{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":10,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":10,"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":"ab38acd60060","filters":{"venue":"International Joint Conference on Natural Language Processing"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01899128694098449,"gpt":0.2948058488755669,"spread":0.2758145619345824,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002660472,0.0002168559,0.0002795334,0.0005839961,0.0001407142,0.0007994032,0.0009074301,0.00007875854,0.001634636],"category_scores_gemma":[0.0001123829,0.0001661975,0.00022008,0.0005942869,0.00004307992,0.0004474833,0.0002116542,0.000333792,0.0002190846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001096459,"about_ca_system_score_gemma":0.0001003035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002131381,"about_ca_topic_score_gemma":0.0000380582,"domain_scores_codex":[0.9972971,0.00005544717,0.000398249,0.0005560516,0.001377581,0.0003155847],"domain_scores_gemma":[0.9989567,0.00005159233,0.0002149867,0.0003074705,0.0003001091,0.0001690824],"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":[0.00002584226,0.0003948663,0.002774015,0.00002322462,0.001218422,0.0001721993,0.004047784,0.0003516996,0.004753514,0.05357015,0.001396994,0.9312713],"study_design_scores_gemma":[0.0003920713,0.00006090916,0.00473635,0.0001961566,0.00004883133,0.00001169614,0.0005864304,0.9887557,0.004053584,0.0005944218,0.000235247,0.000328621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6260839,0.001849562,0.1692197,0.1588832,0.00360686,0.0008854177,0.00002547229,0.0009467314,0.03849921],"genre_scores_gemma":[0.991815,0.000009622854,0.003702267,0.002551963,0.0001609435,0.00002085566,0.0000526361,0.00000857098,0.001678145],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.988404,"threshold_uncertainty_score":0.999278,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04678864868712887,"gpt":0.357966264190523,"spread":0.3111776155033941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001703651,0.0002389237,0.0001986187,0.0001575026,0.0002387506,0.0005567205,0.0005084418,0.0001473672,0.00002538085],"category_scores_gemma":[0.0002525545,0.0001809115,0.00007191233,0.00007836895,0.0002512358,0.00005448742,0.0002215443,0.0006655907,0.000001433865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006348662,"about_ca_system_score_gemma":0.00008609459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004225488,"about_ca_topic_score_gemma":0.0001707873,"domain_scores_codex":[0.9985216,0.00005457561,0.0002951375,0.0004872652,0.0003380028,0.0003033896],"domain_scores_gemma":[0.9992035,0.000008423438,0.0002225852,0.0002899345,0.0001843337,0.00009121352],"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":[0.0004185007,0.0001693278,0.002110604,0.0001038294,0.00007405657,0.0005634933,0.0005899122,0.00005856885,0.4263145,0.0000529681,0.00001832296,0.5695259],"study_design_scores_gemma":[0.006539328,0.001349478,0.08151826,0.03058425,0.0001228296,0.001849462,0.003869634,0.6542304,0.2156033,0.0003025278,0.0005138216,0.003516776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.988239,0.001759624,0.008103192,0.0007144751,0.0005911473,0.0002293768,0.00001353946,0.00003477706,0.00031488],"genre_scores_gemma":[0.9957625,0.00001231837,0.003052735,0.00008083238,0.0004990441,0.00003408284,0.0001941756,0.0000198967,0.0003444694],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6541718,"threshold_uncertainty_score":0.7377356,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.06018724801345868,"gpt":0.3217091971620433,"spread":0.2615219491485846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002216499,0.0001662159,0.0001638252,0.000132749,0.0003315587,0.001215751,0.001099408,0.00007084821,0.0000272404],"category_scores_gemma":[0.0006368777,0.0001490651,0.00007789567,0.00004713139,0.00005449266,0.001249085,0.0001989591,0.0002501852,0.00002677619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000834678,"about_ca_system_score_gemma":0.0001215498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008452532,"about_ca_topic_score_gemma":0.00004247102,"domain_scores_codex":[0.9986302,0.00002212801,0.0002683507,0.0004632001,0.0003778611,0.0002383076],"domain_scores_gemma":[0.9985484,0.00004202417,0.0003729384,0.0003855807,0.0005849234,0.00006607336],"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":[0.00004843885,0.00004998727,0.000138822,0.00003848994,0.00002342939,0.00004119777,0.0008704222,0.00001046587,0.01578257,0.006829258,0.0001037293,0.9760632],"study_design_scores_gemma":[0.001118214,0.00005823079,0.001565109,0.0004413766,0.00001102854,0.00004136666,0.0001175195,0.9737205,0.0124094,0.009639973,0.0004942761,0.000383012],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.359935,0.0006924808,0.6114752,0.01139822,0.006048809,0.0006839986,0.00007335595,0.0005423714,0.009150531],"genre_scores_gemma":[0.9565787,0.000009600278,0.04173307,0.0004337488,0.0003500242,0.00003644488,0.00005518902,0.00001023416,0.0007929472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9756802,"threshold_uncertainty_score":0.9998211,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06351610469634573,"gpt":0.3261799200032158,"spread":0.2626638153068701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004761584,0.0001983031,0.0001829313,0.0001295117,0.0008634407,0.001760102,0.00068506,0.00005331276,0.00001652081],"category_scores_gemma":[0.0004774898,0.0001523613,0.00004901228,0.0000807584,0.00009931863,0.001359139,0.0002829728,0.0005359756,0.000005553384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000624452,"about_ca_system_score_gemma":0.00004417979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003073478,"about_ca_topic_score_gemma":0.0001091905,"domain_scores_codex":[0.9984443,0.00008767071,0.0002896837,0.0004708306,0.0004439235,0.0002636003],"domain_scores_gemma":[0.9986967,0.00007818523,0.0004329815,0.0003594735,0.0003307344,0.0001019514],"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":[0.0005283774,0.0001295612,0.07985589,0.0001836141,0.0001427683,0.0004323967,0.005701865,0.0005740831,0.0005999653,0.07409701,0.0001143733,0.8376401],"study_design_scores_gemma":[0.001048524,0.00003836445,0.06042236,0.0006673621,0.00001405092,0.00006222261,0.0002591027,0.9357601,0.0004636142,0.0009616104,0.00003605854,0.0002666046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2682411,0.003101033,0.7092617,0.01348873,0.002784909,0.0005871138,0.00001102582,0.0003443387,0.002180026],"genre_scores_gemma":[0.9964262,0.00002452403,0.002806823,0.000272959,0.0002055276,0.00001753665,0.00003254463,0.00001079683,0.0002031295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.935186,"threshold_uncertainty_score":0.9992762,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02833968079378524,"gpt":0.3111720211243554,"spread":0.2828323403305702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001496184,0.0002000225,0.0001483285,0.0002014802,0.0001644538,0.001361609,0.0004334668,0.00007401322,0.00003330427],"category_scores_gemma":[0.0001104333,0.0001697447,0.00004422136,0.0001206145,0.00004751436,0.002215149,0.00008169207,0.0002063894,0.000007195307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009233644,"about_ca_system_score_gemma":0.0000783294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006760581,"about_ca_topic_score_gemma":0.00001562517,"domain_scores_codex":[0.9987131,0.00002789982,0.0002836843,0.0004081634,0.0003430737,0.0002240612],"domain_scores_gemma":[0.9991647,0.000130876,0.0001836178,0.0001219667,0.0003417619,0.00005707993],"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":[0.00001477135,0.0000205822,0.000009821551,0.00004822163,0.0000120124,0.000008011119,0.001676693,0.00001235389,0.1667779,0.01660419,0.00002368877,0.8147917],"study_design_scores_gemma":[0.0005876113,0.0001004308,0.00005304594,0.0002772257,0.000008751598,0.00005233152,0.001781555,0.9094615,0.05677022,0.03051396,0.00002579699,0.0003675582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0474139,0.004268515,0.9428076,0.002857871,0.0003440022,0.0007298377,0.00001028748,0.0005874271,0.0009805585],"genre_scores_gemma":[0.663362,0.000009569244,0.3360689,0.0003517382,0.00006163484,0.00006151719,0.00002500261,0.000009098106,0.00005055283],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9094492,"threshold_uncertainty_score":0.9996751,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03583080388495406,"gpt":0.3049195049577958,"spread":0.2690887010728417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001950475,0.000207695,0.0001624316,0.0001983901,0.0001587904,0.0003694396,0.0004013517,0.00008996203,0.00004328668],"category_scores_gemma":[0.0002082412,0.0001491633,0.00004752387,0.0001145869,0.00005668024,0.001056813,0.000172532,0.0002599893,0.000006968839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001887275,"about_ca_system_score_gemma":0.0001418579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009503811,"about_ca_topic_score_gemma":0.000007282894,"domain_scores_codex":[0.9983022,0.00005747566,0.0003004847,0.0005537341,0.0005487808,0.000237382],"domain_scores_gemma":[0.9989838,0.00008786094,0.0002489709,0.0002250304,0.0003720592,0.00008226778],"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":[0.00005625839,0.00007051471,0.0006215089,0.00004149441,0.00002755263,0.00004378054,0.0009015662,0.001704773,0.2636756,0.01469281,0.000002563792,0.7181616],"study_design_scores_gemma":[0.0005073443,0.00002435548,0.002034055,0.001243367,0.000008239055,0.00001330833,0.0001719121,0.9641856,0.02961582,0.001929439,0.00001858727,0.0002479635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.115165,0.0004405539,0.8816016,0.001773455,0.0006406585,0.0001184599,0.000004859,0.0001287206,0.0001266605],"genre_scores_gemma":[0.858716,0.000009902623,0.1407295,0.0003560815,0.00009630035,0.000008034259,0.000006684616,0.00001074346,0.00006674224],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9624808,"threshold_uncertainty_score":0.6082701,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04957342895840701,"gpt":0.3699171184644701,"spread":0.3203436895060631,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003474287,0.0002108988,0.000273845,0.0004016816,0.0005206045,0.0030939,0.001289461,0.00006718784,0.0002382779],"category_scores_gemma":[0.00008695011,0.0001789944,0.0002461506,0.0002057797,0.0000743054,0.001290041,0.0001869936,0.000246875,0.00004613098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006524924,"about_ca_system_score_gemma":0.00007397828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007249307,"about_ca_topic_score_gemma":0.00003638163,"domain_scores_codex":[0.9979641,0.00003620387,0.0003917057,0.0005686502,0.0007884948,0.0002508707],"domain_scores_gemma":[0.9984976,0.00002737597,0.0005177418,0.0005318156,0.0003464166,0.00007902432],"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":[0.00005592807,0.0001665741,0.03933084,0.00002369965,0.001000448,0.00008466322,0.004305755,0.0007196065,0.01635963,0.01139778,0.00001950309,0.9265355],"study_design_scores_gemma":[0.0006517954,0.00002586022,0.03917824,0.0001294773,0.0001087627,0.000007847169,0.000189481,0.942728,0.0161704,0.0002380088,0.0002121757,0.0003599933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6986945,0.001535896,0.2489307,0.006521762,0.002448704,0.0003180333,0.00001887543,0.0004129202,0.04111861],"genre_scores_gemma":[0.9830517,0.000008349054,0.01463062,0.0002068173,0.0002081654,0.000007095879,0.00004399407,0.000008618368,0.001834665],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9420084,"threshold_uncertainty_score":0.997941,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05657633475324485,"gpt":0.3502884604063141,"spread":0.2937121256530692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002554314,0.0001938698,0.000239038,0.00009039567,0.0003447519,0.0006022988,0.0007742976,0.000063126,0.000005267086],"category_scores_gemma":[0.0004676134,0.0001597654,0.00007610476,0.0000597114,0.00008937351,0.0009426964,0.0003602743,0.0002574346,8.220672e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006674939,"about_ca_system_score_gemma":0.00009358073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000995662,"about_ca_topic_score_gemma":0.00005677211,"domain_scores_codex":[0.99861,0.00003277237,0.0003140876,0.0004664981,0.0003245645,0.0002520472],"domain_scores_gemma":[0.9986063,0.00005599406,0.0004773889,0.0003279321,0.0004655662,0.00006686729],"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":[0.00009910355,0.00007986437,0.005277674,0.0001142981,0.00005997821,0.00004004951,0.002681645,0.0007066503,0.005501415,0.006784297,0.00001263786,0.9786424],"study_design_scores_gemma":[0.0005407722,0.00003987183,0.005800454,0.0003429497,0.000007254977,0.0000213077,0.0000736233,0.9910063,0.0008610995,0.001088089,0.00002814522,0.0001901473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.781981,0.001499712,0.212718,0.0008566727,0.002310629,0.0003244187,0.00002166518,0.00007500403,0.0002129168],"genre_scores_gemma":[0.9008562,0.00001030545,0.09857632,0.0000813035,0.0003900808,0.0000128772,0.000006667211,0.000009247324,0.00005699383],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9902996,"threshold_uncertainty_score":0.6515046,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0672499933037815,"gpt":0.3678505938284904,"spread":0.3006006005247089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000404128,0.0001129777,0.0001476141,0.00009356025,0.0002401204,0.0009593993,0.001552825,0.00004750033,0.00002213307],"category_scores_gemma":[0.0007107808,0.00007949237,0.00005594246,0.00007830748,0.0001114983,0.001347195,0.0003323715,0.0003427121,0.000006046669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009524258,"about_ca_system_score_gemma":0.0001708679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000370506,"about_ca_topic_score_gemma":0.0001050847,"domain_scores_codex":[0.9987692,0.0000542301,0.00031408,0.000311538,0.0003769649,0.0001740078],"domain_scores_gemma":[0.9987351,0.00006993079,0.0003281115,0.0005916645,0.0002459429,0.00002921247],"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":[0.000009771631,0.0001005103,0.005885545,0.00003925481,0.00001471899,0.00003439904,0.002376208,0.0002130622,0.01678657,0.08829049,0.00001600571,0.8862334],"study_design_scores_gemma":[0.0004408683,0.00001742203,0.09466671,0.0005487528,0.000004028092,0.00001917373,0.0009314049,0.8893886,0.007663772,0.006015738,0.00008202567,0.0002215488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7132909,0.0005553499,0.2502302,0.01796634,0.001290066,0.000258022,0.000007538083,0.00009579695,0.01630575],"genre_scores_gemma":[0.9913359,0.000005889738,0.008307132,0.0001686887,0.00007665266,0.000008249013,0.000003264331,0.000003983404,0.00009025718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8891755,"threshold_uncertainty_score":0.925151,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03193183759763282,"gpt":0.3179565227045993,"spread":0.2860246851069665,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005020559,0.0001309813,0.0002107548,0.0001242961,0.00005902496,0.0001637611,0.0004475086,0.0000390378,0.00001837378],"category_scores_gemma":[0.000324749,0.00008712678,0.00005475741,0.00008584411,0.00004876279,0.0003749406,0.0001105333,0.0001508767,8.471447e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006768276,"about_ca_system_score_gemma":0.0001036348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009154766,"about_ca_topic_score_gemma":0.00000419711,"domain_scores_codex":[0.9988534,0.0001073388,0.0002812892,0.0002595735,0.0003634409,0.0001349896],"domain_scores_gemma":[0.9984531,0.0007399524,0.0002670074,0.0001968243,0.0003162523,0.00002688775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003912124,0.0001966453,0.001291469,0.001153254,0.000137336,0.000009961946,0.001849885,0.001139092,0.2636479,0.4208487,0.000002434406,0.3096842],"study_design_scores_gemma":[0.0002689259,0.00005041798,0.008795988,0.00129789,0.000009659388,0.00001100496,0.0001758786,0.9667839,0.00918031,0.01333248,1.054244e-7,0.0000934053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.71617,0.0001053898,0.2819833,0.0003480019,0.000169476,0.0003546412,0.000002303814,0.00002754152,0.0008392663],"genre_scores_gemma":[0.9745285,0.000001520806,0.02531886,0.00007065171,0.0000205659,0.00003469732,0.000001930386,0.000007222939,0.00001606235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9656448,"threshold_uncertainty_score":0.3552927,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}