{"meta":{"query_hash":"ab38acd60060","filters":{"venue":"International Joint Conference on Natural Language Processing"},"cohort_total":10,"direct_labels_cover":0,"predictions_cover":10,"exported":10,"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/ab38acd60060","api":"https://metacan.xera.ac/api/v1/cohort?venue=International+Joint+Conference+on+Natural+Language+Processing"},"results":[{"id":"W2132959801","doi":"","title":"Incremental Segmentation and Decoding Strategies for Simultaneous Translation","year":2013,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Decoding methods; Segmentation; Artificial intelligence; Machine translation; Speech recognition; Interpreter; Natural language processing; Speech translation; Active listening; Phrase; Task (project management); Latency (audio); Translation (biology); Algorithm; Programming language; Communication","score_opus":0.02833968079378524,"score_gpt":0.31117202112435544,"score_spread":0.2828323403305702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132959801","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047413897,0.004268515,0.9428076,0.0028578711,0.0003440022,0.00072983775,0.000010287481,0.00058742706,0.0009805585],"genre_scores_gemma":[0.663362,0.000009569244,0.33606887,0.00035173818,0.00006163484,0.00006151719,0.000025002613,0.000009098106,0.000050552826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871314,0.000027899816,0.00028368426,0.00040816344,0.00034307374,0.00022406121],"domain_scores_gemma":[0.9991647,0.00013087601,0.00018361778,0.00012196665,0.00034176194,0.000057079928],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00014961838,0.00020002248,0.00014832852,0.0002014802,0.00016445384,0.0013616085,0.00043346678,0.00007401322,0.00003330427],"category_scores_gemma":[0.000110433255,0.00016974473,0.00004422136,0.00012061448,0.00004751436,0.002215149,0.00008169207,0.00020638936,0.000007195307],"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":[0.000014771354,0.000020582202,0.000009821551,0.00004822163,0.000012012397,0.0000080111195,0.0016766929,0.000012353886,0.16677794,0.016604189,0.00002368877,0.81479174],"study_design_scores_gemma":[0.0005876113,0.000100430756,0.000053045944,0.00027722566,0.000008751598,0.000052331518,0.001781555,0.9094615,0.056770224,0.030513957,0.000025796988,0.00036755824],"about_ca_topic_score_codex":0.00006760581,"about_ca_topic_score_gemma":0.00001562517,"teacher_disagreement_score":0.90944916,"about_ca_system_score_codex":0.000092336435,"about_ca_system_score_gemma":0.0000783294,"threshold_uncertainty_score":0.9996751},"labels":[],"label_agreement":null},{"id":"W2250473310","doi":"","title":"Can I Hear You? Sentiment Analysis on Medical Forums","year":2013,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":42,"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 Ottawa","funders":"","keywords":"Lexicon; Sentiment analysis; Computer science; Annotation; Natural language processing; World Wide Web; Information retrieval; Artificial intelligence","score_opus":0.018991286940984495,"score_gpt":0.29480584887556693,"score_spread":0.2758145619345824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250473310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62608385,0.0018495619,0.16921966,0.15888323,0.0036068596,0.00088541774,0.000025472285,0.0009467314,0.03849921],"genre_scores_gemma":[0.991815,0.000009622854,0.0037022673,0.0025519629,0.00016094347,0.000020855656,0.0000526361,0.00000857098,0.0016781446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972971,0.000055447174,0.00039824902,0.0005560516,0.0013775807,0.00031558474],"domain_scores_gemma":[0.99895674,0.000051592335,0.0002149867,0.0003074705,0.0003001091,0.00016908237],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002660472,0.00021685586,0.00027953336,0.0005839961,0.0001407142,0.00079940323,0.0009074301,0.00007875854,0.0016346356],"category_scores_gemma":[0.00011238291,0.00016619754,0.00022008,0.0005942869,0.00004307992,0.0004474833,0.00021165422,0.000333792,0.0002190846],"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":[0.000025842262,0.00039486634,0.0027740153,0.000023224617,0.0012184215,0.00017219932,0.0040477836,0.00035169962,0.0047535137,0.053570148,0.0013969943,0.9312713],"study_design_scores_gemma":[0.00039207135,0.000060909162,0.00473635,0.00019615664,0.00004883133,0.000011696143,0.0005864304,0.9887557,0.004053584,0.0005944218,0.00023524703,0.00032862095],"about_ca_topic_score_codex":0.00021313808,"about_ca_topic_score_gemma":0.0000380582,"teacher_disagreement_score":0.988404,"about_ca_system_score_codex":0.00010964594,"about_ca_system_score_gemma":0.000100303485,"threshold_uncertainty_score":0.999278},"labels":[],"label_agreement":null},{"id":"W2252242089","doi":"","title":"On the Effectiveness of Using Syntactic and Shallow Semantic Tree Kernels for Automatic Assessment of Essays","year":2013,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"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 Lethbridge","funders":"","keywords":"Computer science; Natural language processing; Grading (engineering); Artificial intelligence; Latent semantic analysis; Task (project management); Tree (set theory); Tree structure; Data structure; Programming language","score_opus":0.031931837597632816,"score_gpt":0.3179565227045993,"score_spread":0.2860246851069665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2252242089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71617,0.00010538977,0.28198335,0.00034800186,0.00016947598,0.00035464118,0.0000023038144,0.000027541522,0.00083926634],"genre_scores_gemma":[0.9745285,0.0000015208061,0.02531886,0.00007065171,0.0000205659,0.00003469732,0.0000019303861,0.0000072229386,0.000016062355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988534,0.000107338754,0.00028128925,0.00025957354,0.00036344092,0.00013498958],"domain_scores_gemma":[0.9984531,0.0007399524,0.00026700745,0.0001968243,0.00031625226,0.000026887747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050205586,0.00013098134,0.0002107548,0.00012429607,0.000059024962,0.00016376114,0.0004475086,0.0000390378,0.000018373777],"category_scores_gemma":[0.000324749,0.000087126784,0.00005475741,0.00008584411,0.000048762788,0.00037494057,0.000110533256,0.00015087666,8.471447e-7],"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":[0.00003912124,0.00019664531,0.0012914691,0.001153254,0.00013733604,0.000009961946,0.0018498847,0.0011390921,0.26364794,0.4208487,0.0000024344063,0.30968416],"study_design_scores_gemma":[0.00026892588,0.000050417977,0.008795988,0.0012978899,0.000009659388,0.000011004961,0.00017587864,0.96678394,0.00918031,0.013332476,1.0542443e-7,0.0000934053],"about_ca_topic_score_codex":0.00009154766,"about_ca_topic_score_gemma":0.0000041971102,"teacher_disagreement_score":0.96564484,"about_ca_system_score_codex":0.00006768276,"about_ca_system_score_gemma":0.00010363483,"threshold_uncertainty_score":0.3552927},"labels":[],"label_agreement":null},{"id":"W2622583534","doi":"","title":"Towards Abstractive Multi-Document Summarization Using Submodular Function-Based Framework, Sentence Compression and Merging","year":2016,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"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 Lethbridge","funders":"","keywords":"Submodular set function; Automatic summarization; Computer science; Redundancy (engineering); Sentence; Artificial intelligence; Natural language processing; Scalability; Set (abstract data type); Multi-document summarization; Information retrieval; Mathematics; Database","score_opus":0.03583080388495406,"score_gpt":0.3049195049577958,"score_spread":0.2690887010728417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2622583534","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11516498,0.0004405539,0.88160163,0.0017734546,0.0006406585,0.00011845993,0.0000048590005,0.00012872055,0.00012666047],"genre_scores_gemma":[0.85871595,0.000009902623,0.14072955,0.00035608152,0.00009630035,0.000008034259,0.0000066846155,0.000010743455,0.000066742236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830216,0.00005747566,0.00030048468,0.00055373413,0.0005487808,0.00023738199],"domain_scores_gemma":[0.9989838,0.00008786094,0.0002489709,0.00022503037,0.0003720592,0.000082267776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019504753,0.00020769505,0.00016243164,0.00019839009,0.00015879044,0.00036943963,0.0004013517,0.00008996203,0.000043286684],"category_scores_gemma":[0.00020824121,0.00014916326,0.00004752387,0.00011458691,0.000056680245,0.0010568128,0.000172532,0.00025998926,0.0000069688385],"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":[0.00005625839,0.00007051471,0.00062150887,0.00004149441,0.000027552627,0.000043780536,0.00090156624,0.0017047727,0.2636756,0.014692809,0.0000025637923,0.7181616],"study_design_scores_gemma":[0.0005073443,0.000024355484,0.002034055,0.0012433666,0.000008239055,0.00001330833,0.0001719121,0.9641856,0.029615823,0.0019294395,0.000018587272,0.00024796347],"about_ca_topic_score_codex":0.00009503811,"about_ca_topic_score_gemma":0.000007282894,"teacher_disagreement_score":0.96248084,"about_ca_system_score_codex":0.00018872746,"about_ca_system_score_gemma":0.0001418579,"threshold_uncertainty_score":0.6082701},"labels":[],"label_agreement":null},{"id":"W2773368817","doi":"","title":"Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Recurrent neural network; Benchmark (surveying); Feature engineering; Computer science; Artificial intelligence; Machine learning; Feature (linguistics); Artificial neural network; Long short term memory; Term (time); Deep learning","score_opus":0.04678864868712887,"score_gpt":0.35796626419052296,"score_spread":0.31117761550339407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773368817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988239,0.0017596243,0.008103192,0.00071447506,0.00059114734,0.00022937682,0.000013539458,0.00003477706,0.00031487996],"genre_scores_gemma":[0.99576247,0.0000123183745,0.0030527348,0.00008083238,0.00049904414,0.00003408284,0.00019417559,0.000019896703,0.00034446936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985216,0.000054575612,0.00029513755,0.0004872652,0.00033800278,0.0003033896],"domain_scores_gemma":[0.9992035,0.000008423438,0.00022258516,0.00028993448,0.00018433374,0.00009121352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017036512,0.00023892372,0.00019861868,0.0001575026,0.00023875055,0.0005567205,0.00050844176,0.00014736719,0.000025380852],"category_scores_gemma":[0.00025255446,0.00018091146,0.000071912335,0.00007836895,0.00025123585,0.000054487416,0.00022154434,0.00066559075,0.0000014338655],"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":[0.00041850068,0.00016932785,0.0021106037,0.00010382943,0.00007405657,0.00056349335,0.0005899122,0.000058568854,0.42631453,0.000052968102,0.00001832296,0.5695259],"study_design_scores_gemma":[0.0065393276,0.0013494779,0.081518255,0.030584248,0.00012282962,0.0018494623,0.0038696337,0.65423036,0.21560329,0.00030252783,0.0005138216,0.0035167763],"about_ca_topic_score_codex":0.000042254876,"about_ca_topic_score_gemma":0.00017078726,"teacher_disagreement_score":0.65417176,"about_ca_system_score_codex":0.000063486616,"about_ca_system_score_gemma":0.00008609459,"threshold_uncertainty_score":0.73773557},"labels":[],"label_agreement":null},{"id":"W2773782067","doi":"","title":"Chat Disentanglement: Identifying Semantic Reply Relationships with Random Forests and Recurrent Neural Networks","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":33,"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 British Columbia","funders":"","keywords":"Computer science; Thread (computing); Random forest; Recurrent neural network; Classifier (UML); Artificial intelligence; Machine learning; Artificial neural network; Natural language processing; Data mining; Programming language","score_opus":0.06351610469634573,"score_gpt":0.32617992000321583,"score_spread":0.2626638153068701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773782067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2682411,0.003101033,0.7092617,0.013488729,0.0027849087,0.00058711384,0.000011025815,0.0003443387,0.0021800257],"genre_scores_gemma":[0.99642617,0.000024524034,0.0028068232,0.000272959,0.00020552757,0.000017536646,0.00003254463,0.000010796829,0.00020312953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984443,0.000087670705,0.00028968367,0.00047083056,0.00044392346,0.0002636003],"domain_scores_gemma":[0.9986967,0.00007818523,0.0004329815,0.00035947355,0.00033073442,0.000101951395],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004761584,0.00019830311,0.00018293134,0.00012951171,0.0008634407,0.0017601016,0.00068506005,0.000053312764,0.000016520811],"category_scores_gemma":[0.00047748975,0.00015236129,0.00004901228,0.0000807584,0.00009931863,0.0013591386,0.00028297282,0.00053597556,0.000005553384],"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":[0.00052837736,0.00012956125,0.07985589,0.00018361407,0.00014276827,0.00043239666,0.005701865,0.00057408307,0.00059996534,0.07409701,0.00011437325,0.8376401],"study_design_scores_gemma":[0.001048524,0.000038364447,0.060422357,0.0006673621,0.000014050918,0.000062222614,0.0002591027,0.93576014,0.00046361418,0.0009616104,0.000036058544,0.00026660462],"about_ca_topic_score_codex":0.000030734776,"about_ca_topic_score_gemma":0.00010919047,"teacher_disagreement_score":0.935186,"about_ca_system_score_codex":0.0000624452,"about_ca_system_score_gemma":0.00004417979,"threshold_uncertainty_score":0.99927616},"labels":[],"label_agreement":null},{"id":"W2773947245","doi":"","title":"MONPA: Multi-objective Named-entity and Part-of-speech Annotator for Chinese using Recurrent Neural Network","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Named-entity recognition; Sentence; Recurrent neural network; Task (project management); Segmentation; Speech recognition; Part of speech; Word (group theory); Artificial neural network; Named entity; Text segmentation","score_opus":0.05657633475324485,"score_gpt":0.35028846040631406,"score_spread":0.2937121256530692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773947245","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.781981,0.0014997124,0.21271798,0.0008566727,0.0023106288,0.0003244187,0.000021665177,0.00007500403,0.00021291681],"genre_scores_gemma":[0.9008562,0.000010305453,0.09857632,0.0000813035,0.0003900808,0.000012877202,0.0000066672105,0.000009247324,0.00005699383],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861,0.000032772372,0.00031408758,0.00046649808,0.00032456452,0.0002520472],"domain_scores_gemma":[0.99860626,0.000055994056,0.00047738894,0.00032793212,0.00046556623,0.000066867295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025543137,0.00019386975,0.00023903797,0.00009039567,0.00034475187,0.0006022988,0.0007742976,0.000063126005,0.000005267086],"category_scores_gemma":[0.00046761343,0.00015976545,0.000076104756,0.000059711405,0.000089373505,0.0009426964,0.00036027434,0.0002574346,8.220672e-7],"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":[0.00009910355,0.000079864374,0.0052776737,0.000114298135,0.000059978214,0.000040049512,0.0026816453,0.0007066503,0.0055014146,0.006784297,0.000012637859,0.9786424],"study_design_scores_gemma":[0.0005407722,0.000039871833,0.0058004544,0.00034294973,0.000007254977,0.0000213077,0.0000736233,0.9910063,0.00086109946,0.0010880886,0.000028145216,0.00019014733],"about_ca_topic_score_codex":0.000099566205,"about_ca_topic_score_gemma":0.000056772107,"teacher_disagreement_score":0.99029964,"about_ca_system_score_codex":0.00006674939,"about_ca_system_score_gemma":0.000093580726,"threshold_uncertainty_score":0.6515046},"labels":[],"label_agreement":null},{"id":"W2775337853","doi":"","title":"Assessing the Verifiability of Attributions in News Text","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Operationalization; Attribution; Verifiable secret sharing; Computer science; Rank (graph theory); Task (project management); Fidelity; Crowdsourcing; Statement (logic); Authorship attribution; Natural language processing; Information retrieval; Artificial intelligence; Psychology; Social psychology; World Wide Web; Linguistics; Set (abstract data type); Mathematics","score_opus":0.0672499933037815,"score_gpt":0.36785059382849045,"score_spread":0.30060060052470894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775337853","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7132909,0.0005553499,0.2502302,0.01796634,0.0012900664,0.000258022,0.0000075380826,0.00009579695,0.016305752],"genre_scores_gemma":[0.99133587,0.000005889738,0.008307132,0.0001686887,0.00007665266,0.000008249013,0.0000032643313,0.0000039834035,0.000090257185],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876916,0.0000542301,0.00031407998,0.00031153802,0.0003769649,0.0001740078],"domain_scores_gemma":[0.99873513,0.000069930786,0.00032811155,0.0005916645,0.0002459429,0.000029212473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040412796,0.000112977694,0.00014761406,0.00009356025,0.0002401204,0.00095939933,0.0015528253,0.000047500333,0.000022133068],"category_scores_gemma":[0.00071078085,0.00007949237,0.000055942455,0.00007830748,0.00011149828,0.0013471947,0.00033237154,0.00034271207,0.000006046669],"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":[0.000009771631,0.00010051035,0.005885545,0.000039254806,0.00001471899,0.000034399036,0.0023762076,0.00021306225,0.016786572,0.08829049,0.00001600571,0.88623345],"study_design_scores_gemma":[0.00044086835,0.000017422028,0.09466671,0.0005487528,0.000004028092,0.000019173729,0.00093140494,0.88938856,0.0076637724,0.0060157375,0.00008202567,0.0002215488],"about_ca_topic_score_codex":0.000370506,"about_ca_topic_score_gemma":0.00010508467,"teacher_disagreement_score":0.8891755,"about_ca_system_score_codex":0.000095242576,"about_ca_system_score_gemma":0.00017086795,"threshold_uncertainty_score":0.925151},"labels":[],"label_agreement":null},{"id":"W2775747321","doi":"","title":"WiNER: A Wikipedia Annotated Corpus for Named Entity Recognition","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Information retrieval; Artificial intelligence; Quality (philosophy); Named-entity recognition; Simple (philosophy); Training set; Range (aeronautics); Task (project management)","score_opus":0.060187248013458684,"score_gpt":0.3217091971620433,"score_spread":0.2615219491485846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775747321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35993502,0.00069248077,0.6114752,0.011398219,0.006048809,0.0006839986,0.00007335595,0.0005423714,0.009150531],"genre_scores_gemma":[0.95657873,0.000009600278,0.04173307,0.00043374885,0.0003500242,0.00003644488,0.000055189023,0.000010234163,0.0007929472],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863017,0.000022128013,0.00026835073,0.00046320012,0.00037786108,0.00023830756],"domain_scores_gemma":[0.99854845,0.000042024167,0.00037293838,0.00038558073,0.00058492343,0.00006607336],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00022164985,0.00016621593,0.00016382517,0.00013274896,0.00033155867,0.0012157512,0.0010994077,0.00007084821,0.000027240396],"category_scores_gemma":[0.0006368777,0.0001490651,0.000077895675,0.00004713139,0.000054492662,0.0012490853,0.00019895913,0.00025018517,0.000026776193],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004843885,0.00004998727,0.00013882198,0.000038489936,0.000023429388,0.00004119777,0.00087042217,0.000010465869,0.01578257,0.0068292576,0.00010372934,0.9760632],"study_design_scores_gemma":[0.0011182141,0.000058230795,0.0015651092,0.00044137656,0.000011028544,0.000041366664,0.000117519485,0.9737205,0.012409401,0.009639973,0.00049427606,0.000383012],"about_ca_topic_score_codex":0.000084525316,"about_ca_topic_score_gemma":0.00004247102,"teacher_disagreement_score":0.9756802,"about_ca_system_score_codex":0.0000834678,"about_ca_system_score_gemma":0.00012154983,"threshold_uncertainty_score":0.99982107},"labels":[],"label_agreement":null},{"id":"W2963881255","doi":"","title":"Cross-Lingual Sentiment Analysis Without (Good) Translation","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Leverage (statistics); Natural language processing; Sentiment analysis; Artificial intelligence; Machine translation; Word (group theory); Translation (biology); Set (abstract data type); Context (archaeology); Linguistics","score_opus":0.04957342895840701,"score_gpt":0.3699171184644701,"score_spread":0.3203436895060631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963881255","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6986945,0.0015358959,0.24893066,0.006521762,0.0024487039,0.0003180333,0.000018875427,0.00041292023,0.041118614],"genre_scores_gemma":[0.98305166,0.000008349054,0.014630617,0.00020681729,0.00020816537,0.0000070958795,0.000043994067,0.000008618368,0.001834665],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979641,0.000036203874,0.00039170566,0.0005686502,0.00078849477,0.00025087065],"domain_scores_gemma":[0.9984976,0.000027375967,0.0005177418,0.0005318156,0.00034641658,0.00007902432],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00034742866,0.00021089875,0.00027384504,0.0004016816,0.0005206045,0.0030939004,0.0012894612,0.00006718784,0.00023827788],"category_scores_gemma":[0.00008695011,0.00017899444,0.00024615056,0.00020577972,0.000074305404,0.0012900415,0.0001869936,0.00024687496,0.000046130976],"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":[0.000055928067,0.0001665741,0.03933084,0.00002369965,0.0010004485,0.000084663225,0.004305755,0.00071960647,0.016359631,0.011397784,0.000019503088,0.92653555],"study_design_scores_gemma":[0.00065179536,0.000025860225,0.039178245,0.00012947734,0.00010876266,0.000007847169,0.00018948103,0.942728,0.016170396,0.00023800877,0.00021217574,0.0003599933],"about_ca_topic_score_codex":0.000072493065,"about_ca_topic_score_gemma":0.000036381633,"teacher_disagreement_score":0.9420084,"about_ca_system_score_codex":0.00006524924,"about_ca_system_score_gemma":0.00007397828,"threshold_uncertainty_score":0.99794096},"labels":[],"label_agreement":null}]}