{"meta":{"query_hash":"6b3902dad86c","filters":{"venue":"Natural Language Processing Journal"},"cohort_total":14,"direct_labels_cover":0,"predictions_cover":14,"exported":14,"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/6b3902dad86c","api":"https://metacan.xera.ac/api/v1/cohort?venue=Natural+Language+Processing+Journal"},"results":[{"id":"W4389371257","doi":"10.1016/j.nlp.2023.100046","title":"Context is not key: Detecting Alzheimer’s disease with both classical and transformer-based neural language models","year":2023,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Dalhousie University; Toronto Rehabilitation Institute; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Transformer; Language model; Word2vec; Artificial intelligence; Machine learning; Artificial neural network; Natural language processing; Speech recognition","score_opus":0.028935805657169744,"score_gpt":0.2818778643010476,"score_spread":0.25294205864387787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389371257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76654,0.0033690513,0.21918723,0.0012900305,0.00019240729,0.00007726256,0.0012546412,0.0024991315,0.0055902717],"genre_scores_gemma":[0.9799973,0.00031045318,0.017223312,0.0001533515,0.000041821382,0.00002260311,0.0009764045,0.000031234827,0.001243569],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997365,0.000096590156,0.000014914129,0.00007930921,0.00003312235,0.000039594503],"domain_scores_gemma":[0.99954826,0.00026864692,0.000034074266,0.000039664366,0.00007871796,0.00003052202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081963016,0.0006039485,0.00036390912,0.00062839437,0.00016944694,0.00053530757,0.0005197416,0.00038779466,0.00059659546],"category_scores_gemma":[0.0017676583,0.00016875313,0.00050928537,0.00039421747,0.0002601113,0.0009079441,0.0005526888,0.0007531629,0.00040031693],"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":[0.0014567015,0.00044937074,0.040426463,0.00021284746,0.00028748403,0.00057597377,0.00034976308,0.3784644,0.015453738,0.007786413,0.008581165,0.54595566],"study_design_scores_gemma":[0.000016017368,0.00007524425,0.0023075484,0.000013929702,0.000045437737,0.000086992906,0.000038053644,0.99158317,0.0017571384,0.0034516018,0.00061494525,0.000009996856],"about_ca_topic_score_codex":0.008014279,"about_ca_topic_score_gemma":0.01437728,"teacher_disagreement_score":0.008014279,"about_ca_system_score_codex":0.00040150914,"about_ca_system_score_gemma":0.0006030834,"threshold_uncertainty_score":0.015935302},"labels":[],"label_agreement":null},{"id":"W4390686563","doi":"10.1016/j.nlp.2023.100052","title":"Deep temporal modelling of clinical depression through social media text","year":2024,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Mental Health via Writing","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute","keywords":"Computer science; Timeline; Social media; Artificial intelligence; Classifier (UML); Machine learning; Depression (economics); Data mining; Statistics; World Wide Web","score_opus":0.1007322898652962,"score_gpt":0.4643236625793267,"score_spread":0.3635913727140305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390686563","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":[0.42851588,0.0021685977,0.5351319,0.0047033024,0.0004843417,0.00034601236,0.015154102,0.0035582895,0.009937684],"genre_scores_gemma":[0.94668466,0.0004909506,0.041281298,0.00026804913,0.0001505479,0.00019306083,0.0044872253,0.00005574354,0.006388381],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998122,0.00003645841,0.000015377027,0.000069346024,0.00003689341,0.000029672294],"domain_scores_gemma":[0.9993654,0.00037541118,0.00009669492,0.000045771467,0.000082292994,0.00003436101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041424623,0.00074875366,0.00033262043,0.00097093906,0.00020455547,0.00086232874,0.00077396963,0.00067064416,0.0021008123],"category_scores_gemma":[0.0024679173,0.000276618,0.0005661117,0.00062840176,0.00019752694,0.0008908933,0.00041242738,0.0010363202,0.0010692384],"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":[0.001014191,0.0011329137,0.08566034,0.00037487276,0.0003494337,0.0012706025,0.0006031216,0.43442944,0.021650791,0.012381243,0.022026908,0.41910616],"study_design_scores_gemma":[0.000009498899,0.000039438208,0.00361509,0.000012306693,0.00002021394,0.000086349464,0.000022185219,0.99037945,0.0011131825,0.0034157513,0.0012789225,0.000007599344],"about_ca_topic_score_codex":0.009155143,"about_ca_topic_score_gemma":0.013773656,"teacher_disagreement_score":0.009155143,"about_ca_system_score_codex":0.0006215442,"about_ca_system_score_gemma":0.0005955543,"threshold_uncertainty_score":0.018203735},"labels":[],"label_agreement":null},{"id":"W4396853851","doi":"10.1016/j.nlp.2024.100079","title":"Decoding depression: Analyzing social network insights for depression severity assessment with transformers and explainable AI","year":2024,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Mental Health via Writing","field":"Psychology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Depression (economics); Decoding methods; Transformer; Psychology; Computer science; Artificial intelligence; Algorithm; Engineering; Electrical engineering; Economics","score_opus":0.014749563455451602,"score_gpt":0.3798009601573698,"score_spread":0.3650513967019182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396853851","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":[0.4639291,0.0022720837,0.512711,0.0023271095,0.0002584841,0.00026822786,0.0048430543,0.0058638253,0.0075271],"genre_scores_gemma":[0.9561913,0.0003294445,0.03805045,0.00012646591,0.00006397696,0.00006181717,0.0030187378,0.000058658297,0.0020991676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997261,0.000098937904,0.000019617739,0.00008021372,0.00003901513,0.0000360781],"domain_scores_gemma":[0.999087,0.00058582163,0.00007063019,0.00010161895,0.000112220805,0.000042819524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007685723,0.0008913254,0.00033792385,0.0017065462,0.0002760468,0.00081419747,0.0005848458,0.0005140425,0.0016814907],"category_scores_gemma":[0.0038925533,0.00020034137,0.00064438686,0.000843567,0.00026816616,0.0010449139,0.0007477639,0.00096118444,0.0010288194],"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":[0.0008303954,0.00044724796,0.094269656,0.0002773085,0.000407886,0.0005786875,0.0009090169,0.18628132,0.013035261,0.010136451,0.014672782,0.6781541],"study_design_scores_gemma":[0.000011551728,0.0000624231,0.0048582326,0.000014784709,0.000037118138,0.00007731068,0.00009211295,0.9833618,0.0014672845,0.008872549,0.0011331508,0.000011715785],"about_ca_topic_score_codex":0.0061817104,"about_ca_topic_score_gemma":0.010515389,"teacher_disagreement_score":0.0061817104,"about_ca_system_score_codex":0.0005382965,"about_ca_system_score_gemma":0.0004113055,"threshold_uncertainty_score":0.012291491},"labels":[],"label_agreement":null},{"id":"W4401813233","doi":"10.1016/j.nlp.2024.100098","title":"HarmonyNet: Navigating hate speech detection","year":2024,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"Vector Institute; Government of Ontario; Canadian Institute for Advanced Research","keywords":"Voice activity detection; Computer science; Speech recognition; Speech processing","score_opus":0.006087059208944044,"score_gpt":0.26614302229227743,"score_spread":0.2600559630833334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401813233","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":[0.3842869,0.0027573076,0.5529469,0.0015535894,0.0009435217,0.0005376204,0.0039273873,0.030415434,0.022631325],"genre_scores_gemma":[0.8233431,0.00042502416,0.15208387,0.0007284074,0.00021946013,0.00015896116,0.0053090244,0.0005575543,0.017174602],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990701,0.00024134081,0.000038540282,0.00029171424,0.00022864249,0.00012958155],"domain_scores_gemma":[0.9988825,0.00043153137,0.00009738699,0.0001890927,0.00031790975,0.0000815883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013213343,0.0012989091,0.00085459556,0.0016551986,0.00069895736,0.0009904621,0.0012454968,0.0013005312,0.0026504202],"category_scores_gemma":[0.0036391683,0.00035529953,0.00055699784,0.00055059086,0.00045731026,0.001943174,0.0024606988,0.00117066,0.0017585628],"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":[0.00066176837,0.00055999355,0.024045028,0.00029603252,0.0003188949,0.0009068323,0.00073461264,0.04996382,0.029583013,0.002901873,0.05736713,0.83266115],"study_design_scores_gemma":[0.000020384034,0.00018194673,0.0037982878,0.000023758055,0.00005102776,0.0002669933,0.00028375248,0.96891886,0.015061749,0.0035901999,0.0077678817,0.00003509211],"about_ca_topic_score_codex":0.0060741412,"about_ca_topic_score_gemma":0.010315668,"teacher_disagreement_score":0.0060741412,"about_ca_system_score_codex":0.0005599273,"about_ca_system_score_gemma":0.00065906293,"threshold_uncertainty_score":0.01207757},"labels":[],"label_agreement":null},{"id":"W4402206897","doi":"10.1016/j.nlp.2024.100102","title":"Job description parsing with explainable transformer based ensemble models to extract the technical and non-technical skills","year":2024,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Interpretability; Computer science; Margin (machine learning); Artificial intelligence; Machine learning; Transformer; Statistical model; Engineering","score_opus":0.013537905842925406,"score_gpt":0.2620085156993179,"score_spread":0.24847060985639247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402206897","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":[0.17916663,0.001530385,0.78725547,0.0009602274,0.00028174793,0.00022526618,0.0074997237,0.014512393,0.0085681435],"genre_scores_gemma":[0.7903439,0.0007190886,0.17756374,0.000350965,0.00010028137,0.00023278281,0.018682512,0.0003752851,0.011631552],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997956,0.000038692095,0.0000127286585,0.000085825704,0.00003635396,0.00003075667],"domain_scores_gemma":[0.99951994,0.0002477315,0.000035261746,0.000068779176,0.00010248379,0.000025838868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050892675,0.0009084745,0.0003600557,0.0012215595,0.00029785736,0.00055249763,0.0009659869,0.0006872932,0.0023853362],"category_scores_gemma":[0.0015454487,0.0003014377,0.0011640537,0.0010430173,0.00021247266,0.0014602509,0.0008710432,0.0013523522,0.0012571058],"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":[0.00042964742,0.00044437178,0.01988093,0.00034343058,0.0002747146,0.000777702,0.00061517453,0.2733017,0.016682891,0.009728899,0.030535165,0.64698535],"study_design_scores_gemma":[0.000009581355,0.00003874311,0.0020299163,0.000021152355,0.000056601395,0.00007824958,0.00005947211,0.98555076,0.0035052174,0.0047537256,0.003881671,0.000014801224],"about_ca_topic_score_codex":0.012681339,"about_ca_topic_score_gemma":0.02418,"teacher_disagreement_score":0.012681339,"about_ca_system_score_codex":0.00063705037,"about_ca_system_score_gemma":0.0009670905,"threshold_uncertainty_score":0.02521503},"labels":[],"label_agreement":null},{"id":"W4402468717","doi":"10.1016/j.nlp.2024.100105","title":"Personality and emotion—A comprehensive analysis using contextual text embeddings","year":2024,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"New York Institute of Technology","funders":"","keywords":"Personality; Psychology; Natural language processing; Cognitive psychology; Computer science; Social psychology","score_opus":0.021775286337649503,"score_gpt":0.32170208357638164,"score_spread":0.2999267972387321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402468717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91708714,0.0020079527,0.06751524,0.00039950118,0.00029308072,0.00012337093,0.0065495144,0.00069845055,0.005325807],"genre_scores_gemma":[0.9790835,0.00039221862,0.015106227,0.000041776962,0.000121175144,0.000069104644,0.0036660484,0.000040719093,0.0014794188],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943334,0.00016381973,0.00006169572,0.00014791019,0.0001395968,0.0000535894],"domain_scores_gemma":[0.9987457,0.0005116413,0.00022687993,0.00016128123,0.00026361513,0.00009088392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047046776,0.00049288257,0.0002589019,0.001608716,0.00024316399,0.00068484,0.00015185916,0.0002715489,0.0012382034],"category_scores_gemma":[0.002587012,0.000085664826,0.0003864386,0.0012555986,0.00020423625,0.0011276288,0.0005188089,0.0003557176,0.0006475149],"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":[0.0013004529,0.00064733176,0.34571272,0.00082498323,0.0004430349,0.0016742594,0.0023729773,0.011102544,0.056396507,0.0044097635,0.015529345,0.55958605],"study_design_scores_gemma":[0.000020176134,0.00085660256,0.70291275,0.00017142681,0.0002852707,0.0028749115,0.0026225704,0.23968942,0.014192589,0.0059430217,0.03032077,0.00011039274],"about_ca_topic_score_codex":0.0007064696,"about_ca_topic_score_gemma":0.0009708618,"teacher_disagreement_score":0.001608716,"about_ca_system_score_codex":0.00016909752,"about_ca_system_score_gemma":0.00012484488,"threshold_uncertainty_score":0.004142165},"labels":[],"label_agreement":null},{"id":"W4403096752","doi":"10.1016/j.nlp.2024.100110","title":"Recent advancements in automatic disordered speech recognition: A survey paper","year":2024,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":11,"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":"","keywords":"Speech recognition; Computer science","score_opus":0.024658999476806286,"score_gpt":0.301425732541467,"score_spread":0.2767667330646607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403096752","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077905823,0.9386557,0.03591299,0.003732268,0.0016949193,0.00009040841,0.00064515806,0.0006535057,0.010824506],"genre_scores_gemma":[0.031233354,0.9278124,0.02765872,0.001957063,0.0040940666,0.00007614708,0.00242378,0.00018156241,0.004562975],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972996,0.0004466784,0.00046045662,0.00088046206,0.0007784324,0.0001343219],"domain_scores_gemma":[0.9850492,0.009653568,0.0006425501,0.0007679244,0.0035425667,0.0003442483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004810812,0.001306758,0.0014163757,0.0061961925,0.00052893243,0.0030908466,0.0017026422,0.0016703948,0.005452555],"category_scores_gemma":[0.010180478,0.0007780403,0.0012318727,0.007301997,0.0010345451,0.005653986,0.0016346594,0.0018982658,0.004427928],"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":[0.00009645336,0.00008642651,0.0024094605,0.004593588,0.00007939032,0.00011537957,0.00022273786,0.0013536902,0.0018006555,0.004003457,0.015961692,0.96927714],"study_design_scores_gemma":[0.000025812407,0.0005149083,0.010384143,0.004995996,0.00051116396,0.002681973,0.0013218423,0.013187612,0.00722524,0.009717094,0.9492203,0.00021393248],"about_ca_topic_score_codex":0.0025990708,"about_ca_topic_score_gemma":0.0019207625,"teacher_disagreement_score":0.0061961925,"about_ca_system_score_codex":0.00067871646,"about_ca_system_score_gemma":0.0019953002,"threshold_uncertainty_score":0.025442302},"labels":[],"label_agreement":null},{"id":"W4406572044","doi":"10.1016/j.nlp.2025.100126","title":"RESPECT: A framework for promoting inclusive and respectful conversations in online communications","year":2025,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sheridan College; Toronto Metropolitan University; Vector Institute","funders":"","keywords":"Inclusion (mineral); Psychology; Internet privacy; Sociology; Computer science; Social psychology","score_opus":0.010413841497334457,"score_gpt":0.3321838089788432,"score_spread":0.32176996748150877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406572044","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":[0.004790983,0.00015903162,0.98626035,0.0011697634,0.00006006689,0.00033107426,0.0001860435,0.0023296692,0.004713014],"genre_scores_gemma":[0.19287084,0.00036790204,0.79934883,0.00056722434,0.00010986675,0.0007707004,0.0006428999,0.00037438772,0.0049473383],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930668,0.003463389,0.00048423753,0.0013024758,0.0013539512,0.0003292085],"domain_scores_gemma":[0.99218726,0.0037666124,0.0010310527,0.0012729783,0.001151622,0.00059045956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064953337,0.0015557995,0.0006733933,0.0026950878,0.001995587,0.0044611464,0.0022600514,0.002371007,0.0039731455],"category_scores_gemma":[0.017904973,0.00086159207,0.0016338846,0.00092407735,0.004493254,0.007855867,0.0053008716,0.0028995257,0.0018118713],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002559194,0.00039121514,0.0054697893,0.000578821,0.00008041779,0.000651844,0.008939944,0.057048436,0.016448336,0.6466315,0.014318541,0.2491853],"study_design_scores_gemma":[0.000054861808,0.000341953,0.0015874677,0.00031889504,0.00009904685,0.00077147584,0.0024107576,0.437959,0.011701311,0.44412696,0.100440554,0.00018770173],"about_ca_topic_score_codex":0.007448119,"about_ca_topic_score_gemma":0.007915911,"teacher_disagreement_score":0.007448119,"about_ca_system_score_codex":0.0023520286,"about_ca_system_score_gemma":0.005336461,"threshold_uncertainty_score":0.03435099},"labels":[],"label_agreement":null},{"id":"W4409360343","doi":"10.1016/j.nlp.2025.100146","title":"Detecting cognitive engagement in online course forums: A review of frameworks and methodologies","year":2025,"lang":"en","type":"review","venue":"Natural Language Processing Journal","topic":"Online and Blended Learning","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Course (navigation); Massive open online course; Cognition; Computer science; Psychology; Data science; World Wide Web; Engineering; Neuroscience","score_opus":0.06930139704892432,"score_gpt":0.4957217460275704,"score_spread":0.4264203489786461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409360343","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036726808,0.9969317,0.0013049488,0.0003870034,0.00008450622,0.000031767268,0.000036248784,0.000015645832,0.00084092276],"genre_scores_gemma":[0.004073058,0.9928342,0.0024487304,0.00019573426,0.00010647665,0.00009422446,0.000048322214,0.000007945433,0.00019137577],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972108,0.0008760586,0.0004472812,0.00056213216,0.00081980013,0.00008385367],"domain_scores_gemma":[0.97962624,0.016786868,0.0011153255,0.0003160342,0.0019357781,0.00021971994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068295836,0.0014062519,0.0024584362,0.009778777,0.0006002817,0.0024576483,0.0016613575,0.0017312841,0.0019994378],"category_scores_gemma":[0.013909473,0.0007584753,0.0013447335,0.007196029,0.0017884142,0.0039435015,0.0014907243,0.0016794916,0.00083694287],"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":[0.000044829212,0.00007649582,0.0011440987,0.04542019,0.00016333541,0.000048531838,0.0006147424,0.00023140153,0.0004439036,0.0034002117,0.0033263895,0.9450859],"study_design_scores_gemma":[0.000044043423,0.00051202526,0.025504835,0.13450952,0.0019899723,0.0017366266,0.0031485,0.0011225543,0.002414314,0.016865633,0.8118778,0.00027418148],"about_ca_topic_score_codex":0.0046779974,"about_ca_topic_score_gemma":0.0061311843,"teacher_disagreement_score":0.009778777,"about_ca_system_score_codex":0.0018359439,"about_ca_system_score_gemma":0.0045332965,"threshold_uncertainty_score":0.036118746},"labels":[],"label_agreement":null},{"id":"W4410109448","doi":"10.1016/j.nlp.2025.100152","title":"Bayesian Q-learning in multi-objective reward model for homophobic and transphobic text classification in low-resource languages: A hypothesis testing framework in multi-objective setting","year":2025,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"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 Calgary","funders":"Science Foundation Ireland","keywords":"Bayesian probability; Computer science; Resource (disambiguation); Machine learning; Artificial intelligence; Natural language processing; Psychology","score_opus":0.02416340836884429,"score_gpt":0.3046702726710389,"score_spread":0.2805068643021946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410109448","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":[0.11552638,0.0007661704,0.87529844,0.0030339928,0.00014441732,0.000323977,0.00040814865,0.000678337,0.003820028],"genre_scores_gemma":[0.91314876,0.00023197912,0.07909059,0.000638162,0.00010865439,0.0005083506,0.0002751856,0.000074320626,0.005924038],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783736,0.0009593814,0.0000994513,0.00055124913,0.00026236937,0.0002901473],"domain_scores_gemma":[0.9874994,0.00945813,0.0009988266,0.00032125346,0.0012574511,0.00046489594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062335776,0.0012205994,0.0028067478,0.00095865753,0.0007286967,0.0017070328,0.0030578908,0.0028941543,0.0043954235],"category_scores_gemma":[0.015884887,0.00085216225,0.00093659153,0.0007113456,0.0022626938,0.0021659713,0.0016937621,0.0033200774,0.0005948248],"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":[0.000292184,0.0001546586,0.0029955558,0.0001283469,0.00006962757,0.0002114626,0.00018659835,0.9437391,0.00071813026,0.022521071,0.0013792975,0.027603915],"study_design_scores_gemma":[0.000014981001,0.00002425077,0.00019023697,0.0000071200166,0.0000059670883,0.000008057302,0.000006089876,0.99533385,0.00010447284,0.0042018867,0.00009636604,0.0000066854104],"about_ca_topic_score_codex":0.014031808,"about_ca_topic_score_gemma":0.008577307,"teacher_disagreement_score":0.014031808,"about_ca_system_score_codex":0.0025358796,"about_ca_system_score_gemma":0.0026192202,"threshold_uncertainty_score":0.032966673},"labels":[],"label_agreement":null},{"id":"W4411176006","doi":"10.1016/j.nlp.2025.100159","title":"Next-generation image captioning: A survey of methodologies and emerging challenges from transformers to Multimodal Large Language Models","year":2025,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":13,"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":"","keywords":"Closed captioning; Computer science; Transformer; Natural language processing; Artificial intelligence; Image (mathematics); Engineering; Electrical engineering","score_opus":0.0630583087593844,"score_gpt":0.36922933374050865,"score_spread":0.30617102498112425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411176006","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054418324,0.04114411,0.92937875,0.0030813825,0.0005160657,0.00022774238,0.0008695492,0.007503779,0.0118367635],"genre_scores_gemma":[0.17809375,0.07177547,0.7191174,0.0028580022,0.001546573,0.0005961126,0.006533983,0.0029917294,0.016486965],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99880683,0.00043488792,0.00009053437,0.00026640636,0.00032858195,0.00007271207],"domain_scores_gemma":[0.99718815,0.0016159638,0.00012202989,0.00044566795,0.00053720764,0.000090991765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002763933,0.0018039485,0.0012502279,0.002030037,0.0005468454,0.0033187398,0.0029198118,0.0015798174,0.008154644],"category_scores_gemma":[0.007123054,0.0006499955,0.0012108439,0.002133507,0.0011728476,0.006005218,0.002399155,0.0029337157,0.0044379705],"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":[0.00014466593,0.00013461502,0.00044277948,0.0014904654,0.00009842421,0.00019335213,0.00035178658,0.059276856,0.0062452373,0.052819874,0.03720463,0.8415973],"study_design_scores_gemma":[0.000028081775,0.00017491406,0.00034671853,0.00046832874,0.00007368151,0.00062535336,0.00027562745,0.795644,0.014261075,0.08294562,0.105060406,0.00009622068],"about_ca_topic_score_codex":0.004702269,"about_ca_topic_score_gemma":0.004344603,"teacher_disagreement_score":0.008154644,"about_ca_system_score_codex":0.0018008668,"about_ca_system_score_gemma":0.0012289897,"threshold_uncertainty_score":0.027279973},"labels":[],"label_agreement":null},{"id":"W4411442784","doi":"10.1016/j.nlp.2025.100163","title":"Can “consciousness” be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis","year":2025,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Language and cultural evolution","field":"Social Sciences","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":"World Anti-Doping Agency","funders":"","keywords":"Representation (politics); Consciousness; Test (biology); Span (engineering); Cognitive science; Psychology; Integrated information theory; Cognitive psychology; Computer science; Engineering; Structural engineering; Political science; Geology","score_opus":0.010703627425701757,"score_gpt":0.30592501771710584,"score_spread":0.2952213902914041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411442784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9412333,0.000065991,0.05486851,0.00014828461,0.0000119810975,0.000025661842,0.00017259271,0.00014343375,0.0033301925],"genre_scores_gemma":[0.99238855,0.000018562148,0.00727704,0.000020566538,0.000003294948,0.000024295505,0.0001359703,0.000026010694,0.00010562126],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989912,0.00036892042,0.000082566985,0.00024299767,0.00022669841,0.00008766732],"domain_scores_gemma":[0.98814815,0.007115724,0.0017577371,0.0019443533,0.0006597149,0.00037439627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020155206,0.0002648101,0.00028625524,0.0014619617,0.0002868921,0.001952612,0.00040870495,0.0004094086,0.0021881005],"category_scores_gemma":[0.033074234,0.00023450826,0.0004174799,0.0008660471,0.0015378227,0.0031664276,0.0018055729,0.00087880035,0.00019713126],"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":[0.001335716,0.0003177797,0.36352497,0.0005829902,0.0005993435,0.00046211676,0.017017597,0.017945644,0.17940989,0.0934617,0.0011203551,0.3242219],"study_design_scores_gemma":[0.00004118028,0.0008617002,0.6067768,0.00010148803,0.00024730305,0.0007791055,0.0048205755,0.13602765,0.038131963,0.20969197,0.0022928412,0.00022742507],"about_ca_topic_score_codex":0.0007450769,"about_ca_topic_score_gemma":0.0006332902,"teacher_disagreement_score":0.0021881005,"about_ca_system_score_codex":0.0004814854,"about_ca_system_score_gemma":0.0004540947,"threshold_uncertainty_score":0.010659218},"labels":[],"label_agreement":null},{"id":"W4413333183","doi":"10.1016/j.nlp.2025.100176","title":"Analyzing social media discourse of avian influenza outbreaks","year":2025,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Ontario Ministry of Agriculture, Food and Rural Affairs; University of Guelph","keywords":"Outbreak; Influenza A virus subtype H5N1; Social media; Virology; Sociology; Geography; Biology; Computer science; Virus; World Wide Web","score_opus":0.021597179736304994,"score_gpt":0.4121351556805344,"score_spread":0.3905379759442294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413333183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960188,0.0001603228,0.0005681107,0.00026952993,0.000026262862,0.000027531121,0.0007362933,0.000024212164,0.0021689283],"genre_scores_gemma":[0.9965295,0.00021084036,0.0012130988,0.00007467347,0.00008062371,0.000046658308,0.0009183151,0.0000135987,0.0009125344],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992142,0.00040603045,0.000059324673,0.00009584635,0.0001635929,0.00006106483],"domain_scores_gemma":[0.99314606,0.0049647707,0.001002467,0.00018232461,0.0005592376,0.00014509926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014766537,0.00030345793,0.00016578757,0.0017640936,0.00053592614,0.0012098829,0.00019375776,0.000449673,0.0010786195],"category_scores_gemma":[0.0067747612,0.000112074005,0.00020147426,0.0011322465,0.00038387283,0.0013735258,0.0010192522,0.00043479752,0.00033272922],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016980518,0.0005017766,0.54786617,0.0016454315,0.00020148764,0.0020183316,0.1836533,0.0027275854,0.061034158,0.0031252182,0.009176907,0.1863516],"study_design_scores_gemma":[0.000029506911,0.0004638095,0.7813728,0.0004955926,0.0001550518,0.00060736795,0.12387629,0.037765045,0.014802378,0.0015448165,0.03877194,0.0001153627],"about_ca_topic_score_codex":0.00448674,"about_ca_topic_score_gemma":0.005743947,"teacher_disagreement_score":0.00448674,"about_ca_system_score_codex":0.0005556446,"about_ca_system_score_gemma":0.0002898708,"threshold_uncertainty_score":0.008921266},"labels":[],"label_agreement":null},{"id":"W4415305391","doi":"10.1016/j.nlp.2025.100185","title":"OPT2CODE: A retrieval-augmented framework for solving linear programming problems","year":2025,"lang":"en","type":"article","venue":"Natural Language Processing Journal","topic":"Optimization and Mathematical Programming","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Executable; Solver; Code generation; Domain (mathematical analysis); Benchmark (surveying); Code (set theory); Linear programming; Integer programming","score_opus":0.00951167119287442,"score_gpt":0.2937268453066785,"score_spread":0.28421517411380404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415305391","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":[0.0036419027,0.0008542587,0.8427414,0.0009306631,0.00020339187,0.00035681034,0.004854557,0.13802145,0.008395522],"genre_scores_gemma":[0.037548613,0.00049248105,0.9209999,0.000721056,0.00006467966,0.0008170121,0.017892739,0.01694902,0.0045144423],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976102,0.0008321226,0.00022498089,0.00036913034,0.0007804748,0.00018298633],"domain_scores_gemma":[0.9965,0.0018647249,0.00022158783,0.00079376664,0.0005204135,0.000099486846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025028046,0.0026353372,0.00086970505,0.001972244,0.0007859452,0.002589012,0.0037307825,0.0021973094,0.021086885],"category_scores_gemma":[0.012895295,0.0012964599,0.003004036,0.0019552547,0.0014652,0.0033021683,0.0035894713,0.0036763547,0.012815162],"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":[0.0004130868,0.0003823355,0.0025167717,0.0026819783,0.00016664052,0.00047616014,0.00054448814,0.1691707,0.0102682365,0.078553446,0.3006889,0.43413737],"study_design_scores_gemma":[0.0003793737,0.00016442577,0.00044116488,0.0002334616,0.00004105955,0.00030987535,0.000114059854,0.7660335,0.0112209255,0.06189004,0.15908025,0.00009187772],"about_ca_topic_score_codex":0.007243221,"about_ca_topic_score_gemma":0.01604936,"teacher_disagreement_score":0.021086885,"about_ca_system_score_codex":0.0016671997,"about_ca_system_score_gemma":0.004083002,"threshold_uncertainty_score":0.07054263},"labels":[],"label_agreement":null}]}