{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":14,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":14,"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":"6b3902dad86c","filters":{"venue":"Natural Language Processing Journal"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Huda Diab Abdulgalil","is_ca":true},{"name":"Otman Basir","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0630583087593844,"gpt":0.3692293337405086,"spread":0.3061710249811243,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002763933,0.001803949,0.001250228,0.002030037,0.0005468454,0.00331874,0.002919812,0.001579817,0.008154644],"category_scores_gemma":[0.007123054,0.0006499955,0.001210844,0.002133507,0.001172848,0.006005218,0.002399155,0.002933716,0.00443797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001800867,"about_ca_system_score_gemma":0.00122899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004702269,"about_ca_topic_score_gemma":0.004344603,"domain_scores_codex":[0.9988068,0.0004348879,0.00009053437,0.0002664064,0.000328582,0.00007271207],"domain_scores_gemma":[0.9971882,0.001615964,0.0001220299,0.0004456679,0.0005372076,0.00009099177],"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":[0.0001446659,0.000134615,0.0004427795,0.001490465,0.00009842421,0.0001933521,0.0003517866,0.05927686,0.006245237,0.05281987,0.03720463,0.8415973],"study_design_scores_gemma":[0.00002808177,0.0001749141,0.0003467185,0.0004683287,0.00007368151,0.0006253534,0.0002756274,0.795644,0.01426108,0.08294562,0.1050604,0.00009622068],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.005441832,0.04114411,0.9293787,0.003081382,0.0005160657,0.0002277424,0.0008695492,0.007503779,0.01183676],"genre_scores_gemma":[0.1780937,0.07177547,0.7191174,0.002858002,0.001546573,0.0005961126,0.006533983,0.002991729,0.01648697],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.008154644,"threshold_uncertainty_score":0.02727997,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Tasnim Ahmed","is_ca":true},{"name":"Shahriar Ivan","is_ca":false},{"name":"Ahnaf Munir","is_ca":false},{"name":"Sabbir Ahmed","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0147495634554516,"gpt":0.3798009601573698,"spread":0.3650513967019182,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007685723,0.0008913254,0.0003379238,0.001706546,0.0002760468,0.0008141975,0.0005848458,0.0005140425,0.001681491],"category_scores_gemma":[0.003892553,0.0002003414,0.0006443869,0.000843567,0.0002681662,0.001044914,0.0007477639,0.0009611844,0.001028819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005382965,"about_ca_system_score_gemma":0.0004113055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00618171,"about_ca_topic_score_gemma":0.01051539,"domain_scores_codex":[0.9997261,0.0000989379,0.00001961774,0.00008021372,0.00003901513,0.0000360781],"domain_scores_gemma":[0.999087,0.0005858216,0.00007063019,0.0001016189,0.0001122208,0.00004281952],"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":[0.0008303954,0.000447248,0.09426966,0.0002773085,0.000407886,0.0005786875,0.0009090169,0.1862813,0.01303526,0.01013645,0.01467278,0.6781541],"study_design_scores_gemma":[0.00001155173,0.0000624231,0.004858233,0.00001478471,0.00003711814,0.00007731068,0.00009211295,0.9833618,0.001467285,0.008872549,0.001133151,0.00001171579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4639291,0.002272084,0.512711,0.002327109,0.0002584841,0.0002682279,0.004843054,0.005863825,0.0075271],"genre_scores_gemma":[0.9561913,0.0003294445,0.03805045,0.0001264659,0.00006397696,0.00006181717,0.003018738,0.0000586583,0.002099168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00618171,"threshold_uncertainty_score":0.01229149,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Speech recognition; Computer science","authors":[{"name":"Nada Gohider","is_ca":true},{"name":"Otman Basir","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02465899947680629,"gpt":0.301425732541467,"spread":0.2767667330646607,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004810812,0.001306758,0.001416376,0.006196192,0.0005289324,0.003090847,0.001702642,0.001670395,0.005452555],"category_scores_gemma":[0.01018048,0.0007780403,0.001231873,0.007301997,0.001034545,0.005653986,0.001634659,0.001898266,0.004427928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006787165,"about_ca_system_score_gemma":0.0019953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002599071,"about_ca_topic_score_gemma":0.001920762,"domain_scores_codex":[0.9972996,0.0004466784,0.0004604566,0.0008804621,0.0007784324,0.0001343219],"domain_scores_gemma":[0.9850492,0.009653568,0.0006425501,0.0007679244,0.003542567,0.0003442483],"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":[0.00009645336,0.00008642651,0.00240946,0.004593588,0.00007939032,0.0001153796,0.0002227379,0.00135369,0.001800656,0.004003457,0.01596169,0.9692771],"study_design_scores_gemma":[0.00002581241,0.0005149083,0.01038414,0.004995996,0.000511164,0.002681973,0.001321842,0.01318761,0.00722524,0.009717094,0.9492203,0.0002139325],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.007790582,0.9386557,0.03591299,0.003732268,0.001694919,0.00009040841,0.0006451581,0.0006535057,0.01082451],"genre_scores_gemma":[0.03123335,0.9278124,0.02765872,0.001957063,0.004094067,0.00007614708,0.00242378,0.0001815624,0.004562975],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.006196192,"threshold_uncertainty_score":0.0254423,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"New York Institute of Technology","funders":"","keywords":"Personality; Psychology; Natural language processing; Cognitive psychology; Computer science; Social psychology","authors":[{"name":"Md. Ali Akber","is_ca":false},{"name":"Tahira Ferdousi","is_ca":false},{"name":"Rasel Ahmed","is_ca":false},{"name":"Risha Asfara","is_ca":false},{"name":"Raqeebir Rab","is_ca":false},{"name":"Umme Zakia","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0217752863376495,"gpt":0.3217020835763816,"spread":0.2999267972387321,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004704678,0.0004928826,0.0002589019,0.001608716,0.000243164,0.00068484,0.0001518592,0.0002715489,0.001238203],"category_scores_gemma":[0.002587012,0.00008566483,0.0003864386,0.001255599,0.0002042362,0.001127629,0.0005188089,0.0003557176,0.0006475149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001690975,"about_ca_system_score_gemma":0.0001248449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007064696,"about_ca_topic_score_gemma":0.0009708618,"domain_scores_codex":[0.9994333,0.0001638197,0.00006169572,0.0001479102,0.0001395968,0.0000535894],"domain_scores_gemma":[0.9987457,0.0005116413,0.0002268799,0.0001612812,0.0002636151,0.00009088392],"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":[0.001300453,0.0006473318,0.3457127,0.0008249832,0.0004430349,0.001674259,0.002372977,0.01110254,0.05639651,0.004409763,0.01552934,0.559586],"study_design_scores_gemma":[0.00002017613,0.0008566026,0.7029127,0.0001714268,0.0002852707,0.002874912,0.00262257,0.2396894,0.01419259,0.005943022,0.03032077,0.0001103927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9170871,0.002007953,0.06751524,0.0003995012,0.0002930807,0.0001233709,0.006549514,0.0006984505,0.005325807],"genre_scores_gemma":[0.9790835,0.0003922186,0.01510623,0.00004177696,0.0001211751,0.00006910464,0.003666048,0.00004071909,0.001479419],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001608716,"threshold_uncertainty_score":0.004142165,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Behrad TaghiBeyglou","is_ca":true},{"name":"Frank Rudzicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02893580565716974,"gpt":0.2818778643010476,"spread":0.2529420586438779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008196302,0.0006039485,0.0003639091,0.0006283944,0.0001694469,0.0005353076,0.0005197416,0.0003877947,0.0005965955],"category_scores_gemma":[0.001767658,0.0001687531,0.0005092854,0.0003942175,0.0002601113,0.0009079441,0.0005526888,0.0007531629,0.0004003169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004015091,"about_ca_system_score_gemma":0.0006030834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008014279,"about_ca_topic_score_gemma":0.01437728,"domain_scores_codex":[0.9997365,0.00009659016,0.00001491413,0.00007930921,0.00003312235,0.0000395945],"domain_scores_gemma":[0.9995483,0.0002686469,0.00003407427,0.00003966437,0.00007871796,0.00003052202],"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":[0.001456702,0.0004493707,0.04042646,0.0002128475,0.000287484,0.0005759738,0.0003497631,0.3784644,0.01545374,0.007786413,0.008581165,0.5459557],"study_design_scores_gemma":[0.00001601737,0.00007524425,0.002307548,0.0000139297,0.00004543774,0.00008699291,0.00003805364,0.9915832,0.001757138,0.003451602,0.0006149453,0.000009996856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.76654,0.003369051,0.2191872,0.001290031,0.0001924073,0.00007726256,0.001254641,0.002499131,0.005590272],"genre_scores_gemma":[0.9799973,0.0003104532,0.01722331,0.0001533515,0.00004182138,0.00002260311,0.0009764045,0.00003123483,0.001243569],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008014279,"threshold_uncertainty_score":0.0159353,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Shaina Raza","is_ca":true},{"name":"Veronica Chatrath","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.006087059208944044,"gpt":0.2661430222922774,"spread":0.2600559630833334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001321334,0.001298909,0.0008545956,0.001655199,0.0006989574,0.0009904621,0.001245497,0.001300531,0.00265042],"category_scores_gemma":[0.003639168,0.0003552995,0.0005569978,0.0005505909,0.0004573103,0.001943174,0.002460699,0.00117066,0.001758563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005599273,"about_ca_system_score_gemma":0.0006590629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006074141,"about_ca_topic_score_gemma":0.01031567,"domain_scores_codex":[0.9990701,0.0002413408,0.00003854028,0.0002917142,0.0002286425,0.0001295815],"domain_scores_gemma":[0.9988825,0.0004315314,0.00009738699,0.0001890927,0.0003179098,0.0000815883],"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":[0.0006617684,0.0005599936,0.02404503,0.0002960325,0.0003188949,0.0009068323,0.0007346126,0.04996382,0.02958301,0.002901873,0.05736713,0.8326612],"study_design_scores_gemma":[0.00002038403,0.0001819467,0.003798288,0.00002375806,0.00005102776,0.0002669933,0.0002837525,0.9689189,0.01506175,0.0035902,0.007767882,0.00003509211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3842869,0.002757308,0.5529469,0.001553589,0.0009435217,0.0005376204,0.003927387,0.03041543,0.02263132],"genre_scores_gemma":[0.8233431,0.0004250242,0.1520839,0.0007284074,0.0002194601,0.0001589612,0.005309024,0.0005575543,0.0171746],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006074141,"threshold_uncertainty_score":0.01207757,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Nawshad Farruque","is_ca":true},{"name":"Randy Goebel","is_ca":true},{"name":"Sudhakar Sivapalan","is_ca":true},{"name":"Osmar R. Zai͏̈ane","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1007322898652962,"gpt":0.4643236625793267,"spread":0.3635913727140305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004142462,0.0007487537,0.0003326204,0.0009709391,0.0002045555,0.0008623287,0.0007739696,0.0006706442,0.002100812],"category_scores_gemma":[0.002467917,0.000276618,0.0005661117,0.0006284018,0.0001975269,0.0008908933,0.0004124274,0.00103632,0.001069238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006215442,"about_ca_system_score_gemma":0.0005955543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009155143,"about_ca_topic_score_gemma":0.01377366,"domain_scores_codex":[0.9998122,0.00003645841,0.00001537703,0.00006934602,0.00003689341,0.00002967229],"domain_scores_gemma":[0.9993654,0.0003754112,0.00009669492,0.00004577147,0.00008229299,0.00003436101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001014191,0.001132914,0.08566034,0.0003748728,0.0003494337,0.001270602,0.0006031216,0.4344294,0.02165079,0.01238124,0.02202691,0.4191062],"study_design_scores_gemma":[0.000009498899,0.00003943821,0.00361509,0.00001230669,0.00002021394,0.00008634946,0.00002218522,0.9903795,0.001113183,0.003415751,0.001278923,0.000007599344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4285159,0.002168598,0.5351319,0.004703302,0.0004843417,0.0003460124,0.0151541,0.003558289,0.009937684],"genre_scores_gemma":[0.9466847,0.0004909506,0.0412813,0.0002680491,0.0001505479,0.0001930608,0.004487225,0.00005574354,0.006388381],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009155143,"threshold_uncertainty_score":0.01820374,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Interpretability; Computer science; Margin (machine learning); Artificial intelligence; Machine learning; Transformer; Statistical model; Engineering","authors":[{"name":"Abbas Akkasi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01353790584292541,"gpt":0.2620085156993179,"spread":0.2484706098563925,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005089268,0.0009084745,0.0003600557,0.001221559,0.0002978574,0.0005524976,0.0009659869,0.0006872932,0.002385336],"category_scores_gemma":[0.001545449,0.0003014377,0.001164054,0.001043017,0.0002124727,0.001460251,0.0008710432,0.001352352,0.001257106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006370504,"about_ca_system_score_gemma":0.0009670905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01268134,"about_ca_topic_score_gemma":0.02418,"domain_scores_codex":[0.9997956,0.00003869209,0.00001272866,0.0000858257,0.00003635396,0.00003075667],"domain_scores_gemma":[0.9995199,0.0002477315,0.00003526175,0.00006877918,0.0001024838,0.00002583887],"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":[0.0004296474,0.0004443718,0.01988093,0.0003434306,0.0002747146,0.000777702,0.0006151745,0.2733017,0.01668289,0.009728899,0.03053517,0.6469854],"study_design_scores_gemma":[0.000009581355,0.00003874311,0.002029916,0.00002115235,0.0000566014,0.00007824958,0.00005947211,0.9855508,0.003505217,0.004753726,0.003881671,0.00001480122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1791666,0.001530385,0.7872555,0.0009602274,0.0002817479,0.0002252662,0.007499724,0.01451239,0.008568143],"genre_scores_gemma":[0.7903439,0.0007190886,0.1775637,0.000350965,0.0001002814,0.0002327828,0.01868251,0.0003752851,0.01163155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01268134,"threshold_uncertainty_score":0.02521503,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Marzieh Soltani","is_ca":true},{"name":"Shayan Sharif","is_ca":true},{"name":"Rozita Dara","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02159717973630499,"gpt":0.4121351556805344,"spread":0.3905379759442294,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001476654,0.0003034579,0.0001657876,0.001764094,0.0005359261,0.001209883,0.0001937578,0.000449673,0.00107862],"category_scores_gemma":[0.006774761,0.000112074,0.0002014743,0.001132246,0.0003838728,0.001373526,0.001019252,0.0004347975,0.0003327292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005556446,"about_ca_system_score_gemma":0.0002898708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00448674,"about_ca_topic_score_gemma":0.005743947,"domain_scores_codex":[0.9992142,0.0004060304,0.00005932467,0.00009584635,0.0001635929,0.00006106483],"domain_scores_gemma":[0.9931461,0.004964771,0.001002467,0.0001823246,0.0005592376,0.0001450993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001698052,0.0005017766,0.5478662,0.001645432,0.0002014876,0.002018332,0.1836533,0.002727585,0.06103416,0.003125218,0.009176907,0.1863516],"study_design_scores_gemma":[0.00002950691,0.0004638095,0.7813728,0.0004955926,0.0001550518,0.000607368,0.1238763,0.03776504,0.01480238,0.001544817,0.03877194,0.0001153627],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9960188,0.0001603228,0.0005681107,0.0002695299,0.00002626286,0.00002753112,0.0007362933,0.00002421216,0.002168928],"genre_scores_gemma":[0.9965295,0.0002108404,0.001213099,0.00007467347,0.00008062371,0.00004665831,0.0009183151,0.0000135987,0.0009125344],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00448674,"threshold_uncertainty_score":0.008921266,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Tasnim Ahmed","is_ca":true},{"name":"Salimur Choudhury","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00951167119287442,"gpt":0.2937268453066785,"spread":0.284215174113804,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002502805,0.002635337,0.0008697051,0.001972244,0.0007859452,0.002589012,0.003730783,0.002197309,0.02108688],"category_scores_gemma":[0.0128953,0.00129646,0.003004036,0.001955255,0.0014652,0.003302168,0.003589471,0.003676355,0.01281516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0016672,"about_ca_system_score_gemma":0.004083002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007243221,"about_ca_topic_score_gemma":0.01604936,"domain_scores_codex":[0.9976102,0.0008321226,0.0002249809,0.0003691303,0.0007804748,0.0001829863],"domain_scores_gemma":[0.9965,0.001864725,0.0002215878,0.0007937666,0.0005204135,0.00009948685],"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":[0.0004130868,0.0003823355,0.002516772,0.002681978,0.0001666405,0.0004761601,0.0005444881,0.1691707,0.01026824,0.07855345,0.3006889,0.4341374],"study_design_scores_gemma":[0.0003793737,0.0001644258,0.0004411649,0.0002334616,0.00004105955,0.0003098754,0.0001140599,0.7660335,0.01122093,0.06189004,0.1590803,0.00009187772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003641903,0.0008542587,0.8427414,0.0009306631,0.0002033919,0.0003568103,0.004854557,0.1380215,0.008395522],"genre_scores_gemma":[0.03754861,0.000492481,0.9209999,0.000721056,0.00006467966,0.0008170121,0.01789274,0.01694902,0.004514442],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02108688,"threshold_uncertainty_score":0.07054263,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Sheridan College; Toronto Metropolitan University; Vector Institute","funders":"","keywords":"Inclusion (mineral); Psychology; Internet privacy; Sociology; Computer science; Social psychology","authors":[{"name":"Shaina Raza","is_ca":true},{"name":"Abdullah Y. Muaad","is_ca":false},{"name":"Emrul Hasan","is_ca":true},{"name":"Muskan Garg","is_ca":false},{"name":"Zainab Al-Zanbouri","is_ca":true},{"name":"Syed Raza Bashir","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01041384149733446,"gpt":0.3321838089788432,"spread":0.3217699674815088,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006495334,0.0015558,0.0006733933,0.002695088,0.001995587,0.004461146,0.002260051,0.002371007,0.003973146],"category_scores_gemma":[0.01790497,0.0008615921,0.001633885,0.0009240774,0.004493254,0.007855867,0.005300872,0.002899526,0.001811871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002352029,"about_ca_system_score_gemma":0.005336461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007448119,"about_ca_topic_score_gemma":0.007915911,"domain_scores_codex":[0.9930668,0.003463389,0.0004842375,0.001302476,0.001353951,0.0003292085],"domain_scores_gemma":[0.9921873,0.003766612,0.001031053,0.001272978,0.001151622,0.0005904596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002559194,0.0003912151,0.005469789,0.000578821,0.00008041779,0.000651844,0.008939944,0.05704844,0.01644834,0.6466315,0.01431854,0.2491853],"study_design_scores_gemma":[0.00005486181,0.000341953,0.001587468,0.000318895,0.00009904685,0.0007714758,0.002410758,0.437959,0.01170131,0.444127,0.1004406,0.0001877017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004790983,0.0001590316,0.9862604,0.001169763,0.00006006689,0.0003310743,0.0001860435,0.002329669,0.004713014],"genre_scores_gemma":[0.1928708,0.000367902,0.7993488,0.0005672243,0.0001098667,0.0007707004,0.0006428999,0.0003743877,0.004947338],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007448119,"threshold_uncertainty_score":0.03435099,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Vivek Suresh Raj","is_ca":true},{"name":"Ruba Priyadharshini","is_ca":false},{"name":"R. Saranya","is_ca":false},{"name":"Bharathi Raja Chakravarthi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02416340836884429,"gpt":0.3046702726710389,"spread":0.2805068643021946,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006233578,0.001220599,0.002806748,0.0009586575,0.0007286967,0.001707033,0.003057891,0.002894154,0.004395423],"category_scores_gemma":[0.01588489,0.0008521623,0.0009365915,0.0007113456,0.002262694,0.002165971,0.001693762,0.003320077,0.0005948248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00253588,"about_ca_system_score_gemma":0.00261922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01403181,"about_ca_topic_score_gemma":0.008577307,"domain_scores_codex":[0.9978374,0.0009593814,0.0000994513,0.0005512491,0.0002623694,0.0002901473],"domain_scores_gemma":[0.9874994,0.00945813,0.0009988266,0.0003212535,0.001257451,0.0004648959],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000292184,0.0001546586,0.002995556,0.0001283469,0.00006962757,0.0002114626,0.0001865984,0.9437391,0.0007181303,0.02252107,0.001379297,0.02760391],"study_design_scores_gemma":[0.000014981,0.00002425077,0.000190237,0.000007120017,0.000005967088,0.000008057302,0.000006089876,0.9953339,0.0001044728,0.004201887,0.00009636604,0.00000668541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1155264,0.0007661704,0.8752984,0.003033993,0.0001444173,0.000323977,0.0004081487,0.000678337,0.003820028],"genre_scores_gemma":[0.9131488,0.0002319791,0.07909059,0.000638162,0.0001086544,0.0005083506,0.0002751856,0.00007432063,0.005924038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01403181,"threshold_uncertainty_score":0.03296667,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Nazmus Sakeef","is_ca":true},{"name":"M. Ali Akber Dewan","is_ca":true},{"name":"Fuhua Lin","is_ca":true},{"name":"Dharamjit Parmar","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06930139704892432,"gpt":0.4957217460275704,"spread":0.4264203489786461,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006829584,0.001406252,0.002458436,0.009778777,0.0006002817,0.002457648,0.001661357,0.001731284,0.001999438],"category_scores_gemma":[0.01390947,0.0007584753,0.001344734,0.007196029,0.001788414,0.003943502,0.001490724,0.001679492,0.0008369429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001835944,"about_ca_system_score_gemma":0.004533296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004677997,"about_ca_topic_score_gemma":0.006131184,"domain_scores_codex":[0.9972108,0.0008760586,0.0004472812,0.0005621322,0.0008198001,0.00008385367],"domain_scores_gemma":[0.9796262,0.01678687,0.001115325,0.0003160342,0.001935778,0.0002197199],"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":[0.00004482921,0.00007649582,0.001144099,0.04542019,0.0001633354,0.00004853184,0.0006147424,0.0002314015,0.0004439036,0.003400212,0.003326389,0.9450859],"study_design_scores_gemma":[0.00004404342,0.0005120253,0.02550483,0.1345095,0.001989972,0.001736627,0.0031485,0.001122554,0.002414314,0.01686563,0.8118778,0.0002741815],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0003672681,0.9969317,0.001304949,0.0003870034,0.00008450622,0.00003176727,0.00003624878,0.00001564583,0.0008409228],"genre_scores_gemma":[0.004073058,0.9928342,0.00244873,0.0001957343,0.0001064766,0.00009422446,0.00004832221,0.000007945433,0.0001913758],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.009778777,"threshold_uncertainty_score":0.03611875,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Jingkai Li","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01070362742570176,"gpt":0.3059250177171058,"spread":0.2952213902914041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002015521,0.0002648101,0.0002862552,0.001461962,0.0002868921,0.001952612,0.0004087049,0.0004094086,0.0021881],"category_scores_gemma":[0.03307423,0.0002345083,0.0004174799,0.0008660471,0.001537823,0.003166428,0.001805573,0.0008788003,0.0001971313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004814854,"about_ca_system_score_gemma":0.0004540947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007450769,"about_ca_topic_score_gemma":0.0006332902,"domain_scores_codex":[0.9989912,0.0003689204,0.00008256698,0.0002429977,0.0002266984,0.00008766732],"domain_scores_gemma":[0.9881482,0.007115724,0.001757737,0.001944353,0.0006597149,0.0003743963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001335716,0.0003177797,0.363525,0.0005829902,0.0005993435,0.0004621168,0.0170176,0.01794564,0.1794099,0.0934617,0.001120355,0.3242219],"study_design_scores_gemma":[0.00004118028,0.0008617002,0.6067768,0.000101488,0.000247303,0.0007791055,0.004820575,0.1360276,0.03813196,0.209692,0.002292841,0.0002274251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9412333,0.000065991,0.05486851,0.0001482846,0.0000119811,0.00002566184,0.0001725927,0.0001434337,0.003330193],"genre_scores_gemma":[0.9923885,0.00001856215,0.00727704,0.00002056654,0.000003294948,0.0000242955,0.0001359703,0.00002601069,0.0001056213],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0021881,"threshold_uncertainty_score":0.01065922,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}