{"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"},"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001333279,0.0001802716,0.0002734283,0.0002949322,0.0003396052,0.000349073,0.0004852718,0.00008957508,0.000005958382],"category_scores_gemma":[0.0006287405,0.000153644,0.00005412213,0.0004377197,0.00003877351,0.0009760634,0.0001324616,0.0005530218,0.000001194344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005261588,"about_ca_system_score_gemma":0.0001136237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0015696,"about_ca_topic_score_gemma":0.0004846693,"domain_scores_codex":[0.9983776,0.0003441494,0.0003580232,0.0003682454,0.0002654352,0.0002865065],"domain_scores_gemma":[0.9989703,0.0002816457,0.0001934501,0.0001985206,0.000267955,0.00008817682],"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":[0.00002665587,0.00003644223,0.0003352919,0.0000558355,0.00003844604,0.000007667559,0.0287252,0.00128723,0.1492496,0.0004874309,0.00002012234,0.81973],"study_design_scores_gemma":[0.0005892712,0.0000300004,0.03068471,0.0001500087,0.00002322757,0.00002108556,0.003043111,0.957644,0.007010986,0.0005701382,0.00001119952,0.000222228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.362071,0.02323296,0.6128168,0.001457518,0.0001136883,0.0001100501,0.00001165097,0.00007837762,0.0001080101],"genre_scores_gemma":[0.6997854,0.00009196009,0.2999023,0.0001168452,0.00005051312,0.000007910132,0.0000138664,0.000008405426,0.00002289935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9563568,"threshold_uncertainty_score":0.6265422,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0007179426,0.0002437782,0.0002926492,0.0001585588,0.001673733,0.0005254391,0.0001337846,0.0001688754,0.00007469209],"category_scores_gemma":[0.0000167466,0.0001732645,0.00008124099,0.0003257875,0.00005718927,0.0007398577,0.00003361787,0.001223101,0.000001420662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002178914,"about_ca_system_score_gemma":0.0001795017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000200662,"about_ca_topic_score_gemma":0.00003590598,"domain_scores_codex":[0.9980572,0.0001326304,0.0004023292,0.0004208604,0.0003218006,0.0006651414],"domain_scores_gemma":[0.999325,0.0001591332,0.0001677626,0.00006739732,0.0000981903,0.000182548],"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":[0.0003929186,0.00003666226,0.005728435,0.0008574909,0.00008878372,0.000379757,0.01187622,0.00002079845,0.000763409,0.0001249184,0.001068197,0.9786624],"study_design_scores_gemma":[0.03258547,0.002413787,0.119127,0.04723171,0.00279813,0.03121541,0.1582677,0.5393317,0.006664752,0.008496994,0.04393066,0.007936617],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7730748,0.1724277,0.04889351,0.0008557939,0.001428072,0.000596554,0.000007831443,0.0002253135,0.002490389],"genre_scores_gemma":[0.9847895,0.00004171837,0.01295142,0.0004122714,0.001457559,0.00004867135,0.00001514616,0.00005025742,0.0002334495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9707258,"threshold_uncertainty_score":0.999626,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009919,0.0001701925,0.0001873057,0.0003268217,0.000148984,0.001053519,0.0004268933,0.00007170017,0.0006661219],"category_scores_gemma":[0.0004595919,0.0001326448,0.0000654059,0.00101353,0.00002318321,0.0016934,0.00006562607,0.0006392855,0.0001397591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000144944,"about_ca_system_score_gemma":0.0001935952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001357996,"about_ca_topic_score_gemma":0.0001319224,"domain_scores_codex":[0.9982824,0.0002100946,0.0003970282,0.000314542,0.0004557559,0.0003401889],"domain_scores_gemma":[0.9993349,0.0001568265,0.00009874828,0.0001412547,0.0001678549,0.0001004604],"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":[0.000007391607,0.00004445187,0.000133234,0.00004996248,0.00001146862,0.0004339245,0.0008501826,3.396501e-7,0.000324593,0.000003022948,0.0003505241,0.9977909],"study_design_scores_gemma":[0.006093896,0.0004070984,0.06204421,0.01266418,0.0001195998,0.01555672,0.004036156,0.8196458,0.01461559,0.01766307,0.0432477,0.003905942],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6130421,0.3242012,0.03812429,0.008940089,0.006828734,0.0007230544,0.00003966032,0.001485475,0.006615342],"genre_scores_gemma":[0.8824034,0.001252298,0.1146284,0.0009325322,0.0002439077,0.00001485837,0.00002854163,0.00002876595,0.0004672171],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.993885,"threshold_uncertainty_score":0.9999835,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003904862,0.0001729511,0.0002849351,0.0005173235,0.0004527809,0.002273194,0.0003042941,0.00006066989,0.00007873206],"category_scores_gemma":[0.00003683112,0.0001320824,0.000229027,0.001355565,0.00006267552,0.001149525,0.0001205084,0.0005012582,0.000005650505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007590151,"about_ca_system_score_gemma":0.00008669513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002278952,"about_ca_topic_score_gemma":0.000003544448,"domain_scores_codex":[0.9985257,0.00008352866,0.0003079919,0.0003731226,0.000440779,0.0002688175],"domain_scores_gemma":[0.9993187,0.00008221601,0.0001487621,0.0001221332,0.0002044186,0.0001237368],"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":[0.00002042968,0.00005323877,0.0038743,0.0001968081,0.001878097,0.0004723179,0.0476909,0.0006839085,0.013551,0.001467145,0.0005299783,0.9295819],"study_design_scores_gemma":[0.0001831419,0.00001639418,0.003203033,0.0001772096,0.0003422326,0.0005617214,0.003151967,0.9915137,0.0002109135,0.00008606855,0.0003347794,0.0002188381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6990619,0.09174578,0.2079777,0.0005080463,0.0004118944,0.00004108763,0.000002090298,0.0001218783,0.0001296028],"genre_scores_gemma":[0.9709617,0.00003747827,0.02821161,0.0002361719,0.0003007716,4.073325e-7,0.000004738718,0.000008572143,0.0002384819],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9908298,"threshold_uncertainty_score":0.9987625,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003599578,0.000264353,0.0002528584,0.0002216149,0.0005033079,0.0007687731,0.0005327215,0.00007862502,0.000008032755],"category_scores_gemma":[0.00005138852,0.0001905752,0.00009278945,0.0004573236,0.00007711665,0.00125264,0.00006243584,0.0008871765,0.000004014585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004448886,"about_ca_system_score_gemma":0.0002497825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000192357,"about_ca_topic_score_gemma":0.00002521819,"domain_scores_codex":[0.9979568,0.00007197383,0.0003122598,0.0004596564,0.000632987,0.0005663866],"domain_scores_gemma":[0.9990543,0.00009380355,0.0001638467,0.0002429826,0.0001029491,0.0003421429],"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":[0.0001357744,0.00002325561,0.0002072717,0.00007174024,0.00003120437,0.0008359195,0.01439869,0.001797326,0.002411524,0.000103053,0.00004754431,0.9799367],"study_design_scores_gemma":[0.0009930996,0.00005960749,0.0004347206,0.0002015199,0.00005015503,0.0002655268,0.001166908,0.9940615,0.002279338,0.0001500072,0.00003324976,0.0003044202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7148138,0.0193814,0.2587133,0.006035137,0.0002637991,0.0001970338,0.000007862261,0.0005030342,0.00008467459],"genre_scores_gemma":[0.9823326,0.000009595152,0.01544787,0.001839051,0.0002313397,0.00000677948,0.000002871615,0.00003045436,0.00009943679],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9922641,"threshold_uncertainty_score":0.7771432,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005570689,0.0001685314,0.000123435,0.0001514119,0.0005025981,0.002464079,0.0004344016,0.0000914097,0.00001988213],"category_scores_gemma":[0.000079782,0.0001323442,0.0001042247,0.0007051903,0.00002499104,0.001598848,0.00007305996,0.001470094,0.00008713623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001272784,"about_ca_system_score_gemma":0.00009480811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002033378,"about_ca_topic_score_gemma":0.000008989083,"domain_scores_codex":[0.9985501,0.00005926942,0.0002597718,0.0003174104,0.0004415372,0.0003719721],"domain_scores_gemma":[0.9994756,0.00003306572,0.0001028092,0.0001466731,0.0001214364,0.0001204286],"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":[0.000004223396,0.0000072906,0.000003046158,0.00004561681,0.00001115443,0.0007487012,0.001527163,0.000008311622,0.06711508,0.00002422679,0.00006689359,0.9304383],"study_design_scores_gemma":[0.000467477,0.0001399923,0.0001311472,0.001466846,0.00003360985,0.02436342,0.000559898,0.603747,0.3623625,0.001567555,0.004568436,0.0005922083],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3912669,0.09303845,0.5056193,0.001497254,0.005690597,0.0001540879,0.000001214158,0.001639862,0.001092306],"genre_scores_gemma":[0.9700234,0.00003694488,0.02830766,0.0001761034,0.0008705454,0.000002740688,0.000001187115,0.00002041937,0.0005609828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9298461,"threshold_uncertainty_score":0.9985715,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001431441,0.000198895,0.0004215282,0.0001304944,0.0003468165,0.0001437345,0.0002873167,0.0002999418,0.0005528503],"category_scores_gemma":[0.0001674333,0.0001526882,0.000220747,0.0003083501,0.0001224046,0.0004522777,0.00006381647,0.00206288,0.00004995496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007159002,"about_ca_system_score_gemma":0.0001812645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003519984,"about_ca_topic_score_gemma":0.00001249165,"domain_scores_codex":[0.9971675,0.0002826591,0.001167837,0.0003594255,0.0005381315,0.0004844415],"domain_scores_gemma":[0.9987576,0.0004171924,0.0004448983,0.0001141895,0.0001296801,0.0001364338],"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":[0.0002409965,0.0001060357,0.002267184,0.0004478713,0.00005575615,0.0005556343,0.04420907,0.00003668706,0.000222135,0.0002139358,0.0010718,0.9505729],"study_design_scores_gemma":[0.01108814,0.0006010671,0.01684938,0.01382801,0.0007914315,0.01145744,0.1414027,0.7789595,0.002566943,0.01079828,0.008633553,0.003023569],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6894258,0.2631169,0.03117155,0.0005110704,0.006667485,0.0001825018,0.000009960711,0.0002217119,0.008693063],"genre_scores_gemma":[0.9796912,0.00004548838,0.01600863,0.0002237192,0.003713658,0.000004310828,0.00001463591,0.000049251,0.0002490884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9475493,"threshold_uncertainty_score":0.8962304,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007789218,0.0001925811,0.0001746356,0.0001758951,0.0004528939,0.001611788,0.0005038463,0.0001046594,0.000004143902],"category_scores_gemma":[0.00003219454,0.0001108476,0.00006359041,0.0004637141,0.00004958904,0.001686995,0.00004802849,0.001029409,0.000002315747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001382816,"about_ca_system_score_gemma":0.0002452073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001290605,"about_ca_topic_score_gemma":0.00003477754,"domain_scores_codex":[0.998373,0.00004820632,0.0002805291,0.0003821266,0.000494963,0.0004212162],"domain_scores_gemma":[0.9993805,0.00008840977,0.00005442308,0.0002192449,0.0001040167,0.0001534417],"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":[0.0000602988,0.00005614953,0.00003562614,0.0001650503,0.00001626643,0.0006323874,0.00671114,0.005842286,0.08360083,0.0006799905,0.0003176447,0.9018824],"study_design_scores_gemma":[0.0003345643,0.0001175842,0.0001522572,0.001169332,0.00003244985,0.004632707,0.0003251547,0.987662,0.003670765,0.001409413,0.0001949949,0.0002987745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06002821,0.008850482,0.9276457,0.002395308,0.0001727277,0.000179363,5.175306e-7,0.0001897474,0.0005378876],"genre_scores_gemma":[0.8031062,0.00001202493,0.1961267,0.0004476308,0.0001466595,0.00001051842,4.948604e-7,0.00001679567,0.0001329393],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9818197,"threshold_uncertainty_score":0.9994246,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001282519,0.00009964473,0.0002396564,0.0003065634,0.0009036763,0.0001978085,0.0002942779,0.00008396762,0.00009674658],"category_scores_gemma":[0.0009901428,0.00007996913,0.0001742626,0.0008933496,0.0002394055,0.0003181213,0.00004130447,0.0004544123,0.000001795403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009106267,"about_ca_system_score_gemma":0.0004707883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001214667,"about_ca_topic_score_gemma":0.0003828006,"domain_scores_codex":[0.9985526,0.0002623287,0.000356356,0.0001304079,0.0004561241,0.0002422069],"domain_scores_gemma":[0.9989613,0.0002547468,0.000299453,0.00004674,0.0003658553,0.00007189511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002632541,0.00003572396,0.005207023,0.00002651874,0.00006594141,0.00001399666,0.04986757,0.00002639689,0.0005573566,0.002545077,0.0001581603,0.9414699],"study_design_scores_gemma":[0.006564142,0.00008160673,0.3844444,0.002836288,0.002545849,0.00009601378,0.4464664,0.01487661,0.003075818,0.112077,0.0242955,0.002640271],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9250697,0.04182398,0.01010394,0.004633829,0.001240403,0.0001052892,0.000007204394,0.00009817017,0.0169175],"genre_scores_gemma":[0.993244,0.00001381648,0.005246324,0.000173501,0.0007109692,8.245115e-7,0.000003036489,0.000005391139,0.0006021422],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9388297,"threshold_uncertainty_score":0.6950439,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004283884,0.0002134801,0.0002533871,0.0001930803,0.0003563937,0.000460002,0.0002264279,0.0001683462,0.00002573987],"category_scores_gemma":[0.0007902798,0.0001779735,0.0001226807,0.0005479733,0.00003764365,0.0003153874,0.0000350575,0.0008261251,0.000003173755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001179264,"about_ca_system_score_gemma":0.0000658723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.368078e-7,"about_ca_topic_score_gemma":7.991341e-7,"domain_scores_codex":[0.9986677,0.00001422556,0.0004408548,0.000176712,0.0002293523,0.0004711137],"domain_scores_gemma":[0.9993235,0.0001259818,0.0001079865,0.0001166822,0.0002193796,0.0001064205],"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":[0.00007517191,0.00009885621,0.00002754468,0.002888281,0.0001576428,0.00002066295,0.003378899,0.009058055,0.004587655,0.001930239,0.000482888,0.9772941],"study_design_scores_gemma":[0.001041619,0.00005410292,0.000007850902,0.002869154,0.0001085154,0.00008691769,0.001295987,0.9795567,0.004723613,0.003818013,0.006006622,0.0004308929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002777645,0.02464787,0.9699555,0.0003683035,0.0007035378,0.0004818196,0.000001967881,0.0006302041,0.0004331566],"genre_scores_gemma":[0.4896357,0.00004080347,0.5094289,0.0001315393,0.0002447327,0.00002111642,0.000008776889,0.00004321531,0.0004452203],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9768632,"threshold_uncertainty_score":0.7257548,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004706533,0.00009419303,0.0001254723,0.0003012253,0.0006017867,0.0004164356,0.0005747952,0.00008040253,0.000001692572],"category_scores_gemma":[0.0009778319,0.00008364955,0.00003531645,0.0006470492,0.00005318601,0.000438193,0.0002435841,0.0007534439,5.731034e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001289659,"about_ca_system_score_gemma":0.0002228698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002128418,"about_ca_topic_score_gemma":0.0001461876,"domain_scores_codex":[0.9991412,0.00007583802,0.0002514682,0.0001891889,0.0001348348,0.0002074844],"domain_scores_gemma":[0.9991217,0.0002415018,0.0001503067,0.000251863,0.0001857019,0.00004891316],"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":[0.00004239026,0.00009781494,0.0005588021,0.00008742901,0.00002141898,0.00003048232,0.01931267,0.000007891075,0.003528779,0.01590396,0.00007521842,0.9603331],"study_design_scores_gemma":[0.004018879,0.0003057612,0.009698825,0.004796203,0.00007440452,0.0009955489,0.0144965,0.7190985,0.00875588,0.2312668,0.005609165,0.0008835929],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1917679,0.04632134,0.7212356,0.03844513,0.000676547,0.0006336659,0.000008852952,0.0002569314,0.0006540081],"genre_scores_gemma":[0.7313312,0.00004933476,0.2680639,0.0003499734,0.00007218134,0.000007732388,0.000002757895,0.000004651433,0.000118168],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9594495,"threshold_uncertainty_score":0.4628517,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009662623,0.0002749034,0.0003467587,0.001127151,0.0003195838,0.0004695237,0.000615445,0.0002851872,9.842504e-7],"category_scores_gemma":[0.003381855,0.000253921,0.0000659918,0.001758607,0.00008805827,0.0008337285,0.00009846876,0.001710686,6.535298e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004356941,"about_ca_system_score_gemma":0.0002740257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004836234,"about_ca_topic_score_gemma":0.0002902494,"domain_scores_codex":[0.9978722,0.0001740271,0.0006044363,0.0006094393,0.0002231279,0.0005168149],"domain_scores_gemma":[0.9983078,0.0009277223,0.0003598301,0.0002107213,0.0001386433,0.00005531],"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":[0.00008540437,0.0002057403,0.02330273,0.0002822095,0.00001556275,0.00005497018,0.04143179,0.005699682,0.01236372,0.0002620812,0.000005726675,0.9162904],"study_design_scores_gemma":[0.001413257,0.00002946049,0.03178999,0.0017161,0.000008936712,0.00002625731,0.01557459,0.9458811,0.001526324,0.001751192,0.00000340891,0.0002794345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1782806,0.008541961,0.8112101,0.001038583,0.00005660518,0.000508878,0.000002291735,0.0002766913,0.00008432966],"genre_scores_gemma":[0.7004533,0.00002324749,0.2992022,0.0001265604,0.0000147294,0.00006362823,0.000001450599,0.00001587264,0.00009893471],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9401814,"threshold_uncertainty_score":0.9999913,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005459469,0.0002687006,0.001348343,0.0003099824,0.0004122219,0.0001214969,0.0003132493,0.0004815142,0.00003911986],"category_scores_gemma":[0.01553595,0.0001961343,0.0002402697,0.0008450974,0.0001739102,0.0002319629,0.0001320222,0.00503028,4.113859e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001234342,"about_ca_system_score_gemma":0.002150885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002730819,"about_ca_topic_score_gemma":0.0001580385,"domain_scores_codex":[0.9960269,0.002115425,0.0007801683,0.0002678024,0.0004136976,0.0003960072],"domain_scores_gemma":[0.9962765,0.002203923,0.001070796,0.00007668594,0.0003011164,0.00007098324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000003813176,0.00002939792,0.000007470987,0.06871711,0.0000413239,0.00004935504,0.002092432,9.091629e-8,1.399972e-7,0.000006993679,0.00001755867,0.9290343],"study_design_scores_gemma":[0.0002069606,0.00003764021,0.000007107712,0.8086711,0.001074146,0.00007302572,0.03215899,0.00001219072,7.782145e-7,0.0001024733,0.1573446,0.0003110371],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000373909,0.9983431,0.0002291948,0.0003881479,0.0002281006,0.000406764,0.00001234085,0.0000315375,0.0003234064],"genre_scores_gemma":[0.0002263256,0.9709349,0.02802076,0.0002111339,0.0003819496,0.000009952142,0.00001817074,0.00001624237,0.000180579],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9287233,"threshold_uncertainty_score":0.9972652,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00101932,0.0001945372,0.0003217937,0.0003131687,0.0007472045,0.0005093968,0.0002693799,0.0001292284,0.0001520336],"category_scores_gemma":[0.002537581,0.000137171,0.0001120961,0.001154663,0.0001909235,0.001445173,0.00005974541,0.0005366907,6.625336e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001716588,"about_ca_system_score_gemma":0.0002801281,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01026454,"about_ca_topic_score_gemma":0.01911264,"domain_scores_codex":[0.9979489,0.000502729,0.0005112005,0.0002561839,0.00047671,0.0003042278],"domain_scores_gemma":[0.9978194,0.000612911,0.0006091597,0.0001669362,0.0006823743,0.0001091726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0009940087,0.0002115572,0.09087586,0.00005768084,0.001063873,0.00005727264,0.7491104,0.001406459,0.01289839,0.000887457,0.0001424727,0.1422945],"study_design_scores_gemma":[0.001630131,0.00005152816,0.03773587,0.0004829759,0.001201429,0.000008006327,0.88789,0.06076718,0.004606321,0.005235161,0.0000271747,0.0003641736],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9623452,0.003607712,0.0324846,0.0004789315,0.0001099963,0.000178867,0.0002380169,0.00005542424,0.0005012396],"genre_scores_gemma":[0.9949092,0.00004073475,0.003035218,0.0002263354,0.0001246176,0.000006277685,0.000730454,0.000009269813,0.0009179416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1419304,"threshold_uncertainty_score":0.998786,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}