{"meta":{"query_hash":"36dc16fc3b99","filters":{"venue":"Biodiversity Informatics"},"cohort_total":5,"direct_labels_cover":0,"predictions_cover":5,"exported":5,"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/36dc16fc3b99","api":"https://metacan.xera.ac/api/v1/cohort?venue=Biodiversity+Informatics"},"results":[{"id":"W1977869532","doi":"10.17161/bi.v9i1.4611","title":"Character Selection During Interactive Taxonomic Identification: “Best Characters”","year":2014,"lang":"en","type":"article","venue":"Biodiversity Informatics","topic":"Species Distribution and Climate Change","field":"Environmental 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":"Royal Ontario Museum","funders":"","keywords":"Computer science; Categorical variable; Python (programming language); Identification (biology); Software; Data mining; Variety (cybernetics); Selection (genetic algorithm); Transparency (behavior); Task (project management); Range (aeronautics); Machine learning; Information retrieval; Artificial intelligence; Programming language","score_opus":0.015855847025344143,"score_gpt":0.19851256704865106,"score_spread":0.1826567200233069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977869532","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":[0.9845433,5.4789456e-7,0.00024318219,0.00017648093,0.0002327322,0.00011773851,0.0000691144,0.000058073063,0.014558801],"genre_scores_gemma":[0.99901164,0.000016344426,0.000053233434,0.00031978157,0.000030087065,0.000004401756,0.00013858207,0.0000019947588,0.00042395588],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993519,0.000016725106,0.00020400198,0.0000913756,0.00016049617,0.00017551055],"domain_scores_gemma":[0.9995656,0.000012131053,0.00019416024,0.00013429477,0.00001850649,0.000075285396],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00011341682,0.000098714,0.00008818774,0.00004059546,0.00027810512,0.00008993544,0.00017147047,0.000055934495,0.013876677],"category_scores_gemma":[0.000022681244,0.00010310847,0.000049384722,0.00012719053,0.0000758703,0.00086657837,0.00016111387,0.00009540043,0.03131587],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025097156,0.0005773822,0.8625359,0.0001874084,0.00011499766,0.0000027199746,0.013085321,0.000090470814,0.028510137,0.0006297046,0.085880786,0.008134186],"study_design_scores_gemma":[0.0004184896,0.00003498448,0.89086664,0.000006252281,0.000020709997,0.000011383585,0.0035963135,0.0005519094,0.0067879856,0.0000032643095,0.09748579,0.00021627315],"about_ca_topic_score_codex":0.000053388994,"about_ca_topic_score_gemma":0.00002743158,"teacher_disagreement_score":0.028330732,"about_ca_system_score_codex":0.0005844153,"about_ca_system_score_gemma":0.0000028724553,"threshold_uncertainty_score":0.9870248},"labels":[],"label_agreement":null},{"id":"W2005086572","doi":"10.17161/bi.v7i2.3987","title":"Leveraging the fullest potential of scientific collections through digitisation.","year":2010,"lang":"en","type":"article","venue":"Biodiversity Informatics","topic":"Identification and Quantification in Food","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Museum of Nature","funders":"","keywords":"Pooling; Work (physics); Computer science; Data science; Engineering; Artificial intelligence; Mechanical engineering","score_opus":0.018964296006611092,"score_gpt":0.22797600594249373,"score_spread":0.20901170993588264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005086572","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":[0.98847604,0.000008704018,0.0055054645,0.0003688041,0.0010657214,0.00015646199,0.00011504189,0.000015579259,0.004288185],"genre_scores_gemma":[0.9968129,0.0000136410445,0.0011621522,0.00011994603,0.000042467953,0.0000030977517,0.00030466114,0.0000020687323,0.0015390626],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993931,0.000015264226,0.00023257753,0.000084303836,0.00017232055,0.000102423524],"domain_scores_gemma":[0.99912906,0.00000878291,0.00017701168,0.00038156635,0.00027544747,0.00002813121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019787904,0.00006623283,0.00005616273,0.000056264624,0.000816038,0.00016381929,0.00027029123,0.0000741191,0.00007512014],"category_scores_gemma":[0.00007660649,0.000056987188,0.00006792693,0.0002524651,0.00035743008,0.000021523098,0.000096427444,0.00008996614,0.000092807706],"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":[0.00005464471,0.0002927151,0.007495054,0.00009845128,0.00018003068,4.0029877e-7,0.007825377,0.0005045743,0.5102143,0.005460255,0.46667388,0.0012003272],"study_design_scores_gemma":[0.0006071953,0.000054913897,0.008803615,0.000005366994,0.000056882516,0.000029243458,0.006316284,0.0005480181,0.2919268,0.00012103681,0.69128543,0.0002451851],"about_ca_topic_score_codex":0.000016497577,"about_ca_topic_score_gemma":0.000017200657,"teacher_disagreement_score":0.2246116,"about_ca_system_score_codex":0.0000058095784,"about_ca_system_score_gemma":0.00008286918,"threshold_uncertainty_score":0.6276387},"labels":[],"label_agreement":null},{"id":"W3045118647","doi":"10.17161/bi.v15i2.13384","title":"Presence-only and Presence-absence Data for Comparing Species Distribution Modeling Methods","year":2020,"lang":"en","type":"article","venue":"Biodiversity Informatics","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Benchmark (surveying); Computer science; Data mining; Environmental niche modelling; Scale (ratio); Publication; Point (geometry); Grid; Data science; Ecology; Cartography; Geography; Mathematics; Biology","score_opus":0.20712773095229517,"score_gpt":0.31351356255086194,"score_spread":0.10638583159856677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045118647","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":[0.53169465,0.00005125399,0.45491967,0.0019147546,0.00018574506,0.00061017985,0.0057659606,0.00013870055,0.0047190706],"genre_scores_gemma":[0.9628216,0.00047938607,0.030497603,0.0010056379,0.00006109886,0.000006854194,0.0050421283,0.000005879948,0.00007983855],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999101,0.000022800908,0.00022929719,0.00017385576,0.00023282823,0.00024023991],"domain_scores_gemma":[0.999345,0.00007753375,0.00010225892,0.00028423758,0.000023327417,0.00016765227],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00027571846,0.00011886064,0.00015644793,0.000008275379,0.00034174076,0.00012134789,0.00056454004,0.000057047866,0.0009483459],"category_scores_gemma":[0.000309648,0.00011637701,0.00003192342,0.00015954355,0.00018983512,0.00092878874,0.0015090927,0.00008717866,0.00019404491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028828118,0.00014912133,0.38691702,0.00062577246,0.00009126928,0.0000036091567,0.017660754,0.007820056,0.0008204015,0.0028398288,0.5706177,0.012166214],"study_design_scores_gemma":[0.00040115282,0.000044910157,0.009121487,0.000008457262,0.00003171935,0.000003652685,0.014594697,0.84808093,0.00014322714,0.000028165388,0.12732944,0.00021213689],"about_ca_topic_score_codex":0.00006894164,"about_ca_topic_score_gemma":0.00002230307,"teacher_disagreement_score":0.8402609,"about_ca_system_score_codex":0.0001173426,"about_ca_system_score_gemma":0.000010369329,"threshold_uncertainty_score":0.9999649},"labels":[],"label_agreement":null},{"id":"W3165717017","doi":"10.12681/psy_hps.24326","title":"Downloading images from GBIF: Licenses, citation and link rot","year":2020,"lang":"el","type":"article","venue":"Biodiversity Informatics","topic":"Migration and Labor Dynamics","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","score_opus":0.0292736844099697,"score_gpt":0.2360846902158487,"score_spread":0.20681100580587902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165717017","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":[0.96199334,0.00031054107,0.0024486654,0.022991292,0.0005140337,0.00047890696,0.0030906994,0.0001930831,0.007979444],"genre_scores_gemma":[0.9721966,0.0051757772,0.008228714,0.012935854,0.00053928816,0.0000016480413,0.000551204,0.000007532124,0.0003633815],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988679,0.0000697748,0.00032613266,0.000119770164,0.00038563128,0.00023078812],"domain_scores_gemma":[0.99904644,0.0001161953,0.00027950422,0.00010337231,0.00015797504,0.00029653753],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019620715,0.00015645161,0.00019391881,0.00006296356,0.000671183,0.00039372814,0.0002295636,0.00019990918,0.0003530961],"category_scores_gemma":[0.00021616921,0.0001690109,0.000060225346,0.00036427638,0.00021676534,0.0008778597,0.00015070653,0.00020584022,0.0009344962],"study_design_candidate":"qualitative","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":[0.000057251946,0.00003288294,0.02290094,0.00019798518,0.00011453139,0.0000053886292,0.8725875,0.000102358004,0.00010608319,0.0014974932,0.08213365,0.020263907],"study_design_scores_gemma":[0.0018545047,0.00022288071,0.019498346,0.00009799919,0.00035512703,8.774518e-7,0.4081626,0.06005908,0.00020007549,0.00017598447,0.5083982,0.0009743483],"about_ca_topic_score_codex":0.001088652,"about_ca_topic_score_gemma":0.00040712793,"teacher_disagreement_score":0.46442494,"about_ca_system_score_codex":0.00006914706,"about_ca_system_score_gemma":0.00009762947,"threshold_uncertainty_score":0.9998434},"labels":[],"label_agreement":null},{"id":"W4401152488","doi":"10.17161/bi.v18i.22332","title":"Guideline Materials and Documentation for the Genetic Diversity Indicators of the Monitoring Framework for the Kunming-Montreal Global Biodiversity Framework","year":2024,"lang":"en","type":"article","venue":"Biodiversity Informatics","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":13,"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":"Naturvårdsverket","keywords":"Genetic diversity; Biodiversity; Documentation; Diversity (politics); Conservation genetics; Environmental resource management; Population; Guideline; Geography; Environmental planning; Ecology; Computer science; Biology; Political science; Medicine; Environmental science; Environmental health; Genetics","score_opus":0.014897437660557955,"score_gpt":0.24833756048241354,"score_spread":0.23344012282185558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401152488","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":[0.9738341,0.00038599354,0.017935054,0.001575576,0.0013467764,0.001457766,0.003374429,0.0000494491,0.000040865176],"genre_scores_gemma":[0.94994754,0.000983076,0.0481655,0.0007168895,0.000097048774,0.000019952216,0.00003826057,0.0000045156166,0.000027228838],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99864453,0.000033835702,0.00033758953,0.00019990197,0.00048712484,0.0002969961],"domain_scores_gemma":[0.9986816,0.00062884146,0.00025418712,0.0003528035,0.000018707655,0.00006387767],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00044878243,0.00021648516,0.0001864201,0.000032009226,0.0023636962,0.00014073198,0.0008546526,0.00015778397,0.00011836035],"category_scores_gemma":[0.00013764724,0.00013150141,0.00016310818,0.00030357833,0.0009205379,0.0003453477,0.0027400034,0.00014546399,0.00008731006],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000083905456,0.000027937398,0.9683891,0.00011487277,0.00024554107,6.567772e-7,0.0072871554,0.00035348118,0.000017678642,0.00011539618,0.018946452,0.0044178357],"study_design_scores_gemma":[0.00042085946,0.00011443509,0.9729098,0.00005927158,0.00080346176,0.0000030512927,0.011647369,0.0003016664,0.0013059516,0.0012420965,0.010924528,0.00026750786],"about_ca_topic_score_codex":0.0010144274,"about_ca_topic_score_gemma":0.000024872961,"teacher_disagreement_score":0.030230444,"about_ca_system_score_codex":0.00033731823,"about_ca_system_score_gemma":0.000008720879,"threshold_uncertainty_score":0.9989351},"labels":[],"label_agreement":null}]}