{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021030432,0.007569425,0.8798203,0.0013737079,0.00077509606,0.0022113412,0.024383405,0.05175575,0.0110804355],"genre_scores_gemma":[0.15527076,0.00209731,0.78466713,0.00038402766,0.0007642869,0.0013286092,0.04438111,0.0014956685,0.009611067],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99738353,0.0006217832,0.0002978571,0.0008778066,0.0005085934,0.0003103871],"domain_scores_gemma":[0.9972144,0.0014238191,0.00015838818,0.00039060466,0.0006004698,0.00021245779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030878522,0.0030027367,0.0021051262,0.011139002,0.0020899265,0.0037337097,0.0024986928,0.002670517,0.013715159],"category_scores_gemma":[0.005537625,0.0008360325,0.0027939393,0.005864418,0.00060438615,0.0051759155,0.0030785745,0.0019187187,0.011950588],"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":[0.00080177607,0.00038013514,0.0041049784,0.0018569404,0.00040088058,0.0005268946,0.0012071634,0.0026694257,0.030709624,0.005175165,0.05552555,0.8966414],"study_design_scores_gemma":[0.0002363291,0.0012732985,0.02423609,0.0009298821,0.0013861097,0.0025789372,0.006205135,0.5532376,0.084150806,0.054741707,0.27058527,0.00043875683],"about_ca_topic_score_codex":0.006231713,"about_ca_topic_score_gemma":0.008846205,"teacher_disagreement_score":0.013715159,"about_ca_system_score_codex":0.0011466864,"about_ca_system_score_gemma":0.0026784865,"threshold_uncertainty_score":0.04588175},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03031716,0.0005295404,0.9678984,0.00025935247,0.000023694136,0.000054788987,0.00008249735,0.00022670215,0.00060784817],"genre_scores_gemma":[0.637905,0.0007189353,0.35907754,0.00018616914,0.00023768835,0.0003006872,0.00067508966,0.00011321836,0.00078579],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913756,0.0040722634,0.0006074857,0.0014180166,0.002134448,0.00039216463],"domain_scores_gemma":[0.9458712,0.045376368,0.0028732065,0.002262623,0.0032279724,0.00038869516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014992056,0.0013032877,0.0027194421,0.004526392,0.0011810412,0.0025082915,0.0029791116,0.0028562476,0.0014518076],"category_scores_gemma":[0.0795247,0.0009872816,0.0012931199,0.0030767866,0.0018620746,0.0059778984,0.002354766,0.0023095093,0.0006983232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076204434,0.00019893945,0.0089770695,0.0005850611,0.00035081006,0.00016470041,0.0005253156,0.49032354,0.002304103,0.052191027,0.0025405183,0.44107693],"study_design_scores_gemma":[0.000031402327,0.000044635064,0.0010898325,0.00004067667,0.00005845638,0.000036905793,0.00003773202,0.9639696,0.0012470622,0.033047393,0.00037012415,0.000026174319],"about_ca_topic_score_codex":0.0029967115,"about_ca_topic_score_gemma":0.0038241292,"teacher_disagreement_score":0.014992056,"about_ca_system_score_codex":0.0014641812,"about_ca_system_score_gemma":0.0016319164,"threshold_uncertainty_score":0.079286516},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002825585,0.000111279776,0.98961276,0.00020897298,0.0001587875,0.000223159,0.00075034593,0.0032113453,0.0028978335],"genre_scores_gemma":[0.09122168,0.00017137123,0.8902231,0.0002436185,0.00016107314,0.000666845,0.0044092224,0.0010647792,0.01183824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972988,0.0006348408,0.00024868408,0.00081279775,0.0006991182,0.0003056965],"domain_scores_gemma":[0.9970432,0.0012026898,0.00017196301,0.00060426706,0.00083774875,0.00014017956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029905674,0.0012323809,0.00080995803,0.001532922,0.0014022994,0.002692837,0.0023512165,0.0016744966,0.024992773],"category_scores_gemma":[0.009523786,0.0007657891,0.0031459418,0.0011347304,0.0008467557,0.004625705,0.0024165853,0.002932444,0.01315085],"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":[0.0005385297,0.00044566236,0.0027605689,0.00039317002,0.00013363459,0.00043323304,0.00064574246,0.06156517,0.012632009,0.1175097,0.031315073,0.7716276],"study_design_scores_gemma":[0.000050265906,0.0000917454,0.0005668219,0.00006925564,0.00004352451,0.00026549413,0.00025494923,0.8593537,0.004988818,0.08811453,0.04614744,0.0000534578],"about_ca_topic_score_codex":0.012103994,"about_ca_topic_score_gemma":0.01210599,"teacher_disagreement_score":0.024992773,"about_ca_system_score_codex":0.0010789818,"about_ca_system_score_gemma":0.0031561626,"threshold_uncertainty_score":0.083609104},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012969563,0.00021521124,0.9869398,0.00022360252,0.00006824567,0.00006544595,0.00040192588,0.0058315275,0.0049573276],"genre_scores_gemma":[0.07692629,0.0006057006,0.9069836,0.0003876949,0.0002244446,0.00022263722,0.0028292476,0.0025911867,0.009229143],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99833125,0.00051986566,0.00014424692,0.0003421701,0.0005330369,0.00012941757],"domain_scores_gemma":[0.99781346,0.0010024161,0.000119186974,0.0006322007,0.00039276434,0.000039884162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018987688,0.00092925923,0.0007393193,0.001368467,0.001011155,0.0024645622,0.0016807329,0.0010178316,0.015353212],"category_scores_gemma":[0.004577035,0.0008621961,0.0014059205,0.0011048575,0.0012199269,0.005157597,0.002524561,0.0016911671,0.012300034],"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":[0.000080729806,0.000053130185,0.0006156477,0.00053295086,0.00007145283,0.00033901518,0.0005464825,0.0062380424,0.023223374,0.61960185,0.041885853,0.30681145],"study_design_scores_gemma":[0.000024034503,0.000037587735,0.00054381654,0.000089577065,0.000061542116,0.00051843823,0.00011922584,0.08821229,0.019167643,0.78613055,0.10504054,0.00005472385],"about_ca_topic_score_codex":0.00074907055,"about_ca_topic_score_gemma":0.0013320069,"teacher_disagreement_score":0.015353212,"about_ca_system_score_codex":0.0007516315,"about_ca_system_score_gemma":0.0010648232,"threshold_uncertainty_score":0.05136156},"labels":[],"label_agreement":null}]}