{"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10890982,0.0025597783,0.79545134,0.0014088633,0.0004754209,0.0009778802,0.051520724,0.029966395,0.008729776],"genre_scores_gemma":[0.22059968,0.00067170535,0.6836305,0.0007449963,0.00012258401,0.0006615438,0.08854976,0.0009531633,0.004066143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849606,0.00033166338,0.00010518937,0.0006089804,0.00036023185,0.00009790636],"domain_scores_gemma":[0.9973605,0.0012377703,0.00031932123,0.00048662935,0.00048884226,0.0001068275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013869064,0.0015105853,0.00063718425,0.009160057,0.00090662757,0.001462023,0.0020775837,0.002080533,0.0021815223],"category_scores_gemma":[0.0074954336,0.00042840914,0.0013809202,0.0056297313,0.0007951894,0.005537635,0.0021869089,0.0016708871,0.0026676739],"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":[0.0008368722,0.0009564028,0.028063929,0.0022270638,0.0004727228,0.0010280022,0.0018259699,0.04409645,0.03215746,0.05827442,0.1468467,0.6832141],"study_design_scores_gemma":[0.00016135233,0.00023702063,0.00931131,0.00022507318,0.00020217572,0.00084494625,0.0013315233,0.7323746,0.024853904,0.10157284,0.12877432,0.00011090472],"about_ca_topic_score_codex":0.012774567,"about_ca_topic_score_gemma":0.022774756,"teacher_disagreement_score":0.012774567,"about_ca_system_score_codex":0.0015409867,"about_ca_system_score_gemma":0.0017288564,"threshold_uncertainty_score":0.0254004},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39154416,0.0009934551,0.59450287,0.00030706846,0.000117375814,0.00015067817,0.0012905265,0.0066451393,0.004448605],"genre_scores_gemma":[0.8009419,0.000444372,0.19203942,0.00012748541,0.00007466296,0.000051185965,0.0021930228,0.00021477937,0.0039131786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997249,0.00003200368,0.000007654149,0.000084057065,0.00008665017,0.00006477067],"domain_scores_gemma":[0.99957806,0.000064240085,0.000059660317,0.000053641797,0.00020671243,0.000037576727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035983746,0.00087800313,0.0004863395,0.0017074643,0.00022708601,0.00077050057,0.0007251491,0.00068708527,0.00066491606],"category_scores_gemma":[0.0010945899,0.0002743754,0.00034288442,0.0007001564,0.0002901683,0.00052170985,0.000605027,0.00066275237,0.0006626813],"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":[0.00066237885,0.00021597683,0.010270313,0.00026417454,0.000107465545,0.00047127003,0.00023435769,0.070833065,0.33701086,0.00091383955,0.009333629,0.5696827],"study_design_scores_gemma":[0.00001563096,0.000091267626,0.019147133,0.000025102285,0.00003666491,0.0002606057,0.00012986289,0.9064803,0.069883205,0.0008981204,0.003008816,0.000023264889],"about_ca_topic_score_codex":0.012151176,"about_ca_topic_score_gemma":0.022054324,"teacher_disagreement_score":0.012151176,"about_ca_system_score_codex":0.0005340819,"about_ca_system_score_gemma":0.00066755083,"threshold_uncertainty_score":0.024160922},"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":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008304042,0.4394355,0.40634143,0.03125509,0.0040754233,0.0001582559,0.0013482685,0.0015304219,0.10755157],"genre_scores_gemma":[0.19264308,0.58239025,0.17530632,0.005100641,0.007076719,0.00037423792,0.0025094387,0.0005347563,0.03406468],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994634,0.00013657825,0.00003264585,0.00012295131,0.00020191116,0.000042517833],"domain_scores_gemma":[0.99910754,0.0005007222,0.000042859665,0.00006450537,0.00022529493,0.000059040558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077934045,0.00092687656,0.0005567993,0.001424007,0.00040468283,0.002002665,0.0009416802,0.00174903,0.0048781736],"category_scores_gemma":[0.0027596373,0.0004985209,0.00047070684,0.0019939828,0.0013141262,0.0039170147,0.0011150239,0.0034534775,0.0017313962],"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":[0.0000436012,0.000052295003,0.0009740291,0.0015790843,0.00004933375,0.00019993607,0.00019019358,0.026445657,0.0012031487,0.44158992,0.071672924,0.45599994],"study_design_scores_gemma":[0.000008846777,0.000040553998,0.0007031506,0.00078060775,0.000024557186,0.00042851106,0.000100832236,0.0670904,0.00091420923,0.65346783,0.27639982,0.000040646923],"about_ca_topic_score_codex":0.0031314567,"about_ca_topic_score_gemma":0.0025536036,"teacher_disagreement_score":0.0048781736,"about_ca_system_score_codex":0.0016855554,"about_ca_system_score_gemma":0.0010192824,"threshold_uncertainty_score":0.016319096},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040883042,0.0007483593,0.9492942,0.0008181927,0.00006868021,0.00016627485,0.004075778,0.0030767175,0.00086883997],"genre_scores_gemma":[0.43808848,0.00087730243,0.53056467,0.0006769002,0.0002986286,0.0005809713,0.024640754,0.00083134236,0.0034408793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980165,0.00074398314,0.00012001474,0.0007616094,0.00021253158,0.00014539479],"domain_scores_gemma":[0.9925783,0.0057825777,0.00029280444,0.0005867283,0.0006072733,0.00015227727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044018803,0.001023565,0.001280499,0.002605442,0.00076834304,0.0016341419,0.0026512835,0.0015792947,0.0024651603],"category_scores_gemma":[0.01263438,0.000946254,0.002228431,0.0025667765,0.0007172727,0.002303644,0.0018511306,0.0022790756,0.0015158902],"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":[0.0013955395,0.0004838325,0.09751209,0.0007674703,0.00071869517,0.0011658779,0.0035234175,0.2797492,0.017013948,0.07238176,0.06276914,0.4625191],"study_design_scores_gemma":[0.00008818589,0.000024733936,0.0030769513,0.000051437495,0.00007896448,0.00017949581,0.00008700868,0.95322156,0.0013975808,0.037074074,0.0046882927,0.000031740954],"about_ca_topic_score_codex":0.021358222,"about_ca_topic_score_gemma":0.031420916,"teacher_disagreement_score":0.021358222,"about_ca_system_score_codex":0.001261518,"about_ca_system_score_gemma":0.0021515787,"threshold_uncertainty_score":0.042467833},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015824351,0.004214719,0.9571762,0.0045594797,0.00028871789,0.00006757639,0.0019965677,0.0013554014,0.014517024],"genre_scores_gemma":[0.58377725,0.015612111,0.35476172,0.0028215111,0.00068079727,0.00035249704,0.008352163,0.00069956883,0.03294245],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935895,0.00020913854,0.000029835155,0.00017540145,0.00015952416,0.00006721429],"domain_scores_gemma":[0.9984364,0.00088545505,0.00011150179,0.00025702742,0.00022037282,0.00008922074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006908387,0.0007609062,0.00074321294,0.0013769842,0.00046472135,0.0018211632,0.0011309055,0.0013242913,0.0066219987],"category_scores_gemma":[0.0052494407,0.0005054132,0.0008864115,0.0015596234,0.0013030812,0.0037738157,0.0017786735,0.0028537347,0.0017675615],"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":[0.000058262925,0.000051292063,0.0011679865,0.000364921,0.00007752312,0.00012870903,0.00014637285,0.3169974,0.0013952631,0.48556432,0.035042606,0.15900527],"study_design_scores_gemma":[0.000008753789,0.0000136606795,0.00028901477,0.00006791841,0.000009484882,0.000037861966,0.000030654537,0.39192614,0.0004803124,0.59329456,0.013831928,0.000009739748],"about_ca_topic_score_codex":0.0063518076,"about_ca_topic_score_gemma":0.009346667,"teacher_disagreement_score":0.0066219987,"about_ca_system_score_codex":0.0015638034,"about_ca_system_score_gemma":0.00086851744,"threshold_uncertainty_score":0.022152781},"labels":[],"label_agreement":null}]}