{"meta":{"query_hash":"d548b861c9c0","filters":{"venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"},"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/d548b861c9c0","api":"https://metacan.xera.ac/api/v1/cohort?venue=Proceedings+of+the+28th+ACM+SIGKDD+Conference+on+Knowledge+Discovery+and+Data+Mining"},"results":[{"id":"W3205467272","doi":"10.1145/3534678.3539077","title":"TAG: Toward Accurate Social Media Content Tagging with a Concept Graph","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","topic":"Topic Modeling","field":"Computer Science","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":"Université de Montréal; University of Alberta","funders":"","keywords":"Computer science; Social media; Conceptualization; Graph; User-generated content; Natural language processing; Artificial intelligence; Information retrieval; World Wide Web; Theoretical computer science","score_opus":0.15618565245343002,"score_gpt":0.2986985138738367,"score_spread":0.1425128614204067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205467272","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":[0.9733376,0.0005311041,0.014055859,0.004667535,0.0009312686,0.0005749867,0.00032741632,0.00016801564,0.005406218],"genre_scores_gemma":[0.9956607,0.000019471037,0.0037448506,0.00023172058,0.00010926013,0.000047018184,0.000019944222,0.000015540047,0.00015148942],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978117,0.00004024619,0.00037891697,0.00086027203,0.000504477,0.00040439103],"domain_scores_gemma":[0.99830425,0.0002663918,0.0004173691,0.00071280345,0.00020892521,0.00009026057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006457295,0.00027165358,0.000372313,0.00012589445,0.00064981554,0.00049038854,0.004764075,0.000047141133,0.000014428023],"category_scores_gemma":[0.00044589385,0.0001981478,0.000059565347,0.00047151875,0.00023872817,0.0019677193,0.006575915,0.00039694912,0.0000011123353],"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":[0.00039621454,0.0003861762,0.0062284553,0.0003108268,0.00022593452,0.000010576456,0.09821959,0.00005983399,0.0070219543,0.790668,0.0030750704,0.09339735],"study_design_scores_gemma":[0.018314162,0.003457018,0.021975124,0.0045807036,0.00095871044,0.000490806,0.35712987,0.44971672,0.03684187,0.08788138,0.010849801,0.0078038555],"about_ca_topic_score_codex":0.000014449574,"about_ca_topic_score_gemma":0.0000077578625,"teacher_disagreement_score":0.7027866,"about_ca_system_score_codex":0.000043116503,"about_ca_system_score_gemma":0.00024129324,"threshold_uncertainty_score":0.88529164},"labels":[],"label_agreement":null},{"id":"W4290875536","doi":"10.1145/3534678.3539219","title":"Towards Reliable Detection of Dielectric Hotspots in Thermal Images of the Underground Distribution Network","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","topic":"Thermography and Photoacoustic Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hydro-Québec","funders":"","keywords":"Hotspot (geology); Software deployment; Computer science; Truck; Segmentation; Visual inspection; Artificial intelligence; Image segmentation; Artificial neural network; Real-time computing; Data mining; Computer vision; Engineering; Geology; Automotive engineering","score_opus":0.023006118105986215,"score_gpt":0.24203993216429306,"score_spread":0.21903381405830685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290875536","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":[0.9959124,0.0006576661,0.0003072583,0.000025987194,0.00019573611,0.00022994557,0.00055543846,0.00003303123,0.002082568],"genre_scores_gemma":[0.99969137,0.000117478834,0.000069242305,0.0000046290984,0.000027817408,0.000029315062,0.000016288006,0.000012898456,0.000030949726],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991076,0.000022912094,0.00029473216,0.00020867326,0.00017130953,0.00019477264],"domain_scores_gemma":[0.9992758,0.000102740145,0.00018709534,0.00035310685,0.00006251804,0.000018707327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048987445,0.00014412693,0.00022524851,0.00006891524,0.0001426423,0.000032561336,0.0009988003,0.00005299552,0.00000701554],"category_scores_gemma":[0.00014608182,0.00010418165,0.000055160323,0.00073419366,0.00011970513,0.00035392816,0.0007532885,0.00027944567,3.3829547e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008561578,0.00038439324,0.035897918,0.0013635032,0.00019473913,6.1641015e-7,0.0032999066,0.0017172922,0.8829494,0.015671907,0.0012831166,0.056381036],"study_design_scores_gemma":[0.0010528066,0.00078236917,0.24401653,0.0015892857,0.00025823503,0.000014919533,0.0042524096,0.031684186,0.6975921,0.017746119,0.00033046538,0.0006806063],"about_ca_topic_score_codex":0.000045845543,"about_ca_topic_score_gemma":0.00001150437,"teacher_disagreement_score":0.2081186,"about_ca_system_score_codex":0.000038196304,"about_ca_system_score_gemma":0.00004909377,"threshold_uncertainty_score":0.42484045},"labels":[],"label_agreement":null},{"id":"W4290876096","doi":"10.1145/3534678.3542609","title":"Graph Neural Networks: Foundation, Frontiers and Applications","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":199,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Artificial neural network; Graph; Data science; Machine learning; Theoretical computer science","score_opus":0.03770490372849548,"score_gpt":0.27829855517463364,"score_spread":0.24059365144613817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290876096","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":[0.4039814,0.006861685,0.5699207,0.005549035,0.0027422858,0.0028350272,0.00029264353,0.00045902788,0.0073581715],"genre_scores_gemma":[0.99256665,0.00018623333,0.00661786,0.00019799535,0.00008905234,0.000116680116,0.000030539857,0.0000131403995,0.00018187506],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984468,0.00002807363,0.00028219097,0.0007437796,0.00021313205,0.00028599697],"domain_scores_gemma":[0.9985559,0.00016331916,0.00029083926,0.0007919492,0.00011348399,0.00008451331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035552072,0.00020327138,0.00022736564,0.00012075591,0.0007946666,0.00038244147,0.0032449898,0.000036113695,0.0000032221083],"category_scores_gemma":[0.00012061588,0.0001678639,0.000038678318,0.000754197,0.00024800867,0.002169034,0.0055256393,0.00031560534,3.6303064e-7],"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":[0.00014982185,0.00025044254,0.035226736,0.00014099709,0.000104630184,0.0000012334389,0.0021363636,0.00086405023,0.0006801515,0.5683152,0.009062334,0.383068],"study_design_scores_gemma":[0.0011523325,0.0004309291,0.006649479,0.00016976219,0.00010622679,0.00006651128,0.0040522376,0.8650205,0.00026390975,0.114322364,0.0068386868,0.00092704885],"about_ca_topic_score_codex":0.0000027301112,"about_ca_topic_score_gemma":0.0000026618657,"teacher_disagreement_score":0.8641565,"about_ca_system_score_codex":0.000018283845,"about_ca_system_score_gemma":0.000044535765,"threshold_uncertainty_score":0.68873143},"labels":[],"label_agreement":null},{"id":"W4290944545","doi":"10.1145/3534678.3542675","title":"Automatic Phenotyping by a Seed-guided Topic Model","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Inference; Computer science; Topic model; Machine learning; Artificial intelligence; Bayesian inference; Source code; Prior probability; Vocabulary; Natural language processing; Bayesian probability; Data science","score_opus":0.08150570998099894,"score_gpt":0.3294082098277484,"score_spread":0.24790249984674945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290944545","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":[0.98037004,0.00059046317,0.0054289685,0.0039904383,0.00046964418,0.0005035229,0.00020221986,0.0001928634,0.008251806],"genre_scores_gemma":[0.9896294,0.000019904077,0.008876101,0.00034991524,0.00004172314,0.000053196116,0.000025993882,0.00001765785,0.0009861228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786836,0.000060499453,0.00043502633,0.00081640476,0.00042968395,0.00039001653],"domain_scores_gemma":[0.9979837,0.00023880258,0.00038103195,0.00115592,0.00013978896,0.0001007443],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0009157613,0.0002481511,0.00032812424,0.00011563373,0.0006024899,0.00038712897,0.005638235,0.000051937626,0.000021600326],"category_scores_gemma":[0.00088765536,0.00020438606,0.000049916187,0.00045980938,0.00009724033,0.0014622323,0.008747732,0.00050718925,0.0000027151066],"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":[0.00010323004,0.00068212627,0.0597103,0.0024635952,0.00016687954,0.0000034640755,0.043198407,0.0006056217,0.011019327,0.63988054,0.02771922,0.21444727],"study_design_scores_gemma":[0.00034772983,0.00011091612,0.0009716559,0.00026760658,0.000021021086,0.000017552838,0.001086289,0.9880689,0.00044988212,0.007786026,0.00058856444,0.000283906],"about_ca_topic_score_codex":0.000031779877,"about_ca_topic_score_gemma":0.0000033650192,"teacher_disagreement_score":0.98746324,"about_ca_system_score_codex":0.00006807524,"about_ca_system_score_gemma":0.00028418878,"threshold_uncertainty_score":0.99974173},"labels":[],"label_agreement":null},{"id":"W4290948538","doi":"10.1145/3534678.3542907","title":"Deep Learning on Graphs","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","topic":"Advanced Graph Neural Networks","field":"Computer Science","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":"Deep learning; Computer science; Artificial intelligence; Data science; Intersection (aeronautics); Deep neural networks; Machine learning; Engineering","score_opus":0.050789844208719355,"score_gpt":0.28848830853912777,"score_spread":0.23769846433040842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290948538","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":[0.9681902,0.00093416165,0.0040797717,0.0015768544,0.00122468,0.00060298765,0.00006250733,0.0002602926,0.023068558],"genre_scores_gemma":[0.9962881,0.000096163596,0.002745111,0.00021415522,0.000047837715,0.000035682893,0.000013945625,0.000018021157,0.00054095953],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790424,0.000050475348,0.0003105851,0.00091488205,0.00041891995,0.00040091012],"domain_scores_gemma":[0.9981283,0.00037300843,0.00035016116,0.00094956165,0.00010770721,0.00009127121],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005463674,0.0002692851,0.000289049,0.00017447352,0.0008377884,0.00032608787,0.0053932727,0.000046463752,0.000011733045],"category_scores_gemma":[0.0005332015,0.00021131472,0.00007194909,0.00082234177,0.0001666027,0.0017770628,0.007914104,0.00069166016,0.0000034103048],"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":[0.00024715072,0.00033164135,0.01362825,0.0001221027,0.00007327202,0.000005195599,0.00437248,0.0006036328,0.003937054,0.80721694,0.0020002525,0.16746204],"study_design_scores_gemma":[0.0040666386,0.0051589347,0.018756185,0.0018653955,0.00020268177,0.00018982546,0.016197518,0.6671642,0.012131055,0.25552773,0.0153732095,0.0033666329],"about_ca_topic_score_codex":0.0000026085877,"about_ca_topic_score_gemma":0.0000025535307,"teacher_disagreement_score":0.6665606,"about_ca_system_score_codex":0.000028666907,"about_ca_system_score_gemma":0.000057019966,"threshold_uncertainty_score":0.999988},"labels":[],"label_agreement":null}]}