{"meta":{"query_hash":"e3535f4a0108","filters":{"venue":"2022 IEEE International Conference on Image Processing (ICIP)"},"cohort_total":7,"direct_labels_cover":0,"predictions_cover":7,"exported":7,"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/e3535f4a0108","api":"https://metacan.xera.ac/api/v1/cohort?venue=2022+IEEE+International+Conference+on+Image+Processing+%28ICIP%29"},"results":[{"id":"W3205781905","doi":"10.1109/icip46576.2022.9897680","title":"Deep Image Debanding","year":2022,"lang":"en","type":"preprint","venue":"2022 IEEE International Conference on Image Processing (ICIP)","topic":"Image Enhancement Techniques","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":"University of Waterloo","funders":"","keywords":"Artifact (error); Deep learning; Artificial intelligence; Computer science; Construct (python library); Image (mathematics); Computer vision","score_opus":0.06057705323253225,"score_gpt":0.35423229935712647,"score_spread":0.2936552461245942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205781905","genre_codex":"methods","genre_gemma":"empirical","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":[0.00075215666,0.00020102366,0.899748,0.0032843524,0.005841647,0.00054853567,0.00003334342,0.0012221531,0.08836877],"genre_scores_gemma":[0.6233538,0.00044569638,0.35962713,0.0023885982,0.0009986922,0.0016871942,0.00038148966,0.00018271082,0.010934686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99432635,0.00022258384,0.0009029225,0.0018244743,0.0020072276,0.0007164403],"domain_scores_gemma":[0.9966663,0.000103822626,0.00095314416,0.0012319993,0.0008811037,0.00016358848],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00094665645,0.00074544887,0.00057896925,0.0008584559,0.0005386358,0.003181555,0.0062592756,0.00022585248,0.0024619866],"category_scores_gemma":[0.00022248067,0.00081165275,0.00027186458,0.00044561233,0.0002123828,0.0016644334,0.003856519,0.0022554966,0.00017029226],"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":[0.00042477634,0.0025499058,0.00038537048,0.0018210125,0.0008504462,0.002398012,0.011042434,0.0013921928,0.30332243,0.1322141,0.06641276,0.47718653],"study_design_scores_gemma":[0.0007411797,0.00026723664,0.00013176723,0.0011431113,0.000059954218,0.00006716502,0.00035118283,0.8528514,0.07451932,0.061408352,0.006375183,0.0020841656],"about_ca_topic_score_codex":0.00006120635,"about_ca_topic_score_gemma":0.000009324175,"teacher_disagreement_score":0.8514592,"about_ca_system_score_codex":0.000955474,"about_ca_system_score_gemma":0.0007172668,"threshold_uncertainty_score":0.99943346},"labels":[],"label_agreement":null},{"id":"W4308233806","doi":"10.1109/icip46576.2022.9897673","title":"ICIP 2022 Organizing Committee","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Image Processing (ICIP)","topic":"Diverse Perspectives in Modern Studies","field":"Economics, Econometrics and Finance","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":"York University","funders":"","keywords":"Computer science","score_opus":0.09495798603910299,"score_gpt":0.30386655326534867,"score_spread":0.20890856722624568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308233806","genre_codex":"other","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":[0.08838066,0.002685142,0.01789427,0.013425142,0.01307575,0.00060493354,0.0009725387,0.0004409202,0.86252064],"genre_scores_gemma":[0.9811629,0.0001671352,0.0012036796,0.0011521754,0.00028146146,0.00014664314,0.00004903756,0.00005709172,0.015779845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99780995,0.00004689866,0.0006035387,0.0008013067,0.00033106902,0.00040726297],"domain_scores_gemma":[0.99874395,0.00006549555,0.0005416766,0.0003271756,0.00024627798,0.00007540404],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000637493,0.00028726293,0.0004164488,0.00047384127,0.0008532953,0.0004098186,0.0010963595,0.000050263377,0.011853075],"category_scores_gemma":[0.00021739875,0.00036398516,0.00012634307,0.00039631134,0.00019460332,0.00051556894,0.0006168437,0.0007176782,0.000745327],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041840458,0.0016389729,0.02180834,0.00014135861,0.0008357927,0.0002464884,0.020714778,0.0011722738,0.0060812933,0.85345167,0.077459574,0.016031029],"study_design_scores_gemma":[0.005730358,0.0010395847,0.010974705,0.0002982255,0.00010918071,0.00014577278,0.049352344,0.22425981,0.0021916952,0.42885742,0.27279654,0.0042443676],"about_ca_topic_score_codex":0.00012591867,"about_ca_topic_score_gemma":0.000015416024,"teacher_disagreement_score":0.8927823,"about_ca_system_score_codex":0.0007593175,"about_ca_system_score_gemma":0.000091648195,"threshold_uncertainty_score":0.9998812},"labels":[],"label_agreement":null},{"id":"W4308234157","doi":"10.1109/icip46576.2022.9897832","title":"Self-Superflow: Self-Supervised Scene Flow Prediction in Stereo Sequences","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Image Processing (ICIP)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":5,"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":"CODE","keywords":"Computer science; Ground truth; Artificial intelligence; Benchmark (surveying); Generalization; Flow (mathematics); Convergence (economics); Representation (politics); Artificial neural network; Deep learning; Machine learning; Test data; Supervised learning; Computer vision; Pattern recognition (psychology); Mathematics","score_opus":0.038593156455610296,"score_gpt":0.3103629937535771,"score_spread":0.27176983729796683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308234157","genre_codex":"methods","genre_gemma":"empirical","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":[0.06465599,0.0006465305,0.84001845,0.015311461,0.012011213,0.0013425193,0.0001572657,0.0028621065,0.06299449],"genre_scores_gemma":[0.74301463,0.00009507744,0.25368604,0.0015691337,0.00020915056,0.00023816893,0.000047451696,0.000035015033,0.0011053475],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965862,0.00020077005,0.0005800643,0.0009065311,0.001264713,0.00046170474],"domain_scores_gemma":[0.99883807,0.00006545724,0.00021918674,0.00040661945,0.0003436865,0.00012695769],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061669236,0.0003089159,0.00026695835,0.0005491245,0.0005205754,0.00070928934,0.0019220535,0.000049937637,0.0008242275],"category_scores_gemma":[0.00005867495,0.0003198335,0.00008634952,0.0007644682,0.00006344631,0.0022459715,0.00050715863,0.0007365136,0.00007763837],"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":[0.00022863294,0.0019759794,0.0030056688,0.00021709195,0.00012222635,0.00046511888,0.014263456,0.005006333,0.055867314,0.008127745,0.0031369822,0.9075835],"study_design_scores_gemma":[0.000836602,0.00016560737,0.00027927922,0.0001062682,0.0000067873075,0.00006024452,0.00061298395,0.9894173,0.0016191724,0.0025789824,0.0039850236,0.0003317423],"about_ca_topic_score_codex":0.000027295811,"about_ca_topic_score_gemma":0.00000918099,"teacher_disagreement_score":0.984411,"about_ca_system_score_codex":0.000560123,"about_ca_system_score_gemma":0.00044657584,"threshold_uncertainty_score":0.9999254},"labels":[],"label_agreement":null},{"id":"W4308235812","doi":"10.1109/icip46576.2022.9897572","title":"Interpretable Concept-Based Prototypical Networks for Few-Shot Learning","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Image Processing (ICIP)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Black box; Computer science; Artificial intelligence; Metric (unit); Set (abstract data type); Task (project management); Machine learning; Shot (pellet)","score_opus":0.0627864200723764,"score_gpt":0.33380520621211196,"score_spread":0.27101878613973557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308235812","genre_codex":"methods","genre_gemma":"empirical","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":[0.0008377911,0.000066837296,0.98222136,0.0028253298,0.0018049612,0.00062240876,0.000010927481,0.00034586538,0.011264532],"genre_scores_gemma":[0.96476316,0.0000037712107,0.026560966,0.0020489574,0.0002061621,0.0010869375,0.00009246522,0.000037616952,0.005199942],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99715626,0.00023373334,0.0004859098,0.00077031064,0.0008608209,0.0004929559],"domain_scores_gemma":[0.9984959,0.00023464275,0.00039032035,0.0002788886,0.00046216033,0.00013811066],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00077701616,0.0002809196,0.0002720886,0.0002655916,0.00093422935,0.0009749439,0.0016180484,0.000066401284,0.0014273609],"category_scores_gemma":[0.00024006679,0.0002986441,0.00014954772,0.00040372286,0.00012326051,0.00068184675,0.00027842095,0.0009837549,0.000024442832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016442336,0.0010802832,0.0006186527,0.00013685341,0.00018772029,0.000118651704,0.0063852197,0.46013105,0.021232633,0.16806257,0.010828783,0.32957333],"study_design_scores_gemma":[0.0009865016,0.00041473372,0.000045204255,0.00007887745,0.000008650717,0.000014288825,0.0004763957,0.97329676,0.0007983455,0.0015086554,0.022021707,0.0003499058],"about_ca_topic_score_codex":0.00001133714,"about_ca_topic_score_gemma":0.000002744946,"teacher_disagreement_score":0.96392536,"about_ca_system_score_codex":0.00025821824,"about_ca_system_score_gemma":0.00041743377,"threshold_uncertainty_score":0.9999466},"labels":[],"label_agreement":null},{"id":"W4308235886","doi":"10.1109/icip46576.2022.9897527","title":"Automatic Inspection of Cultural Monuments Using Deep and Tensor-Based Learning on Hyperspectral Imagery","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Image Processing (ICIP)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Hyperspectral imaging; Robustness (evolution); Artificial intelligence; Deep learning; Computer science; Cultural heritage; Perspective (graphical); Tensor (intrinsic definition); Pattern recognition (psychology); Computer vision; Machine learning; Archaeology; Mathematics; Geography","score_opus":0.050825315607764085,"score_gpt":0.303273541000542,"score_spread":0.2524482253927779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308235886","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":[0.9821145,0.00006486622,0.012845414,0.00030233935,0.00086640386,0.00018208104,0.000011064584,0.00041436084,0.0031990034],"genre_scores_gemma":[0.9918697,0.000014784132,0.007690084,0.00006123373,0.00008162365,0.000019597479,0.00003980402,0.00004845963,0.00017471067],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983084,0.00008623436,0.00039021735,0.00034806627,0.00063101016,0.00023606126],"domain_scores_gemma":[0.99925566,0.00005205011,0.00022967184,0.00014998327,0.0002547245,0.000057911606],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021929153,0.00023631875,0.00022476423,0.00036429742,0.00032448405,0.00022363414,0.00022037477,0.0000469025,0.00019012525],"category_scores_gemma":[0.000119640164,0.00025240693,0.00006411715,0.0002608062,0.00010798948,0.00039453784,0.000039370592,0.0005599276,0.000009621121],"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":[0.00009669902,0.00015228902,0.00050274114,0.000152005,0.00006685964,0.000028827506,0.0014314799,0.15810694,0.8101259,0.00016241142,0.00017343207,0.029000442],"study_design_scores_gemma":[0.00043636127,0.000113268106,0.001138225,0.00014747353,0.00002506185,0.00003360678,0.0012651721,0.972977,0.023439994,0.00013178505,0.00005190944,0.00024014499],"about_ca_topic_score_codex":0.000025209505,"about_ca_topic_score_gemma":0.000001945288,"teacher_disagreement_score":0.81487006,"about_ca_system_score_codex":0.0006789935,"about_ca_system_score_gemma":0.00007109585,"threshold_uncertainty_score":0.9999928},"labels":[],"label_agreement":null},{"id":"W4308236992","doi":"10.1109/icip46576.2022.9897254","title":"Predicting Soil Properties from Hyperspectral Satellite Images","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Image Processing (ICIP)","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Helmholtz Association","keywords":"Hyperspectral imaging; Artificial intelligence; Computer science; Artificial neural network; Satellite; Remote sensing; Fulvic acid; Pattern recognition (psychology); Geology; Chemistry; Engineering","score_opus":0.052939804894811496,"score_gpt":0.2680628145019913,"score_spread":0.21512300960717984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308236992","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":[0.8989657,0.0014047301,0.010711446,0.0033153705,0.0059426283,0.00047704717,0.00021708342,0.0018258718,0.077140085],"genre_scores_gemma":[0.99428797,0.00013271745,0.0029934705,0.00016695255,0.00043647265,0.000071530994,0.00012545518,0.00008889198,0.001696568],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768263,0.00008669282,0.000467598,0.0005334018,0.00084755593,0.00038211906],"domain_scores_gemma":[0.9991015,0.00005219063,0.00016772166,0.00030528993,0.00028442897,0.00008883573],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025669148,0.00031819654,0.00024521336,0.00025201164,0.00034741685,0.00057463505,0.00063296943,0.000059347803,0.0006802428],"category_scores_gemma":[0.00010807348,0.00033626624,0.000090785165,0.00024136741,0.00014128794,0.0006266677,0.000107403146,0.00075047865,0.00009917026],"study_design_candidate":"bench_or_experimental","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":[0.00008691367,0.000091861395,0.0003923072,0.00005281286,0.00008348544,0.0000476076,0.0018008234,0.0065864734,0.9488728,0.0001382004,0.0012674927,0.040579244],"study_design_scores_gemma":[0.00048519266,0.00007349066,0.0013285911,0.00019108104,0.000037356753,0.00003993722,0.0024852725,0.8241835,0.16794895,0.0009267771,0.0017492102,0.0005506176],"about_ca_topic_score_codex":0.00009109629,"about_ca_topic_score_gemma":0.0000152361035,"teacher_disagreement_score":0.81759703,"about_ca_system_score_codex":0.00052262447,"about_ca_system_score_gemma":0.00013039015,"threshold_uncertainty_score":0.9999089},"labels":[],"label_agreement":null},{"id":"W4308237016","doi":"10.1109/icip46576.2022.9898010","title":"Back to Old Constraints to Jointly Supervise Learning Depth, Camera Motion and Optical Flow in a Monocular Video","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Image Processing (ICIP)","topic":"Advanced Vision and Imaging","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":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Optical flow; Artificial intelligence; Computer vision; Constraint (computer-aided design); Monocular; Computer science; Motion (physics); Interpretation (philosophy); Structure from motion; Deep learning; Brightness; Motion estimation; Image (mathematics); Mathematics; Optics; Physics; Geometry","score_opus":0.04102845790298629,"score_gpt":0.32009330496826643,"score_spread":0.2790648470652801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308237016","genre_codex":"methods","genre_gemma":"empirical","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":[0.038808074,0.000036500525,0.94397926,0.010048559,0.0006605843,0.000309254,0.000007739289,0.00009168134,0.0060583223],"genre_scores_gemma":[0.8416342,0.000009338018,0.15457192,0.0027689198,0.00005092794,0.00009367921,0.000009861787,0.000019673014,0.00084144855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767363,0.00012220409,0.0003898114,0.0007689507,0.0006752144,0.00037020227],"domain_scores_gemma":[0.9991635,0.000060344995,0.0000955399,0.0002186864,0.00024057146,0.00022134029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047673448,0.00022248646,0.00022921256,0.00047016874,0.00028237433,0.000607285,0.00077678944,0.000031056676,0.0006714546],"category_scores_gemma":[0.00024188028,0.00024376425,0.00004675158,0.0005072967,0.000092043294,0.000826754,0.00058341824,0.00059663237,0.00012358879],"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":[0.00008572735,0.00017295235,0.0008271024,0.000027609372,0.000013350408,0.000116374904,0.0035493742,0.011746168,0.04880181,0.0045418446,0.00033561228,0.9297821],"study_design_scores_gemma":[0.0006004158,0.00020270425,0.00096235797,0.00015977665,0.0000033079157,0.0000699104,0.0008202928,0.9912234,0.0031270266,0.0012525509,0.0012336519,0.00034462268],"about_ca_topic_score_codex":0.000030896485,"about_ca_topic_score_gemma":0.000013937263,"teacher_disagreement_score":0.9794772,"about_ca_system_score_codex":0.00023469354,"about_ca_system_score_gemma":0.00011776292,"threshold_uncertainty_score":0.9940418},"labels":[],"label_agreement":null}]}