{"meta":{"query_hash":"a68eee857730","filters":{"venue":"NLPRS"},"cohort_total":4,"direct_labels_cover":0,"predictions_cover":4,"exported":4,"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/a68eee857730","api":"https://metacan.xera.ac/api/v1/cohort?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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.015602393950015721,"score_gpt":0.25592303165491265,"score_spread":0.24032063770489692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W21176108","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06396384,0.000011876536,0.9249165,0.0017307709,0.0009396325,0.00029652656,0.000003849647,0.00017598367,0.007961003],"genre_scores_gemma":[0.9838353,0.0000027717906,0.013780016,0.0016340702,0.0001108571,0.000058093337,0.000021819127,0.0000032374783,0.00055383187],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999366,0.00002168935,0.00016867279,0.00011605636,0.00017303605,0.0001545383],"domain_scores_gemma":[0.99951315,0.00004132325,0.000060358947,0.0002451214,0.000051577153,0.000088485736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013426389,0.00006818425,0.00006517817,0.00012521357,0.000095036085,0.00015920428,0.00020817979,0.00003764338,0.000047491932],"category_scores_gemma":[0.000047807345,0.00006594975,0.000029202369,0.00031004482,0.0000056639124,0.0009579367,0.00002525087,0.0000421647,0.0006059164],"study_design_candidate":"not_applicable","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":[0.00017807768,0.00030893105,0.058553923,0.00018071235,0.000041670744,0.0000834123,0.009978795,0.024949327,0.004743864,0.033270102,0.045047984,0.8226632],"study_design_scores_gemma":[0.0024977792,0.0004934343,0.094737425,0.000055112985,0.000009473125,0.00003068786,0.00034471523,0.06232436,0.01296625,0.0011362097,0.82470816,0.0006963631],"about_ca_topic_score_codex":0.00027867226,"about_ca_topic_score_gemma":0.00020288928,"teacher_disagreement_score":0.91987145,"about_ca_system_score_codex":0.00007993913,"about_ca_system_score_gemma":0.00005119465,"threshold_uncertainty_score":0.7788031},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.040011772658586506,"score_gpt":0.3101971451735926,"score_spread":0.2701853725150061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W25291738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29417944,0.00007751815,0.7039754,0.00048276474,0.00017629543,0.000053891614,2.2415549e-7,0.00006097924,0.0009934787],"genre_scores_gemma":[0.87879777,0.0000142198405,0.12096159,0.000121318946,0.000023273014,0.000005070834,4.9266947e-7,0.0000055101586,0.00007078323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998426,0.00014086644,0.00044710084,0.00041140846,0.0002917435,0.00028284048],"domain_scores_gemma":[0.99862623,0.0006455684,0.00013855555,0.00038347315,0.00011245514,0.000093744384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095295446,0.00013362191,0.00023725902,0.00011471026,0.000100721845,0.00009101241,0.00063645793,0.00009456832,0.00003034975],"category_scores_gemma":[0.000823111,0.00011710608,0.00006284597,0.0005232526,0.0001207359,0.0004669712,0.00013275156,0.00032038207,0.000012521979],"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":[0.000064254746,0.0001933269,0.23251776,0.000052222058,0.000014135191,0.0000484948,0.0028553668,0.32376567,0.0007324523,0.058500927,0.00027202623,0.38098338],"study_design_scores_gemma":[0.0002090884,0.000081755396,0.008529407,0.00019562416,0.0000026858675,0.000010417462,0.00024852122,0.9503334,0.0001065596,0.04005671,0.00007355711,0.0001522359],"about_ca_topic_score_codex":0.0003309966,"about_ca_topic_score_gemma":0.00013733207,"teacher_disagreement_score":0.6265678,"about_ca_system_score_codex":0.00006420294,"about_ca_system_score_gemma":0.00013809546,"threshold_uncertainty_score":0.47754472},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.036167706508397304,"score_gpt":0.29543466461596823,"score_spread":0.25926695810757094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37346518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04862573,0.000057075384,0.9475864,0.00091833324,0.00034376237,0.00048118996,0.000008453005,0.00019752009,0.0017815118],"genre_scores_gemma":[0.95489126,0.00000844799,0.04311212,0.0008066258,0.00018535893,0.000057286758,0.000024797362,0.000019538935,0.00089454383],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881274,0.000027082691,0.00024601474,0.00044925362,0.00012619873,0.00033870013],"domain_scores_gemma":[0.99904186,0.000058017675,0.0000793618,0.0006282974,0.000101831574,0.000090654066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002214629,0.00013926205,0.0001664638,0.00006758183,0.0001327033,0.0002784618,0.0010459586,0.00009072214,0.00001841077],"category_scores_gemma":[0.00009030217,0.00013455785,0.00006203548,0.00021006662,0.000008734827,0.00062232336,0.00028177057,0.000099155615,0.000019499836],"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":[0.000120668876,0.00036073243,0.0009454219,0.00009064093,0.000093029,0.00002911641,0.0070116376,0.06533454,0.059618473,0.17047004,0.004686174,0.69123954],"study_design_scores_gemma":[0.0005858401,0.00004780188,0.000023347346,0.000005503738,0.000004889327,0.0000033122856,0.000060479706,0.9773334,0.0006889978,0.008114464,0.012961186,0.00017072435],"about_ca_topic_score_codex":0.00026228002,"about_ca_topic_score_gemma":0.00011547983,"teacher_disagreement_score":0.9119989,"about_ca_system_score_codex":0.00007450448,"about_ca_system_score_gemma":0.00008926582,"threshold_uncertainty_score":0.548711},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.013491939885216,"score_gpt":0.27993489328081017,"score_spread":0.26644295339559415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W74649020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054929346,0.0009834467,0.94183517,0.0010902479,0.00026364558,0.0001611061,0.0000017000697,0.0005478534,0.0001875055],"genre_scores_gemma":[0.56190014,0.0000010772923,0.43767467,0.00028651766,0.000045904486,0.0000053771314,9.662742e-7,0.0000049254504,0.00008040284],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99931747,0.000011739902,0.00010019688,0.00023225555,0.000115181734,0.0002231542],"domain_scores_gemma":[0.99952585,0.00004656725,0.000045391273,0.0002823633,0.000056237106,0.000043617176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001049661,0.00008333715,0.000082804945,0.00006546466,0.00010161922,0.000112334536,0.000522992,0.00005050248,0.000007603014],"category_scores_gemma":[0.000054030133,0.00006917543,0.000036789424,0.00025071306,0.00002009407,0.000081450635,0.00008817204,0.00008352316,0.0000035997077],"study_design_candidate":"design_other","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":[0.000021582746,0.0000464639,0.0002764352,0.000035911307,0.000010584823,0.000030470133,0.000866696,0.00047169687,0.017290201,0.12493387,0.0028101911,0.8532059],"study_design_scores_gemma":[0.00080332055,0.00016067462,0.0005124542,0.00013318752,0.00001681534,0.0001841805,0.000041050593,0.3681211,0.112581864,0.48565072,0.030977465,0.0008171972],"about_ca_topic_score_codex":0.0000065346057,"about_ca_topic_score_gemma":0.0000044761928,"teacher_disagreement_score":0.8523887,"about_ca_system_score_codex":0.0000389556,"about_ca_system_score_gemma":0.000027140828,"threshold_uncertainty_score":0.28208923},"labels":[],"label_agreement":null}]}