{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024094405,0.00034842975,0.9680388,0.00010611767,0.00006866621,0.00009135614,0.00012511578,0.0036116326,0.0035156012],"genre_scores_gemma":[0.24746576,0.00032039563,0.7465414,0.00014260692,0.000067034365,0.00018230868,0.0006952788,0.0010482526,0.0035368926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985215,0.0004960381,0.00011192211,0.00032317307,0.0004087095,0.0001386537],"domain_scores_gemma":[0.9955238,0.002467539,0.0001526054,0.00074126694,0.0010002253,0.000114557624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011897598,0.0015458799,0.00077491975,0.0009082578,0.0006734453,0.0017151721,0.0015983689,0.0017236826,0.00477539],"category_scores_gemma":[0.0073826835,0.0005481722,0.0007531188,0.0012518151,0.0008316542,0.0022309918,0.001337794,0.0015519202,0.0034423347],"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":[0.00091657834,0.00018231024,0.0011499221,0.0004554378,0.00007999012,0.0004687773,0.0013523614,0.038247354,0.1724898,0.018121706,0.0038408826,0.7626949],"study_design_scores_gemma":[0.00014293555,0.0005070817,0.001483224,0.000056867873,0.00018899584,0.0013915533,0.00055310375,0.6521763,0.30290237,0.024560168,0.0158797,0.00015773899],"about_ca_topic_score_codex":0.0027102798,"about_ca_topic_score_gemma":0.005075884,"teacher_disagreement_score":0.00477539,"about_ca_system_score_codex":0.0005516809,"about_ca_system_score_gemma":0.0014685609,"threshold_uncertainty_score":0.015975237},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98340064,0.00036561184,0.0069116508,0.0005919447,0.0001844312,0.0001864117,0.0025135216,0.0001275206,0.005718272],"genre_scores_gemma":[0.9853695,0.00022727289,0.009963064,0.00014752318,0.00026944472,0.00017517024,0.0020435024,0.000046981262,0.0017575081],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979929,0.00093166577,0.0001889443,0.00019447946,0.0005116315,0.00018032492],"domain_scores_gemma":[0.98637277,0.007988187,0.0019851672,0.00027607576,0.0029592786,0.0004185534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033118152,0.00027383887,0.00033855267,0.0034952261,0.0008559614,0.0009251354,0.00019042676,0.00030300458,0.0013987907],"category_scores_gemma":[0.010728126,0.000085685744,0.00025089955,0.0017492883,0.00035185713,0.0008467372,0.00064946106,0.0003622691,0.00044455027],"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":[0.0022076322,0.00045573228,0.33429313,0.002001528,0.00022050219,0.0022079858,0.053809114,0.0015381919,0.18239026,0.003952674,0.02874043,0.38818276],"study_design_scores_gemma":[0.000076161086,0.00073470065,0.803687,0.00056392327,0.00020486195,0.0014171934,0.037609655,0.052415162,0.037168484,0.0054171444,0.06054847,0.00015722073],"about_ca_topic_score_codex":0.0009560575,"about_ca_topic_score_gemma":0.0015089895,"teacher_disagreement_score":0.0034952261,"about_ca_system_score_codex":0.00045093842,"about_ca_system_score_gemma":0.00027430896,"threshold_uncertainty_score":0.017514765},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60745895,0.0022237888,0.38109407,0.0012119131,0.00015506562,0.00011926473,0.00021292365,0.002417459,0.00510664],"genre_scores_gemma":[0.9511302,0.00031211376,0.046720125,0.000079218364,0.00004764641,0.000023620807,0.0002821313,0.00007582788,0.0013290939],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960114,0.0022657567,0.00026205613,0.00057225244,0.0006394,0.00024923027],"domain_scores_gemma":[0.961245,0.03061359,0.0011553549,0.0023454593,0.0039917417,0.0006488019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009898956,0.0012011811,0.00095631904,0.0018476186,0.0008028311,0.0023761482,0.0010719901,0.0021743928,0.001296794],"category_scores_gemma":[0.03698063,0.00047647973,0.00065865036,0.0009928595,0.00087834033,0.006000955,0.002018352,0.0020258296,0.00093815],"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":[0.0027777902,0.0010923271,0.021694468,0.00023536812,0.00030805334,0.00011755108,0.00049930485,0.20308927,0.02212392,0.009571344,0.003492478,0.7349982],"study_design_scores_gemma":[0.000022141185,0.00011178989,0.0022164194,0.000012260452,0.00003473412,0.000023185115,0.000053732034,0.99102634,0.0032434834,0.0030270312,0.00021059767,0.000018194545],"about_ca_topic_score_codex":0.008450241,"about_ca_topic_score_gemma":0.0069870716,"teacher_disagreement_score":0.009898956,"about_ca_system_score_codex":0.0009466435,"about_ca_system_score_gemma":0.0011854555,"threshold_uncertainty_score":0.052351356},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061080754,0.00072685425,0.9904289,0.00014733017,0.000033627588,0.00008182824,0.00023519574,0.0019096876,0.00032845867],"genre_scores_gemma":[0.08466768,0.00066080317,0.9096042,0.00022557919,0.0002150083,0.00028425953,0.0023955528,0.0002963263,0.0016505858],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824667,0.0006375524,0.00016094657,0.0004191165,0.0004422611,0.000093626986],"domain_scores_gemma":[0.99728143,0.0009212206,0.00040974014,0.0004609509,0.00081925176,0.000107287946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026801967,0.0020623412,0.0023717755,0.0035303747,0.00062777504,0.0019789585,0.001811266,0.0013015976,0.0012400233],"category_scores_gemma":[0.004376837,0.00044833997,0.0015158433,0.0032003468,0.00062403985,0.0026772516,0.0012607668,0.0016274469,0.0012005892],"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":[0.00024398853,0.00023608292,0.00090930064,0.0006925449,0.00028247075,0.00026690593,0.0004923813,0.13798851,0.045129973,0.013191303,0.011549634,0.78901696],"study_design_scores_gemma":[0.00003949524,0.00026417803,0.0006525848,0.000028342987,0.0001331239,0.00016423284,0.000103378945,0.9543264,0.020137934,0.016819634,0.00728412,0.000046574725],"about_ca_topic_score_codex":0.0020497835,"about_ca_topic_score_gemma":0.0025055537,"teacher_disagreement_score":0.0035303747,"about_ca_system_score_codex":0.0010362482,"about_ca_system_score_gemma":0.0012381155,"threshold_uncertainty_score":0.014174402},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21906279,0.02058863,0.7394633,0.0018543012,0.00042661373,0.00028650562,0.004654321,0.007838719,0.0058248187],"genre_scores_gemma":[0.79464334,0.0049699764,0.18442899,0.0007007477,0.00045361227,0.00030510864,0.009959215,0.00014144366,0.004397524],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918276,0.00017851911,0.00010815564,0.00024025212,0.00021692741,0.00007340082],"domain_scores_gemma":[0.99838364,0.0007645624,0.00032015433,0.00014270391,0.000347316,0.000041604606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014215918,0.0010867552,0.00088472734,0.0037098993,0.00039580715,0.00093111023,0.0013888314,0.000978357,0.0012309491],"category_scores_gemma":[0.0045152507,0.00032861152,0.0009205429,0.0034242105,0.00030715333,0.0017572724,0.0009218503,0.0007417423,0.0012526535],"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":[0.00058625685,0.000505438,0.01870609,0.0013940653,0.00092066947,0.0012584737,0.00033396264,0.10040699,0.038725924,0.0034029868,0.013557463,0.8202017],"study_design_scores_gemma":[0.000022355993,0.00015078766,0.005765753,0.00008700196,0.00033495334,0.00043878326,0.000087410306,0.97006637,0.0112596955,0.0067847595,0.0049636704,0.00003845241],"about_ca_topic_score_codex":0.0048051714,"about_ca_topic_score_gemma":0.010735867,"teacher_disagreement_score":0.0048051714,"about_ca_system_score_codex":0.00059894816,"about_ca_system_score_gemma":0.0008767934,"threshold_uncertainty_score":0.009554446},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16883063,0.00070425705,0.8211468,0.0004794054,0.0001562678,0.00022400386,0.0011441298,0.0051633674,0.0021511929],"genre_scores_gemma":[0.7638399,0.00017602199,0.22653052,0.00014313462,0.000175316,0.00024840957,0.0038172328,0.00028790112,0.0047815763],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987155,0.00045043134,0.00008588241,0.000409263,0.00018148254,0.00015755407],"domain_scores_gemma":[0.995201,0.0027468617,0.0006579058,0.00052033865,0.0006354248,0.0002384384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003155158,0.0015035019,0.0009468862,0.002752788,0.0007243079,0.0011596942,0.001670173,0.0013238563,0.0016412024],"category_scores_gemma":[0.008988333,0.00044148767,0.0010843405,0.0014214971,0.00047025585,0.0022926398,0.0012473274,0.0022187002,0.0015666836],"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":[0.0009850193,0.0010418622,0.038010642,0.0002991072,0.0003162561,0.00049000996,0.0013736549,0.124744564,0.022228247,0.008482952,0.012373233,0.78965443],"study_design_scores_gemma":[0.000013327517,0.000044923225,0.0016566681,0.000013421482,0.000024421168,0.00003675342,0.00008850621,0.9881421,0.0025801386,0.006482776,0.0009024745,0.000014535975],"about_ca_topic_score_codex":0.005649163,"about_ca_topic_score_gemma":0.011865917,"teacher_disagreement_score":0.005649163,"about_ca_system_score_codex":0.00059253856,"about_ca_system_score_gemma":0.00092974456,"threshold_uncertainty_score":0.01668626},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058952652,0.00084571843,0.8584614,0.00039326033,0.00032002802,0.00045286052,0.005649733,0.07050912,0.004415226],"genre_scores_gemma":[0.33424762,0.00042861243,0.61509806,0.0004161798,0.000110342466,0.00090224086,0.023752686,0.0028991178,0.022145184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998833,0.00026414203,0.00005856735,0.0005419839,0.00017264209,0.00012961136],"domain_scores_gemma":[0.9985983,0.0004584061,0.00011521537,0.00030996744,0.00042801746,0.00009004408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029508406,0.0020527812,0.0011066719,0.0013783835,0.0012530073,0.0011906651,0.0026183284,0.001369752,0.0049904436],"category_scores_gemma":[0.0038896534,0.0007009138,0.0010863815,0.001143375,0.00048573007,0.002639902,0.0024140265,0.0014053817,0.0036925215],"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":[0.0013106938,0.00040657824,0.010049793,0.0008835337,0.0005902103,0.0012380516,0.00079198874,0.08983268,0.064682275,0.006075891,0.07937285,0.74476546],"study_design_scores_gemma":[0.000051939125,0.0001021906,0.00197625,0.00002550663,0.000096425756,0.0001293429,0.000111583824,0.96153873,0.023240266,0.0035782366,0.009084697,0.00006486975],"about_ca_topic_score_codex":0.03145958,"about_ca_topic_score_gemma":0.058632754,"teacher_disagreement_score":0.03145958,"about_ca_system_score_codex":0.0013043004,"about_ca_system_score_gemma":0.0031715382,"threshold_uncertainty_score":0.06255293},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.872023,0.0012054458,0.1108798,0.0010425893,0.00031730175,0.00031500394,0.002546291,0.0008276884,0.010842915],"genre_scores_gemma":[0.9833265,0.00013598689,0.014309974,0.000056206027,0.00013472214,0.000067444664,0.0013345374,0.00006296337,0.0005716559],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9631476,0.017994696,0.0032712552,0.005432263,0.009135879,0.0010183585],"domain_scores_gemma":[0.42670295,0.4742189,0.05132763,0.023384642,0.02229226,0.0020736163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051419243,0.001244263,0.0010034422,0.009632406,0.001718577,0.0059009064,0.0018109616,0.0027889248,0.002760623],"category_scores_gemma":[0.32810107,0.0006121808,0.0009330604,0.006311119,0.0032032414,0.007972193,0.004017776,0.0024939778,0.0013271525],"study_design_candidate":"bench_or_experimental","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":[0.0027225213,0.00093326345,0.58027536,0.0020763527,0.0013595462,0.0014125332,0.0138393035,0.042315785,0.020909652,0.01610883,0.00735031,0.31069657],"study_design_scores_gemma":[0.00022599124,0.0008520853,0.42986313,0.0006541682,0.0005838742,0.0012637051,0.0062380936,0.4427297,0.043637984,0.059361156,0.013965103,0.00062500866],"about_ca_topic_score_codex":0.0050979652,"about_ca_topic_score_gemma":0.0044382443,"teacher_disagreement_score":0.051419243,"about_ca_system_score_codex":0.0015319699,"about_ca_system_score_gemma":0.0014130695,"threshold_uncertainty_score":0.2719342},"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":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07785952,0.0030065887,0.25240153,0.0014517785,0.0022081533,0.0016927245,0.5728976,0.046183966,0.04229807],"genre_scores_gemma":[0.06207394,0.0006622871,0.21829925,0.00033622747,0.00023114007,0.0012813194,0.70595074,0.0022933905,0.008871692],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99783176,0.0005427693,0.00035039993,0.0006255205,0.00052587717,0.00012364316],"domain_scores_gemma":[0.99224234,0.002378907,0.00064644124,0.0015840787,0.0026592081,0.00048912206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019378924,0.0011560015,0.00076066627,0.008492736,0.0013319072,0.0012219516,0.0017273846,0.0012162577,0.008344822],"category_scores_gemma":[0.010094488,0.00063076866,0.00062842004,0.0052913683,0.00052764284,0.0033414438,0.0016657361,0.0016861679,0.0065296474],"study_design_candidate":"bench_or_experimental","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":[0.0005942069,0.000692555,0.010057348,0.0038305,0.00023978816,0.0018390528,0.0015869214,0.006727236,0.039537318,0.013696126,0.62518144,0.2960176],"study_design_scores_gemma":[0.00017721068,0.00023306771,0.020004632,0.00048007496,0.00016009573,0.0017651281,0.00074258517,0.03939936,0.03722933,0.008827311,0.89072305,0.00025813206],"about_ca_topic_score_codex":0.008997921,"about_ca_topic_score_gemma":0.018633133,"teacher_disagreement_score":0.008997921,"about_ca_system_score_codex":0.0005825823,"about_ca_system_score_gemma":0.0021042288,"threshold_uncertainty_score":0.027916253},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18099836,0.000747651,0.77986866,0.0007913908,0.00063475734,0.0003283457,0.005655038,0.0061704563,0.024805298],"genre_scores_gemma":[0.72007424,0.00049929257,0.2536284,0.00046107054,0.0002077219,0.0005860943,0.011376349,0.0012152259,0.011951522],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847835,0.00043365004,0.00016341679,0.00041298597,0.00035054077,0.00016109357],"domain_scores_gemma":[0.9976634,0.00041873843,0.0001923145,0.0007033627,0.00096773915,0.00005452487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018647522,0.0011397488,0.0008205719,0.0016382508,0.0008775954,0.0016872124,0.0005685781,0.0004754127,0.0061437986],"category_scores_gemma":[0.0053933416,0.00036613064,0.0010884652,0.0019123617,0.00045104226,0.0020757301,0.002089122,0.0009883973,0.0062434273],"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":[0.00058344664,0.00040987125,0.021754589,0.0005310194,0.00053780206,0.00060224195,0.0016936586,0.008713324,0.106213465,0.011512832,0.03438369,0.81306404],"study_design_scores_gemma":[0.00014391597,0.0006152017,0.070653014,0.00019168777,0.0006793252,0.001210071,0.0056291698,0.52270615,0.16488086,0.07429024,0.15873803,0.0002623136],"about_ca_topic_score_codex":0.0022019176,"about_ca_topic_score_gemma":0.003603062,"teacher_disagreement_score":0.0061437986,"about_ca_system_score_codex":0.0004742036,"about_ca_system_score_gemma":0.0009861069,"threshold_uncertainty_score":0.020553112},"labels":[],"label_agreement":null}]}