang":"en","type":"article","venue":"NLPRS","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Parsing; Computer science; Natural language processing; Covert; Morpheme; Artificial intelligence; Word (group theory); Selection (genetic algorithm); Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.013491939885216,"gpt":0.2799348932808102,"spread":0.2664429533955942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001049661,0.00008333715,0.00008280495,0.00006546466,0.0001016192,0.0001123345,0.000522992,0.00005050248,0.000007603014],"category_scores_gemma":[0.00005403013,0.00006917543,0.00003678942,0.0002507131,0.00002009407,0.00008145063,0.00008817204,0.00008352316,0.000003599708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000389556,"about_ca_system_score_gemma":0.00002714083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006534606,"about_ca_topic_score_gemma":0.000004476193,"domain_scores_codex":[0.9993175,0.0000117399,0.0001001969,0.0002322556,0.0001151817,0.0002231542],"domain_scores_gemma":[0.9995258,0.00004656725,0.00004539127,0.0002823633,0.00005623711,0.00004361718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002158275,0.0000464639,0.0002764352,0.00003591131,0.00001058482,0.00003047013,0.000866696,0.0004716969,0.0172902,0.1249339,0.002810191,0.8532059],"study_design_scores_gemma":[0.0008033206,0.0001606746,0.0005124542,0.0001331875,0.00001681534,0.0001841805,0.00004105059,0.3681211,0.1125819,0.4856507,0.03097747,0.0008171972],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05492935,0.0009834467,0.9418352,0.001090248,0.0002636456,0.0001611061,0.00000170007,0.0005478534,0.0001875055],"genre_scores_gemma":[0.5619001,0.000001077292,0.4376747,0.0002865177,0.00004590449,0.000005377131,9.662742e-7,0.00000492545,0.00008040284],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8523887,"threshold_uncertainty_score":0.2820892,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W25291738","doi":"10.1109/tnnls.2013.2296627","title":"Estimating Reliability of Contextual Evidences in Decision-List Classifiers under Bayesian Learning","year":2001,"lang":"en","type":"article","venue":"NLPRS","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Machine learning; Classifier (UML); Bayesian probability; Reliability (semiconductor); Naive Bayes classifier; Data mining; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.04001177265858651,"gpt":0.3101971451735926,"spread":0.2701853725150061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009529545,0.0001336219,0.000237259,0.0001147103,0.0001007218,0.00009101241,0.0006364579,0.00009456832,0.00003034975],"category_scores_gemma":[0.000823111,0.0001171061,0.00006284597,0.0005232526,0.0001207359,0.0004669712,0.0001327516,0.0003203821,0.00001252198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006420294,"about_ca_system_score_gemma":0.0001380955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003309966,"about_ca_topic_score_gemma":0.0001373321,"domain_scores_codex":[0.998426,0.0001408664,0.0004471008,0.0004114085,0.0002917435,0.0002828405],"domain_scores_gemma":[0.9986262,0.0006455684,0.0001385556,0.0003834731,0.0001124551,0.00009374438],"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":[0.00006425475,0.0001933269,0.2325178,0.00005222206,0.00001413519,0.0000484948,0.002855367,0.3237657,0.0007324523,0.05850093,0.0002720262,0.3809834],"study_design_scores_gemma":[0.0002090884,0.0000817554,0.008529407,0.0001956242,0.000002685867,0.00001041746,0.0002485212,0.9503334,0.0001065596,0.04005671,0.00007355711,0.0001522359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2941794,0.00007751815,0.7039754,0.0004827647,0.0001762954,0.00005389161,2.241555e-7,0.00006097924,0.0009934787],"genre_scores_gemma":[0.8787978,0.00001421984,0.1209616,0.0001213189,0.00002327301,0.000005070834,4.926695e-7,0.000005510159,0.00007078323],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6265678,"threshold_uncertainty_score":0.4775447,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W37346518","doi":"10.7717/peerj-cs.1363","title":"A Simple Closed-Class/Open-Class Factorization for Improved Language Modeling.","year":2001,"lang":"en","type":"article","venue":"NLPRS","topic":"Topic Modeling","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":"University of Waterloo","funders":"Zemkopības ministrija","keywords":"Perplexity; Language model; Class (philosophy); Computer science; Smoothing; Generalization; Function (biology); Simple (philosophy); Artificial intelligence; Natural language processing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0361677065083973,"gpt":0.2954346646159682,"spread":0.2592669581075709,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002214629,0.000139262,0.0001664638,0.00006758183,0.0001327033,0.0002784618,0.001045959,0.00009072214,0.00001841077],"category_scores_gemma":[0.00009030217,0.0001345578,0.00006203548,0.0002100666,0.000008734827,0.0006223234,0.0002817706,0.00009915562,0.00001949984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007450448,"about_ca_system_score_gemma":0.00008926582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00026228,"about_ca_topic_score_gemma":0.0001154798,"domain_scores_codex":[0.9988127,0.00002708269,0.0002460147,0.0004492536,0.0001261987,0.0003387001],"domain_scores_gemma":[0.9990419,0.00005801767,0.0000793618,0.0006282974,0.0001018316,0.00009065407],"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":[0.0001206689,0.0003607324,0.0009454219,0.00009064093,0.000093029,0.00002911641,0.007011638,0.06533454,0.05961847,0.17047,0.004686174,0.6912395],"study_design_scores_gemma":[0.0005858401,0.00004780188,0.00002334735,0.000005503738,0.000004889327,0.000003312286,0.00006047971,0.9773334,0.0006889978,0.008114464,0.01296119,0.0001707244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04862573,0.00005707538,0.9475864,0.0009183332,0.0003437624,0.00048119,0.000008453005,0.0001975201,0.001781512],"genre_scores_gemma":[0.9548913,0.00000844799,0.04311212,0.0008066258,0.0001853589,0.00005728676,0.00002479736,0.00001953893,0.0008945438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9119989,"threshold_uncertainty_score":0.548711,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}