{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":14,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":14,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"0d7ccbc5d97c","filters":{"venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing"}},"results":[{"id":"W4306694236","doi":"10.1609/hcomp.v10i1.21986","title":"Eliciting and Learning with Soft Labels from Every Annotator","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Canadian Institute for Advanced Research","keywords":"Computer science; Categorical variable; Crowdsourcing; Artificial intelligence; Machine learning; Robustness (evolution); Generalization; Set (abstract data type); Soft skills; Natural language processing; World Wide Web","authors":[{"name":"Katherine M. Collins","is_ca":false},{"name":"Umang Bhatt","is_ca":false},{"name":"Adrian Weller","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02357610624059404,"gpt":0.240562109562208,"spread":0.216986003321614,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005281129,0.0002109972,0.0002601321,0.0001338691,0.001750912,0.0004836191,0.0004206481,0.00003685605,0.00001742009],"category_scores_gemma":[0.00006479857,0.000174767,0.00004204718,0.0003262098,0.0001334332,0.0003055903,0.0005855365,0.0005419081,0.000001181721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003874742,"about_ca_system_score_gemma":0.00004266134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008521218,"about_ca_topic_score_gemma":0.000002261344,"domain_scores_codex":[0.9984179,0.00006419211,0.000296373,0.0005142028,0.0004467936,0.0002605391],"domain_scores_gemma":[0.9989983,0.0001758271,0.0004121672,0.0001240834,0.0002051952,0.00008438285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000296923,0.0003967533,0.07686459,0.0005467107,0.0003379387,0.00002108297,0.1062719,0.03868141,0.3129994,0.1874026,0.001323573,0.274857],"study_design_scores_gemma":[0.00374205,0.001787675,0.04030524,0.001472341,0.0001374853,0.0002486212,0.02464976,0.8725655,0.01733989,0.03486535,0.001182364,0.001703731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9888698,0.00007159366,0.008353719,0.0005863637,0.00006145684,0.0001742481,0.000002263439,0.0001420648,0.001738503],"genre_scores_gemma":[0.9956958,0.000002750798,0.003735845,0.0002904182,0.00004010077,0.00001573458,0.000001866767,0.00001970468,0.0001978332],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8338841,"threshold_uncertainty_score":0.9995487,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2794325666","doi":"10.1609/hcomp.v5i1.13307","title":"Deja Vu: Characterizing Worker Reliability Using Task Consistency","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Consistency (knowledge bases); Task (project management); Reliability (semiconductor); Metric (unit); Computer science; Context (archaeology); Consistency model; Measure (data warehouse); Reliability engineering; Data mining; Artificial intelligence; Data consistency; Engineering; Geography; Operations management; Database","authors":[{"name":"Alex C. Williams","is_ca":true},{"name":"Joslin Goh","is_ca":true},{"name":"Charlie Willis","is_ca":false},{"name":"Aaron M. Ellison","is_ca":false},{"name":"James H. Brusuelas","is_ca":false},{"name":"Charles C. Davis","is_ca":false},{"name":"Edith Law","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06568918211076574,"gpt":0.3058742671703849,"spread":0.2401850850596192,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008305492,0.0002926506,0.0003927334,0.0001287865,0.002518673,0.001629381,0.001184175,0.0001132082,0.000007448294],"category_scores_gemma":[0.0002876768,0.0002411671,0.0001339439,0.0001489951,0.0004462282,0.0008293572,0.0007230587,0.0003449574,0.000003984014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006278772,"about_ca_system_score_gemma":0.00007633049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007851683,"about_ca_topic_score_gemma":0.000003157505,"domain_scores_codex":[0.9979851,0.00003611805,0.0005246113,0.0006606278,0.0004150496,0.000378512],"domain_scores_gemma":[0.997699,0.00007984375,0.0009906967,0.0005658284,0.0005364556,0.0001282342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009133115,0.0003345876,0.08661412,0.0006413728,0.0001360961,0.000007795934,0.01217517,0.001060286,0.5687669,0.2520036,0.0004277135,0.07774106],"study_design_scores_gemma":[0.00237339,0.0003557845,0.271281,0.004209427,0.0001509469,0.0001597395,0.001410174,0.6205763,0.0525928,0.04481362,0.000458779,0.001617949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9813384,0.00002573892,0.009604414,0.001258225,0.0002887009,0.0002772287,0.000001540363,0.0001203029,0.00708545],"genre_scores_gemma":[0.9935684,0.000005053028,0.005924912,0.0002129295,0.0000830273,0.00000604766,5.868292e-7,0.00002042218,0.0001786765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6195161,"threshold_uncertainty_score":0.9994071,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2793871201","doi":"10.1609/hcomp.v5i1.13309","title":"Lessons from an Online Massive Genomics Computer Game","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Computer science; Crowdsourcing; Casual; Task (project management); Data science; Matching (statistics); Citizen science; Artificial intelligence; Human–computer interaction; World Wide Web; Engineering; Biology","authors":[{"name":"Akash Singh","is_ca":true},{"name":"Faizy Ahsan","is_ca":true},{"name":"Mathieu Blanchette","is_ca":true},{"name":"Jérôme Waldispühl","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09804089691815192,"gpt":0.3325677333469798,"spread":0.2345268364288279,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003084851,0.0002821086,0.000358353,0.0001152897,0.001325282,0.001757203,0.001628228,0.0001096374,0.000007815699],"category_scores_gemma":[0.00005593614,0.0002353697,0.0001002903,0.00008737582,0.0003004663,0.0007428642,0.0007490575,0.0003359806,0.000004747174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004852039,"about_ca_system_score_gemma":0.00005801763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001562306,"about_ca_topic_score_gemma":0.00002416466,"domain_scores_codex":[0.9982433,0.00002954664,0.0004036716,0.0006680756,0.0003437345,0.0003116211],"domain_scores_gemma":[0.9980229,0.00006676024,0.0008071286,0.00054581,0.0004038457,0.0001535749],"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":[0.00008725408,0.0006986912,0.01431994,0.0002077402,0.0002138362,0.00001117556,0.02682967,0.006880809,0.1632877,0.4622735,0.0009460203,0.3242437],"study_design_scores_gemma":[0.001164256,0.0002944004,0.1150519,0.0006281055,0.00004746289,0.0000171852,0.0006985479,0.8322365,0.01167326,0.03740872,0.0001924812,0.0005872165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9583521,0.00001586153,0.0363516,0.003319642,0.0002653085,0.0002041265,0.00001049906,0.0001231324,0.001357687],"genre_scores_gemma":[0.9863022,0.000007808877,0.012935,0.0003857914,0.0002257825,0.000004416277,0.000005557623,0.00002270549,0.0001107383],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8253557,"threshold_uncertainty_score":0.9999748,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403434583","doi":"10.1609/hcomp.v12i1.31597","title":"Disclosures & Disclaimers: Investigating the Impact of Transparency Disclosures and Reliability Disclaimers on Learner-LLM Interactions","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":9,"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":"Transparency (behavior); Reliability (semiconductor); Psychology; Political science; Law; Physics; Thermodynamics","authors":[{"name":"Jessica Y. Bo","is_ca":true},{"name":"Harsh Kumar","is_ca":true},{"name":"Michael Liut","is_ca":true},{"name":"Ashton Anderson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1156158976501775,"gpt":0.3606875602226767,"spread":0.2450716625724992,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004167688,0.0002416331,0.0002476141,0.0001778842,0.0005006985,0.0006816977,0.0003167342,0.00004870429,0.00006683773],"category_scores_gemma":[0.0001955946,0.0001331291,0.000127979,0.0004354201,0.000526506,0.0008675594,0.0001620606,0.0003392922,0.000004976442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002383192,"about_ca_system_score_gemma":0.00002640832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006788652,"about_ca_topic_score_gemma":0.00004852875,"domain_scores_codex":[0.9986944,0.00001373273,0.0004284563,0.0003824699,0.0002911289,0.0001898536],"domain_scores_gemma":[0.9991465,0.000149376,0.000328445,0.0001389438,0.0002143359,0.00002243706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0003511872,0.0008074711,0.3717671,0.005845317,0.0005026588,0.000001193577,0.01787477,0.01289662,0.07571097,0.4376457,0.007586901,0.06901009],"study_design_scores_gemma":[0.0008350008,0.0003457498,0.6827123,0.009096797,0.0005715297,0.0000167487,0.007682757,0.1467169,0.003786623,0.1456315,0.001382342,0.00122172],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9915977,0.00007680026,0.000378124,0.002441439,0.0001368658,0.0002644578,0.0000121042,0.00005971202,0.005032855],"genre_scores_gemma":[0.9995122,0.0000187415,0.00005763273,0.00007131219,0.0001471768,0.00001237865,0.00001203472,0.00002002768,0.000148497],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3109452,"threshold_uncertainty_score":0.6573627,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2999004052","doi":"10.1609/hcomp.v7i1.5274","title":"A Hybrid Approach to Identifying Unknown Unknowns of Predictive Models","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Crowdsourcing; Computer science; Task (project management); Machine learning; Set (abstract data type); Artificial intelligence; Data mining; Engineering","authors":[{"name":"Colin Vandenhof","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04897807387878888,"gpt":0.2707203747712563,"spread":0.2217423008924674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000554946,0.0002500737,0.0004080065,0.000278967,0.000275342,0.0003082728,0.000831425,0.00006314128,0.000003807334],"category_scores_gemma":[0.00004605139,0.0002075955,0.0001167881,0.0004164003,0.0001121103,0.000523778,0.0005135356,0.0002484719,0.000005081024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004459666,"about_ca_system_score_gemma":0.00005393014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002828777,"about_ca_topic_score_gemma":5.550904e-7,"domain_scores_codex":[0.9980239,0.00003031972,0.0005052111,0.0006084478,0.0005256154,0.000306497],"domain_scores_gemma":[0.9984873,0.0000712737,0.0004698553,0.0002723586,0.0005798007,0.000119393],"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":[0.00007731363,0.0003140203,0.002375832,0.0008608889,0.0001124032,5.681299e-7,0.02125082,0.08310567,0.1270773,0.7548857,0.0003834302,0.009555968],"study_design_scores_gemma":[0.0006903652,0.0003023078,0.002925118,0.001002485,0.00003147712,0.00002394307,0.001066362,0.9249316,0.03642786,0.03221711,0.00002587215,0.0003554412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.797131,0.00002175737,0.1778327,0.0001383787,0.0001232302,0.0004779157,0.000002181003,0.00009113792,0.02418166],"genre_scores_gemma":[0.9917678,0.000002920156,0.00770943,0.0000983152,0.00002982548,0.00001339459,0.00000115261,0.0000197298,0.0003574003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.841826,"threshold_uncertainty_score":0.8465498,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2780153469","doi":"10.1609/hcomp.v5i1.13300","title":"Drafty: Enlisting Users To Be Editors Who Maintain Structured Data","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":4,"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":"Brown University","keywords":"Computer science; Construct (python library); Matching (statistics); World Wide Web; User modeling; Information retrieval; Data science; User interface","authors":[{"name":"Shaun Wallace","is_ca":false},{"name":"Lucy Van Kleunen","is_ca":false},{"name":"Marianne Aubin-Le Quere","is_ca":false},{"name":"Abraham Peterkin","is_ca":false},{"name":"Yirui Huang","is_ca":true},{"name":"Jeff Huang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0971098124215099,"gpt":0.3317737254023328,"spread":0.2346639129808229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008830107,0.0002936613,0.0003587267,0.0001700028,0.002090985,0.002083797,0.003069931,0.00009865311,0.000006429315],"category_scores_gemma":[0.0005541915,0.0002459172,0.00006609516,0.0001797295,0.0002380382,0.0008606857,0.002140864,0.0003326489,0.000002804024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004953506,"about_ca_system_score_gemma":0.00006648483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001148702,"about_ca_topic_score_gemma":0.00002341558,"domain_scores_codex":[0.9977656,0.0000225059,0.0004374582,0.0008276774,0.0005442461,0.0004025114],"domain_scores_gemma":[0.9976789,0.00009106446,0.0006886314,0.0009527871,0.0004000427,0.0001886261],"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":[0.0001153748,0.0001799058,0.02480531,0.0006443438,0.0002199701,0.00001156794,0.0297318,0.003177854,0.1056332,0.6976002,0.02774187,0.1101386],"study_design_scores_gemma":[0.00291776,0.0006665873,0.0899237,0.003522997,0.0001571443,0.0000956165,0.005381215,0.7833179,0.03938846,0.06814352,0.004204813,0.00228025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9672478,0.000009778668,0.02098224,0.00593987,0.0008065616,0.0003971173,0.0000104273,0.0001607458,0.004445386],"genre_scores_gemma":[0.9911246,0.000001768649,0.007673555,0.0004996529,0.0004401412,0.000005727239,0.000003284365,0.00002338559,0.0002278789],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7801401,"threshold_uncertainty_score":0.9999993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1605921839","doi":"10.1609/hcomp.v1i1.13112","title":"Reducing Error in Context-Sensitive Crowdsourced Tasks","year":2013,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Luxmux Technology (Canada)","funders":"","keywords":"Computer science; Redundancy (engineering); Crowdsourcing; Task (project management); Workflow; Context (archaeology); Quality (philosophy); Hierarchy; Human–computer interaction; World Wide Web; Database; Engineering","authors":[{"name":"Daniel Haas","is_ca":false},{"name":"Matthew Greenstein","is_ca":false},{"name":"Kainar Kamalov","is_ca":false},{"name":"Adam Marcus","is_ca":false},{"name":"Marek Olszewski","is_ca":false},{"name":"Marc Piette","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0393451378942388,"gpt":0.2767068485752072,"spread":0.2373617106809684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005677857,0.0003313047,0.0004383202,0.0003363161,0.0004894972,0.000691257,0.000675181,0.0001266518,0.00001829854],"category_scores_gemma":[0.0001449315,0.0002758885,0.0001116568,0.0005560155,0.0002931572,0.0006497796,0.0003848062,0.0004608484,0.00001781397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000651181,"about_ca_system_score_gemma":0.00005389344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003682654,"about_ca_topic_score_gemma":0.00001655217,"domain_scores_codex":[0.9977354,0.00005868666,0.0006382219,0.0006814525,0.0004234313,0.0004628457],"domain_scores_gemma":[0.99846,0.0001353948,0.0004712686,0.0002555045,0.0005392829,0.0001385756],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006973859,0.0004046071,0.01614571,0.000482006,0.0001143791,0.000008970163,0.05932482,0.005187707,0.4291258,0.3623907,0.002194715,0.1245509],"study_design_scores_gemma":[0.003425553,0.0005244762,0.1155933,0.003495808,0.00004911379,0.0001393238,0.01304791,0.7161531,0.1073258,0.0385689,0.0001241056,0.001552577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9847385,0.00002766781,0.00478095,0.001787511,0.0001405593,0.0005442469,9.200373e-7,0.0001434975,0.007836189],"genre_scores_gemma":[0.996928,0.000002807045,0.002172676,0.0004439696,0.00005054079,0.0000285177,9.311542e-7,0.00002494821,0.0003475616],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7109655,"threshold_uncertainty_score":0.9999693,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403434584","doi":"10.1609/hcomp.v12i1.31596","title":"“Hi. I’m Molly, Your Virtual Interviewer!” Exploring the Impact of Race and Gender in AI-Powered Virtual Interview Experiences","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"AI in Service Interactions","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lehigh Hanson (Canada)","funders":"","keywords":"Interview; Race (biology); Psychology; Applied psychology; Gender studies; Sociology; Anthropology","authors":[{"name":"Shreyan Biswas","is_ca":false},{"name":"Ji‐Youn Jung","is_ca":false},{"name":"Abhishek Unnam","is_ca":true},{"name":"Kuldeep Yadav","is_ca":true},{"name":"Shreyansh Gupta","is_ca":true},{"name":"Ujwal Gadiraju","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1423396126374964,"gpt":0.371991523183155,"spread":0.2296519105456585,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006009336,0.0002208625,0.0002907877,0.0002480776,0.0001954091,0.000566052,0.0007905887,0.00004525707,0.0000254708],"category_scores_gemma":[0.00006292156,0.0001407803,0.0001391421,0.0004784013,0.0001845572,0.00112484,0.000586458,0.0003563258,0.000002647446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006080847,"about_ca_system_score_gemma":0.00005729906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008482338,"about_ca_topic_score_gemma":0.000006632763,"domain_scores_codex":[0.9985285,0.00005664969,0.0005057772,0.0004086211,0.0002918305,0.0002086681],"domain_scores_gemma":[0.9991354,0.0001639879,0.0002379826,0.0001582021,0.0002458785,0.00005855528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005469171,0.0002023586,0.003229692,0.0005640204,0.0002276397,0.000003788214,0.6672905,0.001993358,0.02220066,0.1984208,0.0005210461,0.1052914],"study_design_scores_gemma":[0.0009451567,0.001490419,0.04003729,0.005358444,0.00007134855,0.0001316097,0.08372224,0.8185149,0.01063858,0.03820734,0.00009665146,0.0007860211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848084,0.0002719521,0.01252649,0.001141473,0.0002873903,0.000223368,0.000001577766,0.00006183698,0.0006775466],"genre_scores_gemma":[0.999423,0.00004885552,0.0002606307,0.0001167702,0.00003445902,0.00004552462,4.325239e-7,0.00001336969,0.00005694157],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8165215,"threshold_uncertainty_score":0.5740852,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2811506820","doi":"10.1609/hcomp.v6i1.13323","title":"Towards Quantifying Behaviour in Social Crowdsourcing Communities","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Open Source Software Innovations","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 Calgary","funders":"","keywords":"Crowdsourcing; Quality (philosophy); Proxy (statistics); Process (computing); Psychology; Computer science; Social psychology; Knowledge management; Applied psychology; Machine learning; World Wide Web","authors":[{"name":"Khobaib Zaamout","is_ca":true},{"name":"Ken Barker","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1231108802447632,"gpt":0.3553618345602627,"spread":0.2322509543154995,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007233112,0.0002132802,0.000281434,0.0003568226,0.00116441,0.0006298592,0.001033593,0.00009210195,0.00001710186],"category_scores_gemma":[0.00006393635,0.0001919107,0.00006496267,0.000800656,0.0003682033,0.0005933004,0.0006275774,0.0003794793,0.000005703395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006309063,"about_ca_system_score_gemma":0.00006187771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002202945,"about_ca_topic_score_gemma":0.00006178843,"domain_scores_codex":[0.99845,0.0000426903,0.0005024121,0.0003059616,0.0003931878,0.0003057393],"domain_scores_gemma":[0.9986303,0.00006987826,0.0004099643,0.000163375,0.000680406,0.00004608255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0000245977,0.0001839774,0.1264966,0.0001421785,0.00003147931,9.562332e-7,0.07895024,0.0001025941,0.01034969,0.7663801,0.0005125633,0.016825],"study_design_scores_gemma":[0.002687341,0.0006829427,0.7324535,0.001973143,0.00005471554,0.00005061889,0.02488008,0.1356659,0.02187951,0.0780561,0.0002161289,0.001400095],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.975329,0.000007498228,0.01472526,0.001433068,0.0001209673,0.0002330201,0.000001754649,0.0001331468,0.00801623],"genre_scores_gemma":[0.9941709,0.000001100662,0.005332465,0.0002830841,0.00009209984,0.00001338264,0.000001442591,0.00001765645,0.0000878781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.688324,"threshold_uncertainty_score":0.895582,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2180780611","doi":"10.1609/hcomp.v3i1.13261","title":"Acquiring Reliable Ratings from the Crowd","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Nautical Research Society","funders":"","keywords":"Crowdsourcing; Computer science; Artificial intelligence; Data science; Machine learning; World Wide Web","authors":[{"name":"Beatrice Valeri","is_ca":false},{"name":"Shady Elbassuoni","is_ca":false},{"name":"Sihem Amer-Yahia","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0737925058077919,"gpt":0.2848671676757621,"spread":0.2110746618679702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000871977,0.000254014,0.0002817416,0.00007827095,0.0007870893,0.0009746325,0.001074147,0.00008391559,0.000006668188],"category_scores_gemma":[0.0002091314,0.0001692457,0.00008893319,0.0003784193,0.0002250593,0.0004807774,0.0005647236,0.0003359666,0.00001058094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005180709,"about_ca_system_score_gemma":0.00007960309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001907574,"about_ca_topic_score_gemma":0.000006741904,"domain_scores_codex":[0.9981419,0.0000368691,0.0004412305,0.0005133926,0.0005423862,0.0003242242],"domain_scores_gemma":[0.9983847,0.0001677813,0.0004604689,0.0003037068,0.0005432197,0.0001401237],"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":[0.0001300345,0.0003031933,0.04188797,0.0002313701,0.0002061816,0.000005944374,0.08021287,0.01089135,0.1317091,0.6536555,0.03056372,0.05020282],"study_design_scores_gemma":[0.003748355,0.0006593438,0.02583159,0.002695708,0.0001352855,0.00008450397,0.01118032,0.7080093,0.08039919,0.162809,0.002892583,0.001554828],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9680927,0.0001097877,0.01631741,0.003391738,0.0002956165,0.0002912967,0.000001559934,0.0001981667,0.01130166],"genre_scores_gemma":[0.9944018,0.000003899736,0.004389767,0.0006757743,0.0001355724,0.00001032395,0.000001225016,0.00001945242,0.0003622579],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.697118,"threshold_uncertainty_score":0.9398404,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388332620","doi":"10.1609/hcomp.v11i1.27544","title":"Informing Users about Data Imputation: Exploring the Design Space for Dealing With Non-Responses","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Innovative Human-Technology Interaction","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Toronto","keywords":"Imputation (statistics); Computer science; Software deployment; Autonomy; Missing data; Information retrieval; Data science; Machine learning","authors":[{"name":"Ananya Bhattacharjee","is_ca":false},{"name":"Haochen Song","is_ca":false},{"name":"Xuening Wu","is_ca":false},{"name":"Justice Tomlinson","is_ca":false},{"name":"Mohi Reza","is_ca":false},{"name":"Akmar Ehsan Chowdhury","is_ca":false},{"name":"Nina Deliu","is_ca":false},{"name":"Thomas Price","is_ca":false},{"name":"Joseph Jay Williams","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2356427033280684,"gpt":0.3595694917627186,"spread":0.1239267884346501,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009810514,0.0001801474,0.0001731064,0.0002479744,0.0009491003,0.000441091,0.001095379,0.00004473283,0.000001935658],"category_scores_gemma":[0.0002069052,0.0001205078,0.00002989789,0.0005300152,0.0001635185,0.001214565,0.0004707079,0.0002300579,0.000003414181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003400448,"about_ca_system_score_gemma":0.00005479786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001471438,"about_ca_topic_score_gemma":0.000003796973,"domain_scores_codex":[0.9987622,0.00001659294,0.0003116842,0.0003883617,0.0002765564,0.0002446077],"domain_scores_gemma":[0.9983287,0.0003902926,0.0004391963,0.0002574474,0.0005566723,0.0000277066],"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":[0.0002231766,0.00003382747,0.001535408,0.0002272429,0.0001301757,0.000001671826,0.01851594,0.009756989,0.02847878,0.8793572,0.0008913186,0.06084833],"study_design_scores_gemma":[0.0008913339,0.0004121855,0.01106735,0.0007717104,0.00003811955,0.00003092286,0.00398624,0.922776,0.04044139,0.01897033,0.000259807,0.0003545373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5819531,0.000005930747,0.4135877,0.003069278,0.000136112,0.0005725428,0.000002424449,0.0002157318,0.000457199],"genre_scores_gemma":[0.9817005,0.000006406209,0.01789543,0.0001440547,0.00004013064,0.00007251481,0.000003704663,0.00001637213,0.000120931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9130191,"threshold_uncertainty_score":0.7299808,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1487101415","doi":"10.1609/hcomp.v2i1.13137","title":"Phylo and Open-Phylo: A Human-Computing Platform for Comparative Genomics","year":2014,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"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":"Genomics; Comparative genomics; Computer science; Open science; Field (mathematics); Open source; Data science; Biology; Genetics; Genome; Gene","authors":[{"name":"Jérôme Waldispühl","is_ca":true},{"name":"Mathieu Blanchette","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3266005297275615,"gpt":0.4420037016325501,"spread":0.1154031719049887,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00398926,0.0002013261,0.000419952,0.00022747,0.001290515,0.002166874,0.001197297,0.00004613593,0.00001327813],"category_scores_gemma":[0.0004268298,0.0001460521,0.0000684851,0.0003180458,0.0002408871,0.0003550378,0.001168047,0.0001433101,0.000004563463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002986935,"about_ca_system_score_gemma":0.00002345699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002684928,"about_ca_topic_score_gemma":0.00001131239,"domain_scores_codex":[0.9977631,0.00003014996,0.0006531448,0.0007517778,0.0005303355,0.0002715242],"domain_scores_gemma":[0.9977813,0.0005610411,0.0007418974,0.0002325715,0.0005826585,0.000100479],"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":[0.0001132786,0.0001761388,0.003657752,0.0001693514,0.00007247081,1.497851e-7,0.01835717,0.002670519,0.02219819,0.8195386,0.009220793,0.1238256],"study_design_scores_gemma":[0.001968934,0.0004346057,0.02294242,0.0003361419,0.00004424961,0.000005586503,0.007554799,0.6743407,0.003253047,0.2854098,0.003265051,0.0004447431],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9651324,0.00001116747,0.01890969,0.0005886302,0.0001659266,0.0005992447,0.000007097677,0.00003508497,0.01455077],"genre_scores_gemma":[0.9955997,7.880431e-7,0.003501575,0.0002099986,0.00007242779,0.00000793297,0.000004100268,0.00001027537,0.0005931499],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6716701,"threshold_uncertainty_score":0.9988689,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403434723","doi":"10.1609/hcomp.v12i1.31600","title":"Unveiling the Inter-Related Preferences of Crowdworkers: Implications for Personalized and Flexible Platform Design","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Digital Marketing and Social Media","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Human–computer interaction; Computer science; World Wide Web","authors":[{"name":"Senjuti Dutta","is_ca":false},{"name":"Rhema Linder","is_ca":false},{"name":"Alex C. Williams","is_ca":false},{"name":"Anastasia Kuzminykh","is_ca":true},{"name":"Scott Ruoti","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1322345241962908,"gpt":0.3694382266520061,"spread":0.2372037024557153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001017446,0.00009227886,0.0001462107,0.00006545638,0.000652873,0.0003593415,0.0001934599,0.00006077478,0.0000107211],"category_scores_gemma":[0.0003652605,0.0000618233,0.00005850013,0.0002183847,0.0005570187,0.0001912853,0.00004659542,0.0001149242,4.39531e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002252632,"about_ca_system_score_gemma":0.0000834265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006077116,"about_ca_topic_score_gemma":0.00001068307,"domain_scores_codex":[0.9992655,0.00002618688,0.0002384602,0.0001780539,0.0001497126,0.0001420755],"domain_scores_gemma":[0.9988865,0.0006260447,0.0001642624,0.00003481015,0.0002457105,0.00004266817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004945714,0.00002892873,0.001451975,0.0002483791,0.00006603396,2.410215e-8,0.0701884,0.00003485188,0.00238902,0.8753148,0.00057069,0.04965742],"study_design_scores_gemma":[0.001035972,0.0004957552,0.01079354,0.004091253,0.000229736,0.000003598491,0.1003215,0.01864835,0.002591707,0.858697,0.002576029,0.0005155615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9623303,0.000304341,0.002658588,0.00376351,0.0001465742,0.0006658201,0.000006862075,0.00009616469,0.0300278],"genre_scores_gemma":[0.9984956,0.00003617599,0.0003557717,0.00002899609,0.00003984033,0.00002741986,0.000001069715,0.000008242107,0.001006927],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04914186,"threshold_uncertainty_score":0.5021437,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1926732392","doi":"10.1609/hcomp.v1i1.13110","title":"TrailView: Combining Gamification and Social Network Voting Mechanisms for Useful Data Collection","year":2013,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Incentive; Voting; Data collection; Computer science; Point (geometry); Competition (biology); Scheme (mathematics); Social network (sociolinguistics); Social worlds; Data science; World Wide Web; Social media; Sociology; Political science; Economics","authors":[{"name":"Michael Weingert","is_ca":true},{"name":"Kate Larson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08141775148202438,"gpt":0.2917844663459198,"spread":0.2103667148638954,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0007941774,0.000201379,0.0002728628,0.0001011911,0.001356622,0.0008226905,0.0005957678,0.00008967461,0.000003279908],"category_scores_gemma":[0.00007621403,0.0001771481,0.00004779817,0.0002699627,0.0001098408,0.0006384506,0.0003910758,0.0001857281,0.000001401141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002817763,"about_ca_system_score_gemma":0.00003140053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002186618,"about_ca_topic_score_gemma":0.000003746527,"domain_scores_codex":[0.998449,0.00003277174,0.0004085016,0.0005670849,0.0002491915,0.0002934211],"domain_scores_gemma":[0.9987201,0.0001418708,0.0004935642,0.0001706066,0.0004147241,0.00005911778],"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":[0.00003063311,0.0001065045,0.002264729,0.0005344041,0.00008356368,1.718719e-7,0.0110133,0.0007175094,0.0609935,0.8580435,0.004472763,0.0617394],"study_design_scores_gemma":[0.0007504976,0.0001584481,0.008174521,0.0003398866,0.00003889187,0.00001449463,0.001038681,0.9384454,0.002013222,0.04864337,0.00007881552,0.0003037846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6311432,0.0000413277,0.3647053,0.002321923,0.0001883373,0.0008173016,0.000002164882,0.0001583612,0.0006221067],"genre_scores_gemma":[0.9803035,0.000004226345,0.01920179,0.0002422403,0.00008338756,0.00003499799,0.000007113802,0.00001822303,0.0001045778],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9377279,"threshold_uncertainty_score":0.9999435,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}