{"meta":{"query_hash":"ddb50c5bddf8","filters":{"venue":"Harvard Data Science Review"},"cohort_total":18,"direct_labels_cover":0,"predictions_cover":18,"exported":18,"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/ddb50c5bddf8","api":"https://metacan.xera.ac/api/v1/cohort?venue=Harvard+Data+Science+Review"},"results":[{"id":"W2954249017","doi":"10.1162/99608f92.130f856e","title":"(A) Data in the Life: Authorship Attribution in Lennon-McCartney Songs","year":2019,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Music and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Melody; Chord (peer-to-peer); Authorship attribution; Musical; Lyrics; Period (music)","score_opus":0.16064901104838888,"score_gpt":0.3739416594571497,"score_spread":0.2132926484087608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954249017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033927977,0.16263996,0.5854682,0.18344294,0.005077125,0.009701144,0.0012905997,0.00063861895,0.017813435],"genre_scores_gemma":[0.7618012,0.100764096,0.064660855,0.07015685,0.0004818247,0.00011675514,0.0016653899,0.000042411462,0.0003106362],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99648505,0.0002812791,0.00048363666,0.0012496284,0.000928582,0.0005718398],"domain_scores_gemma":[0.99350375,0.00014666676,0.00019594759,0.005966259,0.00006702739,0.00012037926],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017423613,0.00015684705,0.0003240411,0.000136058,0.0001596961,0.00059840194,0.016028216,0.000042112148,0.000100594545],"category_scores_gemma":[0.001285422,0.000104984574,0.000022345788,0.0036140715,0.00019433607,0.008180785,0.0041334266,0.00034521922,0.0013029446],"study_design_candidate":"not_applicable","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":[0.0000052408955,0.00027869112,0.016357275,0.004283177,0.0000075996904,0.000058421778,0.0011277498,0.000013075343,0.00059947197,0.1006321,0.0897145,0.7869227],"study_design_scores_gemma":[0.00017350716,0.000017887392,0.011478558,0.0037897856,0.000010825255,0.0000319126,0.000031608688,0.030135773,0.000013072506,0.0005885107,0.95346797,0.00026060193],"about_ca_topic_score_codex":0.0000498924,"about_ca_topic_score_gemma":0.000040367897,"teacher_disagreement_score":0.86375344,"about_ca_system_score_codex":0.00005067093,"about_ca_system_score_gemma":0.00091454195,"threshold_uncertainty_score":0.99947464},"labels":[],"label_agreement":null},{"id":"W3172682396","doi":"10.1162/99608f92.8bb28793","title":"The Building Blocks of Statistical Education in the Data Science Ecosystem","year":2021,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Ecosystem; Data science; Environmental science; Environmental resource management; Computer science; Ecology; Biology","score_opus":0.060116750503667465,"score_gpt":0.3821871329555472,"score_spread":0.3220703824518797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172682396","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002442169,0.08978606,0.8661001,0.023134574,0.0032959355,0.0029522874,0.003411936,0.00013537734,0.008741581],"genre_scores_gemma":[0.24951926,0.21865636,0.52242285,0.0073074163,0.00032040934,0.00011801737,0.0014897406,0.000030356116,0.00013559248],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99490845,0.00040524796,0.0007272977,0.0014566889,0.001980061,0.0005222638],"domain_scores_gemma":[0.9847987,0.00075835007,0.00034062145,0.013470192,0.00049268414,0.00013944323],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.024949433,0.00014032984,0.00032335336,0.00014648709,0.0006653403,0.0012337358,0.033719264,0.00001612514,0.00004206243],"category_scores_gemma":[0.008746939,0.00007877979,0.00002584274,0.007435407,0.000992078,0.006885674,0.00936281,0.000196468,0.000117351155],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[8.255843e-7,0.00018249081,0.00047946334,0.00062354567,0.0000100764055,0.000019812629,0.00010035907,0.000005810746,0.0010736185,0.410523,0.03015772,0.55682325],"study_design_scores_gemma":[0.00007308503,0.000016159676,0.002400703,0.0024816259,0.000066182685,0.00018850634,0.0001715993,0.083508685,0.0002873335,0.00092306454,0.90964454,0.00023852712],"about_ca_topic_score_codex":0.000061906896,"about_ca_topic_score_gemma":0.00016805458,"teacher_disagreement_score":0.8794868,"about_ca_system_score_codex":0.000087362256,"about_ca_system_score_gemma":0.0073406287,"threshold_uncertainty_score":0.99980307},"labels":[],"label_agreement":null},{"id":"W4307407759","doi":"10.1162/99608f92.13e1d60e","title":"The Use of Data Science in a National Statistical Office","year":2022,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Data Analysis with R","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":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Data science; Computer science","score_opus":0.25460396327041324,"score_gpt":0.39743772442241093,"score_spread":0.1428337611519977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307407759","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006442209,0.022441976,0.9086236,0.020258568,0.0027294748,0.0043889685,0.03681201,0.00030214735,0.0037990687],"genre_scores_gemma":[0.046147402,0.0802732,0.85730803,0.011594029,0.000106569525,0.00020326891,0.0040956517,0.000036355792,0.0002354696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99278796,0.0003231901,0.0007031405,0.0015483549,0.0040929443,0.0005444046],"domain_scores_gemma":[0.98988223,0.0010199309,0.0003475378,0.008180021,0.0004026288,0.00016766456],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.02344427,0.00012905897,0.00029729027,0.00030945078,0.0010217915,0.000716537,0.03529165,0.000008249886,0.0001816653],"category_scores_gemma":[0.010550813,0.0000927673,0.000021356655,0.009609573,0.0019327779,0.015613647,0.030129781,0.00025248606,0.00016209845],"study_design_candidate":"not_applicable","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":[0.000009065026,0.00025191388,0.00064818334,0.0003156221,0.00001531006,0.00003698084,0.00006783066,0.00020409969,0.00048506865,0.49016273,0.16398786,0.34381536],"study_design_scores_gemma":[0.000057522717,0.00001669986,0.0017414859,0.00013291021,0.000012469283,0.000030525924,0.0000073356596,0.21610163,0.0000049826795,0.00018464295,0.78159475,0.00011504258],"about_ca_topic_score_codex":0.00015186459,"about_ca_topic_score_gemma":0.00007364167,"teacher_disagreement_score":0.6176069,"about_ca_system_score_codex":0.00019780132,"about_ca_system_score_gemma":0.0040950626,"threshold_uncertainty_score":0.99815446},"labels":[],"label_agreement":null},{"id":"W4367177363","doi":"10.1162/99608f92.81172cdd","title":"On “A conversation with Sir David Cox”","year":2023,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Dental Education, Practice, Research","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Conversation; Psychology; Psychoanalysis; Communication","score_opus":0.27616997298837553,"score_gpt":0.5653658902526287,"score_spread":0.2891959172642532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367177363","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20468588,0.020925483,0.0017718358,0.30384338,0.016568221,0.04607164,0.004616072,0.00375353,0.39776397],"genre_scores_gemma":[0.17475466,0.69383353,0.0027852932,0.0787685,0.001189512,0.0023885595,0.010561945,0.00022231229,0.035495684],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99676883,0.00042498187,0.00035000496,0.00064009655,0.0012316109,0.00058448646],"domain_scores_gemma":[0.9966175,0.0006233743,0.00022504826,0.0019474337,0.0003376783,0.00024896947],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009840042,0.00011342495,0.00021294708,0.00019740517,0.0009343359,0.000057329995,0.0015097243,0.00003665907,0.0043402365],"category_scores_gemma":[0.0064574927,0.000081000806,0.000016214715,0.0030871406,0.00035883865,0.0022411607,0.0006784991,0.00043494493,0.08477777],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009179147,0.0002815633,0.05820413,0.011768466,0.00003317377,0.000040346727,0.0024874692,0.0000039059287,0.00046724713,0.021539586,0.76606745,0.13901488],"study_design_scores_gemma":[0.0001997062,0.00005346709,0.050601594,0.0032081197,0.000025780235,0.0000051497473,0.0008535639,0.00028755306,0.000009688245,0.00011162,0.94452196,0.00012182213],"about_ca_topic_score_codex":0.00015606296,"about_ca_topic_score_gemma":0.00001975582,"teacher_disagreement_score":0.67290807,"about_ca_system_score_codex":0.0002642397,"about_ca_system_score_gemma":0.0026754807,"threshold_uncertainty_score":0.99656993},"labels":[],"label_agreement":null},{"id":"W4385297687","doi":"10.1162/99608f92.9ba2bd43","title":"Reinforcing Reproducibility and Replicability: An Introduction","year":2023,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"BIM and Construction Integration","field":"Engineering","cited_by":4,"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 du Québec à Montréal","funders":"National Science Foundation","keywords":"Reproducibility; Computer science; Statistics; Mathematics","score_opus":0.052198051255793125,"score_gpt":0.3084426474261471,"score_spread":0.25624459617035394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385297687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82443535,0.046937056,0.029562812,0.039686035,0.017098814,0.008303,0.0009130643,0.016718874,0.016344981],"genre_scores_gemma":[0.6624819,0.31852967,0.013586145,0.00088194024,0.0023042012,0.00021265254,0.0014482522,0.00007668198,0.000478575],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983351,0.000028778835,0.0002689758,0.0009932687,0.00020557974,0.00016824472],"domain_scores_gemma":[0.9960387,0.000014354924,0.000031202548,0.003752819,0.00007969008,0.0000832699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059181824,0.00007893746,0.00013768152,0.00007464103,0.00014306778,0.00008277071,0.00038521597,0.000020818565,0.0001344396],"category_scores_gemma":[0.0016374008,0.0000680292,0.000012853169,0.0012007658,0.00023017672,0.0022200646,0.00016122288,0.00009765709,0.0001789891],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010355775,0.0000036589229,0.0005533761,0.0013494676,0.0000029659388,4.3640608e-7,0.000031431246,0.000059193717,0.0036376158,0.0045777173,0.012644504,0.9771386],"study_design_scores_gemma":[0.00004748447,0.000025594507,0.0076861177,0.00030060648,0.000030140012,0.00007124254,0.00004674256,0.045159064,0.0011226622,0.00068635674,0.94461876,0.00020521898],"about_ca_topic_score_codex":0.000008917291,"about_ca_topic_score_gemma":0.000005150107,"teacher_disagreement_score":0.97693336,"about_ca_system_score_codex":0.000040237977,"about_ca_system_score_gemma":0.000046239835,"threshold_uncertainty_score":0.27741504},"labels":[],"label_agreement":null},{"id":"W4391378488","doi":"10.1162/99608f92.e3d09bff","title":"Discerning Audiences Through Like Buttons","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Communication in Education and Healthcare","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University","keywords":"Aesthetics; Art; Computer science","score_opus":0.2906058399536966,"score_gpt":0.5471223570002874,"score_spread":0.25651651704659084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391378488","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021749716,0.61977243,0.0021936982,0.07027858,0.00845096,0.00093399803,0.00035110448,0.00048307725,0.29731864],"genre_scores_gemma":[0.07043683,0.8879127,0.012563242,0.017876131,0.00050304894,0.0003129515,0.000545037,0.000037034337,0.0098130535],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982133,0.0001383763,0.00034694944,0.0006476864,0.00033148532,0.00032218645],"domain_scores_gemma":[0.99680346,0.0001775306,0.000076776145,0.0027344825,0.00008644891,0.0001213284],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020383678,0.00010202523,0.00017789066,0.000074769276,0.0004219495,0.00020291762,0.0026694813,0.00002561824,0.012970903],"category_scores_gemma":[0.00030163035,0.000078827914,0.000039255923,0.0015159046,0.00051157747,0.0012196632,0.00065735204,0.00023763944,0.014036351],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.4559154e-7,0.000054588643,0.00052758324,0.0013326843,0.000012241763,0.00000415958,0.0029403092,9.028656e-8,0.000019069326,0.22548681,0.43390182,0.33571988],"study_design_scores_gemma":[0.00001641816,0.000009822579,0.0022829503,0.0023804659,0.000021806192,0.00003231081,0.00055903906,0.000050899263,8.5149054e-7,0.00033303362,0.9942135,0.00009888132],"about_ca_topic_score_codex":0.00015841777,"about_ca_topic_score_gemma":0.0000388489,"teacher_disagreement_score":0.56031173,"about_ca_system_score_codex":0.00006131183,"about_ca_system_score_gemma":0.0005904905,"threshold_uncertainty_score":0.9879314},"labels":[],"label_agreement":null},{"id":"W4391382837","doi":"10.1162/99608f92.d3197524","title":"Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Defense, Military, and Policy Studies","field":"Economics, Econometrics and Finance","cited_by":35,"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 Waterloo","funders":"","keywords":"Differential privacy; Software deployment; Internet privacy; Computer science; Differential (mechanical device); Computer security; Engineering; Data mining; Aerospace engineering; Software engineering","score_opus":0.06757007992727386,"score_gpt":0.32236731613325914,"score_spread":0.25479723620598527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391382837","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010839695,0.95446455,0.00071828155,0.032049328,0.0025524967,0.0009511679,0.004002891,0.00013654122,0.004040786],"genre_scores_gemma":[0.0022819382,0.994312,0.001304868,0.00039496517,0.0005982385,0.00008964306,0.00005515569,0.000018727595,0.00094445585],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99828666,0.00001237846,0.0004459409,0.00080485677,0.00006909014,0.00038106332],"domain_scores_gemma":[0.9988109,0.00008777108,0.00012203733,0.0008187035,0.000035841298,0.0001247613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092981715,0.00017196666,0.00047116497,0.00020236139,0.00037617207,0.00018921675,0.0005610075,0.000024688325,0.0002205096],"category_scores_gemma":[0.00018172397,0.00015198185,0.000083392224,0.00073341455,0.00016902744,0.0008913937,0.00042716766,0.00010636858,0.00038615885],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010607327,0.00011883101,0.01713679,0.022471065,0.00018659334,0.000009245267,0.0007666974,7.461655e-7,0.000021308571,0.14790365,0.5840291,0.2273454],"study_design_scores_gemma":[0.00006605892,0.000017971919,0.0061066393,0.0017048491,0.000040969615,0.000004609405,0.000033224263,0.00046199156,0.0000016866608,0.0014381774,0.98993784,0.00018597838],"about_ca_topic_score_codex":0.00012227839,"about_ca_topic_score_gemma":0.0019493616,"teacher_disagreement_score":0.40590876,"about_ca_system_score_codex":0.00009464934,"about_ca_system_score_gemma":0.000057408306,"threshold_uncertainty_score":0.61976403},"labels":[],"label_agreement":null},{"id":"W4392785285","doi":"10.1162/99608f92.35a2f3ff","title":"The Turing Transformation: Artificial Intelligence, Intelligence Augmentation, and Skill Premiums","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Economic Development and Digital Transformation","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Creative Destruction Lab; University of Toronto","funders":"","keywords":"Transformation (genetics); Turing; Computer science; Artificial intelligence; Cognitive science; Cognitive psychology; Psychology; Programming language","score_opus":0.11922236168275696,"score_gpt":0.30994067499290423,"score_spread":0.19071831331014727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392785285","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042438814,0.25826994,0.3868949,0.016253948,0.004912856,0.0035116272,0.0011857896,0.0004195935,0.32430747],"genre_scores_gemma":[0.48423257,0.51205117,0.0021415516,0.0006997079,0.00012102919,0.00008004207,0.0002710629,0.000018859142,0.00038399076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99834585,0.0000082702,0.0008744707,0.00044155613,0.000080305734,0.00024951957],"domain_scores_gemma":[0.99925804,0.000090249676,0.00010664481,0.0004341835,0.000030916573,0.000079984304],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030949237,0.000118679454,0.0001861299,0.00013166954,0.00035765648,0.0010485006,0.0007738419,0.000023259385,0.0002595436],"category_scores_gemma":[0.00014496775,0.000095457595,0.00003576015,0.00066354766,0.00027716384,0.0051509906,0.00011874936,0.00009867291,0.0023620937],"study_design_candidate":"not_applicable","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":[0.0000011695175,0.000005801409,0.000032236912,0.0004892091,0.0000075499665,3.9205642e-7,0.0004102588,0.000003530376,0.0000014583857,0.6106782,0.00038271243,0.38798746],"study_design_scores_gemma":[0.000019073002,0.000017810647,0.00031628844,0.001137861,0.000012625955,0.000020825713,0.00024063376,0.025228761,0.00027788986,0.097722,0.87472403,0.00028221405],"about_ca_topic_score_codex":0.000008245239,"about_ca_topic_score_gemma":0.000010234359,"teacher_disagreement_score":0.8743413,"about_ca_system_score_codex":0.00007143326,"about_ca_system_score_gemma":0.000085951535,"threshold_uncertainty_score":0.9999885},"labels":[],"label_agreement":null},{"id":"W4394820768","doi":"10.1162/99608f92.d949f941","title":"Government Interventions to Avert Future Catastrophic AI Risks","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Leadership, Behavior, and Decision-Making Studies","field":"Decision Sciences","cited_by":5,"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":"Government (linguistics); Psychological intervention; Business; Risk analysis (engineering); Psychology; Psychiatry","score_opus":0.4249351892336851,"score_gpt":0.5346952383454162,"score_spread":0.1097600491117311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394820768","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004581599,0.5995319,0.13062848,0.19134144,0.03510955,0.0071290936,0.015686318,0.0011391804,0.014852419],"genre_scores_gemma":[0.62765455,0.28131613,0.03701887,0.03668421,0.0040210583,0.00039759508,0.0003613487,0.00017444002,0.012371778],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99077284,0.00020567131,0.0011797858,0.0019210754,0.005302015,0.0006186007],"domain_scores_gemma":[0.99429065,0.0006083571,0.0001810619,0.004132807,0.00038340056,0.0004036959],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012764039,0.00029012424,0.00061179424,0.0002937549,0.00061154633,0.001858449,0.0063734706,0.000049060094,0.002279165],"category_scores_gemma":[0.008162572,0.00018214596,0.00031736432,0.004676575,0.00047981716,0.002885684,0.0032850178,0.00035756003,0.021240357],"study_design_candidate":"not_applicable","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":[0.0000030211681,0.000050670493,0.00019033157,0.0003037854,0.000009374489,0.000046286026,0.00019636308,0.0000030741096,0.000028542541,0.0036489242,0.41962004,0.5758996],"study_design_scores_gemma":[0.00004804217,0.00005980326,0.0025484748,0.006367806,0.0001059273,0.00004270952,0.00059205096,0.00012992401,0.000011803052,0.00079618697,0.9890572,0.00024007921],"about_ca_topic_score_codex":0.000028062288,"about_ca_topic_score_gemma":0.00007693882,"teacher_disagreement_score":0.623073,"about_ca_system_score_codex":0.00024599893,"about_ca_system_score_gemma":0.00039283925,"threshold_uncertainty_score":0.9991777},"labels":[],"label_agreement":null},{"id":"W4398764826","doi":"10.1162/99608f92.f86474d0","title":"A Familiar, Invisible Engine Is Driving the AI Revolution","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Aeronautics; Psychology; Automotive engineering; Engineering","score_opus":0.06234315868469324,"score_gpt":0.3537710257510638,"score_spread":0.2914278670663705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398764826","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009748259,0.08522278,0.8624473,0.044370238,0.0018768648,0.001089006,0.000047845468,0.0006322328,0.0042162086],"genre_scores_gemma":[0.060891006,0.81604576,0.074855015,0.044802792,0.00078441453,0.00025029367,0.0000781731,0.00007508175,0.0022174877],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99648774,0.00012259507,0.000497275,0.001248897,0.0009891655,0.00065434945],"domain_scores_gemma":[0.99518174,0.00020992028,0.000082572886,0.0041378224,0.0002104397,0.00017750564],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006343241,0.00020494383,0.0002574095,0.00018718706,0.000575754,0.0013185566,0.00814305,0.00003507293,0.0002588726],"category_scores_gemma":[0.0012505536,0.00013532938,0.000082089595,0.0053066653,0.0004342335,0.0082205115,0.002836374,0.00033074623,0.0063350517],"study_design_candidate":"not_applicable","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":[3.4111852e-7,0.000026929709,0.000036031826,0.0009802855,0.000010675025,0.000031810872,0.00031810824,0.000017208624,0.001158578,0.1521634,0.18055229,0.6647043],"study_design_scores_gemma":[0.00000842393,0.000017092496,0.00005534928,0.0027518268,0.000017895127,0.000043459113,0.000015534344,0.21894854,0.0009498262,0.0024846096,0.77453864,0.00016882626],"about_ca_topic_score_codex":0.0000924201,"about_ca_topic_score_gemma":0.00002077043,"teacher_disagreement_score":0.78759235,"about_ca_system_score_codex":0.00014911921,"about_ca_system_score_gemma":0.00072117045,"threshold_uncertainty_score":0.9997182},"labels":[],"label_agreement":null},{"id":"W4400451566","doi":"10.1162/99608f92.6a5d7a87","title":"Differentially Private Linear Regression With Linked Data","year":2024,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"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":"Linear regression; Regression; Statistics; Mathematics","score_opus":0.10649766255760484,"score_gpt":0.3586239172977485,"score_spread":0.25212625474014366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400451566","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019601508,0.04428541,0.9041715,0.04418037,0.0013476103,0.0011400251,0.0011404156,0.0030333414,0.00050529576],"genre_scores_gemma":[0.0022475326,0.17843859,0.81683654,0.00091149117,0.00013166941,0.000028908482,0.0013122318,0.000033192908,0.000059834092],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99422777,0.00011661078,0.00053486635,0.0029054298,0.0014820123,0.00073332316],"domain_scores_gemma":[0.9315095,0.00019734532,0.00019023813,0.06775735,0.00012539208,0.00022020323],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0044294316,0.00033933413,0.00046817283,0.00025702515,0.00033111102,0.0012691092,0.19262058,0.00007887654,0.0001139342],"category_scores_gemma":[0.020563308,0.00020912108,0.000035205067,0.003908,0.000784192,0.012375443,0.38205838,0.0005501868,0.00094070885],"study_design_candidate":"not_applicable","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":[0.000003205243,0.000059368722,0.00007034187,0.0025993278,0.00003158922,0.00019184581,0.000010404214,4.186759e-7,0.000967138,0.0081052715,0.47929597,0.50866514],"study_design_scores_gemma":[0.00007399735,0.00004218098,0.0001070108,0.012335232,0.000046401125,0.00010859582,0.0000011279735,0.33103034,0.00021037886,0.0033798108,0.6523378,0.00032715284],"about_ca_topic_score_codex":0.000015412988,"about_ca_topic_score_gemma":0.000006976814,"teacher_disagreement_score":0.508338,"about_ca_system_score_codex":0.00007870257,"about_ca_system_score_gemma":0.00082344166,"threshold_uncertainty_score":0.99983716},"labels":[],"label_agreement":null},{"id":"W4406435392","doi":"10.1162/99608f92.6f5dfc6f","title":"Data Literacy in Industry: High Time to Focus on Operationalization Through Middle Managers","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Dalhousie University","keywords":"Operationalization; Focus (optics); Middle management; Business; Literacy; Psychology; Marketing; Pedagogy","score_opus":0.33414786909287836,"score_gpt":0.49253170853835254,"score_spread":0.15838383944547418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406435392","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001857673,0.016457664,0.21028414,0.41643775,0.004368391,0.015129707,0.03695855,0.0004718614,0.29803428],"genre_scores_gemma":[0.034918036,0.10081,0.15972184,0.5483087,0.00079568656,0.00068925106,0.047949623,0.00012144052,0.106685475],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.994378,0.00039793574,0.0010023107,0.0018352235,0.0020126705,0.0003738707],"domain_scores_gemma":[0.9913082,0.0004960886,0.00019579894,0.0076333047,0.00024116503,0.00012545682],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.015204515,0.00018067964,0.0004279747,0.0004731114,0.00026429398,0.0013613942,0.011712191,0.000057303325,0.0037626894],"category_scores_gemma":[0.013914847,0.00013756812,0.000024729077,0.007387759,0.00020849891,0.009244401,0.007072378,0.00021285507,0.0151168015],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006683358,0.00010180463,0.00006921301,0.00015545244,0.000006479927,0.000007522959,0.00004072033,0.00006766745,0.000011018866,0.098153025,0.6566022,0.24477823],"study_design_scores_gemma":[0.00012135406,0.000017654502,0.00089214137,0.002360533,0.000019450938,8.180194e-7,0.000042647753,0.002341711,0.000012228538,0.0055055707,0.98852944,0.00015641772],"about_ca_topic_score_codex":0.0001754103,"about_ca_topic_score_gemma":0.00008713342,"teacher_disagreement_score":0.3319273,"about_ca_system_score_codex":0.00010733308,"about_ca_system_score_gemma":0.0003832127,"threshold_uncertainty_score":0.9996753},"labels":[],"label_agreement":null},{"id":"W4406971547","doi":"10.1162/99608f92.7fcd521d","title":"What Are Statistical Assumptions About? An Answer From Perspectivism","year":2025,"lang":"en","type":"preprint","venue":"Harvard Data Science Review","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":0,"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":"Perspectivism; Epistemology; Computer science; Econometrics; Mathematics; Philosophy","score_opus":0.5070296381043464,"score_gpt":0.5557659503054858,"score_spread":0.04873631220113939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406971547","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035385747,0.07515152,0.79631984,0.00557072,0.022440298,0.0036309152,0.09285996,0.0006217571,0.0030511091],"genre_scores_gemma":[0.00005539654,0.3435973,0.6507672,0.0012416317,0.00022332347,0.00013181547,0.0033519028,0.00001893852,0.00061247475],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955972,0.0007503927,0.0007100989,0.0016750947,0.0008346872,0.00043255993],"domain_scores_gemma":[0.99090225,0.0026965577,0.0005351464,0.005031225,0.00055005075,0.0002847544],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005328293,0.0003678574,0.00097068795,0.00018401444,0.00029603863,0.0009965481,0.0035624087,0.0001489691,0.0041579884],"category_scores_gemma":[0.030113947,0.00031389573,0.00007876779,0.00048582087,0.00075904053,0.0013073939,0.0029317718,0.0006994878,0.0004925373],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053567674,0.0004730379,0.00013010523,0.009808996,0.0000944532,0.000017387267,0.0007794744,0.0000016714582,0.00001533411,0.37010136,0.47500506,0.14356774],"study_design_scores_gemma":[0.0001269354,0.000018838811,0.0052274577,0.029614529,0.00092664664,0.000008280336,0.0015034744,0.0011879125,0.000014475754,0.44388092,0.51672214,0.0007683837],"about_ca_topic_score_codex":0.000116748284,"about_ca_topic_score_gemma":0.000080737205,"teacher_disagreement_score":0.26844576,"about_ca_system_score_codex":0.00021338207,"about_ca_system_score_gemma":0.0020255863,"threshold_uncertainty_score":0.99993134},"labels":[],"label_agreement":null},{"id":"W4407949312","doi":"10.1162/99608f92.d605e50f","title":"The Problem of Terroir in the Anthropocene","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Global Energy and Sustainability Research","field":"Energy","cited_by":0,"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":"Anthropocene; Terroir; Environmental ethics; Geography; History; Archaeology; Philosophy; Art","score_opus":0.041182875888009673,"score_gpt":0.3828525447909881,"score_spread":0.34166966890297845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407949312","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005815123,0.18795839,0.00042324982,0.1340152,0.00044975316,0.0044283224,0.00015273754,0.000095123934,0.6666621],"genre_scores_gemma":[0.5132052,0.47923654,0.0015952782,0.004597136,0.000045196706,0.00021195957,0.00008251011,0.0000117384725,0.0010144684],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810153,0.00031409206,0.00034358312,0.00033826288,0.00052902196,0.00037351035],"domain_scores_gemma":[0.99750984,0.00025490354,0.00005626055,0.0019744588,0.00017108355,0.000033431184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007776748,0.000079134916,0.00018679719,0.00005218383,0.00034055978,0.00008302239,0.0040717837,0.00002079645,0.000094528885],"category_scores_gemma":[0.0015220846,0.000036971272,0.00003537826,0.002578766,0.0014174745,0.00043036454,0.000873219,0.00014971157,0.00004895069],"study_design_candidate":"not_applicable","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":[0.0000064815513,0.00007355882,0.00058466103,0.0012224455,0.000005510236,0.0000042682946,0.000034226672,0.000034407694,0.000029263267,0.4927525,0.007352023,0.49790064],"study_design_scores_gemma":[0.00005764121,0.000013950398,0.001638666,0.0008121722,0.000008410741,0.000003027475,0.00015905115,0.0002580464,0.000043743967,0.010286156,0.986675,0.000044108132],"about_ca_topic_score_codex":0.0009841471,"about_ca_topic_score_gemma":0.0004812214,"teacher_disagreement_score":0.979323,"about_ca_system_score_codex":0.00006112895,"about_ca_system_score_gemma":0.00062377675,"threshold_uncertainty_score":0.7566455},"labels":[],"label_agreement":null},{"id":"W4409640743","doi":"10.1162/99608f92.abf14c9d","title":"Challenges and Opportunities for Statistics in the Era of Data Science","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","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 Alberta","funders":"","keywords":"Data science; Statistics; Computer science; Mathematics","score_opus":0.47368453054411114,"score_gpt":0.41809491985268776,"score_spread":0.055589610691423375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409640743","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018835623,0.6548253,0.08905501,0.14144138,0.0034422697,0.009623018,0.0120838145,0.00019764176,0.087448],"genre_scores_gemma":[0.02977265,0.95278484,0.007738712,0.008486386,0.000147319,0.00004462032,0.0009802054,0.000008668784,0.000036594265],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982775,0.000012141298,0.0003435151,0.00062484486,0.00047411284,0.00026790664],"domain_scores_gemma":[0.9970082,0.00017613279,0.00017936307,0.0022958715,0.00032967512,0.000010762039],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.008293966,0.00011048444,0.00023835231,0.00019763871,0.0002527042,0.0003439317,0.006092518,0.000015108073,0.00003674283],"category_scores_gemma":[0.002471406,0.00007211018,0.000008522559,0.0012725051,0.0015429605,0.009279613,0.0031642425,0.00009037178,0.00001470591],"study_design_candidate":"not_applicable","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":[0.0000019548763,0.00002461071,0.00005048674,0.0038901549,0.0000015260691,0.0000011562116,0.00001003371,7.922451e-8,0.000018939803,0.28373063,0.009051923,0.7032185],"study_design_scores_gemma":[0.000060862527,0.0000038016703,0.0028443253,0.0031744346,0.00006055666,0.0000025171912,0.00027942524,0.0037103496,0.0000064420983,0.0025255948,0.98722166,0.000110052875],"about_ca_topic_score_codex":0.0000755506,"about_ca_topic_score_gemma":0.00011529047,"teacher_disagreement_score":0.97816974,"about_ca_system_score_codex":0.000008932981,"about_ca_system_score_gemma":0.00036776968,"threshold_uncertainty_score":0.999285},"labels":[],"label_agreement":null},{"id":"W4411542049","doi":"10.1162/99608f92.dc58eb7a","title":"Navigating the Privacy Landscape: Harmonizing Legislative and Public Sector Approaches in the Canadian Context","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Criminal Law and Evidence","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Legislature; Context (archaeology); Public sector; Political science; Public relations; Internet privacy; Public administration; Geography; Computer science; Law; Archaeology","score_opus":0.35686093694706433,"score_gpt":0.4034727452268728,"score_spread":0.046611808279808487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411542049","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022948308,0.16944475,0.00015806484,0.66641945,0.00062598573,0.0041793366,0.0001493271,0.000073297626,0.1360015],"genre_scores_gemma":[0.975378,0.01956181,0.0001636353,0.004750344,0.000051753068,0.00003864554,0.000012128486,0.000002597573,0.000041130468],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99791986,0.00044433528,0.00022636486,0.0004199905,0.0005002242,0.0004892152],"domain_scores_gemma":[0.9984381,0.00050085975,0.000085957516,0.0007567011,0.000084737214,0.00013360195],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.010528211,0.000097795026,0.0001769289,0.00004149961,0.002314687,0.0010141863,0.0028396745,0.000028629242,0.00007005289],"category_scores_gemma":[0.0046419185,0.000054877364,0.000023214348,0.0018464688,0.0013929738,0.0018091031,0.00039472766,0.00036115642,0.000034752506],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016847774,0.00002513708,0.02183512,0.00054202636,0.00001041853,0.00001061011,0.03429788,3.0348832e-7,0.000006795792,0.3372995,0.015133374,0.5908371],"study_design_scores_gemma":[0.000037617014,0.0000041200065,0.004012678,0.0019380389,0.000021025038,0.0000037269951,0.010245635,0.00018479748,0.0000010707764,0.00034897562,0.98311496,0.00008737589],"about_ca_topic_score_codex":0.19449158,"about_ca_topic_score_gemma":0.6467139,"teacher_disagreement_score":0.9679816,"about_ca_system_score_codex":0.000116735246,"about_ca_system_score_gemma":0.0020931074,"threshold_uncertainty_score":0.99898416},"labels":[],"label_agreement":null},{"id":"W4415667311","doi":"10.1162/99608f92.28e9f828","title":"An Undergraduate Course in Causality","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Course (navigation); Set (abstract data type); Causality (physics); Quarter (Canadian coin); Graduate students; Advice (programming)","score_opus":0.383188568202988,"score_gpt":0.5747813044805024,"score_spread":0.19159273627751433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415667311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058721793,0.05276747,0.76457787,0.06835255,0.011137757,0.007415919,0.003621598,0.0010422509,0.08521243],"genre_scores_gemma":[0.016051525,0.17170005,0.80226207,0.0076406715,0.000059552927,0.00009692985,0.00033275757,0.000019052159,0.0018374065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985283,0.00029157754,0.0003182796,0.0004089827,0.00023683633,0.00021600928],"domain_scores_gemma":[0.9973278,0.00064770604,0.00009283228,0.0017556975,0.00010468061,0.00007130247],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0073542823,0.00008454031,0.0002563568,0.00007976666,0.000088113644,0.000067970104,0.0013041021,0.000018354043,0.0001678478],"category_scores_gemma":[0.012078295,0.000067855144,0.000013949565,0.0010362073,0.00029818522,0.00048353823,0.00025290498,0.00009556715,0.00012833644],"study_design_candidate":"theoretical_or_conceptual","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":[0.0000013701952,0.0001795125,0.0011928563,0.0018993741,0.000004645317,0.000003016188,0.0000374683,2.464366e-7,0.00008236063,0.78521866,0.146229,0.06515151],"study_design_scores_gemma":[0.00016004631,0.000015571359,0.011009214,0.0034607032,0.00010942528,0.0000067691403,0.00016548505,0.0005592922,0.00011187844,0.42198458,0.562195,0.00022204996],"about_ca_topic_score_codex":0.000033851928,"about_ca_topic_score_gemma":0.00006966185,"teacher_disagreement_score":0.415966,"about_ca_system_score_codex":0.000055594748,"about_ca_system_score_gemma":0.0008602187,"threshold_uncertainty_score":0.9962434},"labels":[],"label_agreement":null},{"id":"W4415741689","doi":"10.1162/99608f92.dbc60044","title":"AI and Writing in the Straddle Generation","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Cybernetics and Technology in Society","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Column (typography); Straddle; Face (sociological concept); Technical writing; Affect (linguistics)","score_opus":0.1138791503751696,"score_gpt":0.3484377760184191,"score_spread":0.23455862564324947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415741689","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08765728,0.36047152,0.0009847513,0.2072148,0.0022907283,0.0044328687,0.00081163784,0.00032511522,0.3358113],"genre_scores_gemma":[0.803207,0.17027526,0.00050254446,0.025362775,0.00017868644,0.00003767719,0.00009592729,0.0000041700437,0.00033594898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994236,0.000022135131,0.00014079479,0.00019447958,0.000111383124,0.00010761076],"domain_scores_gemma":[0.9994442,0.000027747952,0.000026272835,0.00045993016,0.000033032386,0.000008858086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015585795,0.00004322384,0.0000812977,0.000027586426,0.0003039276,0.0002530451,0.0006048257,0.0000114544555,0.00016632433],"category_scores_gemma":[0.0000918254,0.000027573873,0.000010257751,0.00015224925,0.00057964266,0.00037256177,0.00020930944,0.00009509964,0.000021060658],"study_design_candidate":"not_applicable","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":[5.1518708e-8,0.000010058473,0.00014145151,0.00013481732,0.0000014315491,6.203029e-7,0.00048174246,3.5932008e-8,0.000029763743,0.8844914,0.032581914,0.08212672],"study_design_scores_gemma":[0.00003117379,0.0000044490207,0.00028534,0.0004342552,0.000013060442,0.0000017977311,0.00038907648,0.00066760543,0.0000052490323,0.0013797255,0.9967488,0.000039475788],"about_ca_topic_score_codex":0.000037101367,"about_ca_topic_score_gemma":0.00019633814,"teacher_disagreement_score":0.9641669,"about_ca_system_score_codex":0.000008677883,"about_ca_system_score_gemma":0.000049477512,"threshold_uncertainty_score":0.24401197},"labels":[],"label_agreement":null}]}