{"as_of":"2026-08-21T03:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e691b8b41090e51c3adb0c10ef0e5aae90d59676acf14fd362a268cbde5c2595","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T14:23:07.316138Z","state":"measured"},{"denominator":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.10506/citation-record","integrity":"/paper/2608.10506/integrity","json":"/paper/2608.10506/citation-record.json","paper":"/paper/2608.10506"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.594146Z","title":"Maple: Microprocessor a priori for latency estimation","venue":null,"work_id":"9cbf4198-ade0-4c3d-95ef-72e05b059fef","year":2022},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.222322Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:9da4a6380f38b5b76c27a26b238abf1816f74f7b61c748688053f13f5fceb106","observation_id":"64f7202e-e778-4e59-995b-0532999e44a2","resolution":{"observed_at":"2026-08-15T14:23:07.598067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.582842Z","title":"Neuralpower: Predict and deploy energy-efficient convolu- tional neural networks","venue":null,"work_id":"64a46c6d-dd0d-4df5-87ca-57143f77b302","year":2017},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.227042Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:ef7d581d9c34c5e0b89a50b3c0588d6eeb3b0c74e71f7e2ca2a2d83629a94d4e","observation_id":"33a07804-88ea-4b11-badd-3601c00e4ae8","resolution":{"observed_at":"2026-08-15T14:23:07.587026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00332","last_updated":"2019-02-23T01:36:47Z","snapshot_observed_at":"2026-08-14T17:50:01.332860Z","submitted_at":"2018-12-02T05:29:53Z","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00332","snapshot_observed_at":"2026-08-15T14:23:07.231045Z","title":"Proxylessnas: Direct neural architecture search on target task and hardware.arXiv preprint arXiv:1812.00332, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.231045Z"},"links":{"cited_paper":"/paper/1812.00332","citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:dea813c698841b0df82958481c4fc74baa6894c4f62269b5440ba0dec9c28799","observation_id":"6c24aea5-4791-42d7-9010-d7ce96d5f42f","resolution":{"observed_at":"2026-08-15T14:23:07.231045Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07678","last_updated":"2017-04-14T23:40:21Z","snapshot_observed_at":"2026-08-14T21:55:52.571212Z","submitted_at":"2016-05-24T22:36:02Z","title":"An Analysis of Deep Neural Network Models for Practical Applications","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07678","snapshot_observed_at":"2026-08-15T14:23:07.235299Z","title":"An analysis of deep neural network models for practical applications.arXiv preprint arXiv:1605.07678, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.235299Z"},"links":{"cited_paper":"/paper/1605.07678","citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:d4dc0bace99e60dff3b911375e10ccc37d2478e23844dafc7ceec6e1ae913b5d","observation_id":"afdf49fc-5058-4f44-9c7d-abbd2f61b8de","resolution":{"observed_at":"2026-08-15T14:23:07.235299Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.572185Z","title":"Energy-based tuning of convolu- tional neural networks on multi-gpus.Concurrency and Computation: Practice and Experience, 31(21):e4786, 2019","venue":null,"work_id":"32e290c0-5af1-434f-aee8-307cab7a2573","year":2019},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.239779Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:06aedca88328ce80bcc6a4b161adc2dbeeb465efadaa6b540506714bac7f39e2","observation_id":"076cb8ed-0606-4ea1-beab-8b4b47697857","resolution":{"observed_at":"2026-08-15T14:23:07.576174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.243594Z","title":"Xgboost: A scalable tree boosting system","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.243594Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:16cbc12fa47aae397bc43e2c83e0fb6cae622113e2f97ed7f1bb8513947fc41b","observation_id":"00db2303-eef3-44cd-ac01-710ca1e31e15","resolution":{"observed_at":"2026-08-15T14:23:07.243594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.247549Z","title":null,"venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.247549Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:a75bdb732329f35804316829884b81838a2a12beee6037e12b25bd526b3dafa1","observation_id":"6a027f71-8b6f-4e7f-952d-39525ef71591","resolution":{"observed_at":"2026-08-15T14:23:07.247549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.547522Z","title":"Extremely randomized trees.Machine Learning, 63(1):3–42, Mar 2006","venue":null,"work_id":"d9c11df2-d4ac-4b01-a114-625f8128dc77","year":2006},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.251259Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:c7c220ff3365d30d05aa519ab2681aaf048d6fe6b55d1c9b283012b3dfc94102","observation_id":"00cc8bc4-a9fb-49d9-812e-47cd02ad01a5","resolution":{"observed_at":"2026-08-15T14:23:07.551865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.536745Z","title":"Dvfs- aware dnn inference on gpus: Latency modeling and performance analysis","venue":null,"work_id":"8893952a-2861-4bd2-bbc7-d008ca166cd2","year":2025},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.254858Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:6f70f5c360f38fa2677579a71319659d89b74eb97a269ac8ea9717c3c016353f","observation_id":"86ba8e02-93f1-4ada-91c2-c12b3d9164fe","resolution":{"observed_at":"2026-08-15T14:23:07.540535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.258851Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.258851Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:4a4a5aa8c434e71f804d7faa2b1fcc679dff9f1d9c2cdd3278f4923dcea65ed5","observation_id":"988a338e-df55-4a50-afd0-748e48175ae3","resolution":{"observed_at":"2026-08-15T14:23:07.258851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.262507Z","title":"Lightgbm: A highly efficient gradient boosting decision tree","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.262507Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:a18ba40c0a452104b9516072a0c958c8f218983ca461bb29055195d3901e7378","observation_id":"dcb27f3d-09f1-43a3-9a7c-c5cdaa124025","resolution":{"observed_at":"2026-08-15T14:23:07.262507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.266146Z","title":"Imagenet classification with deep convolutional neural networks.Advances in neural information processing systems, 25, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.266146Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:494514c4a1d6d94462eb5a20cdd33ef69ba6a93aa2fa5fa2e308a064dda11f74","observation_id":"fce2b9a4-59e6-40d8-92bd-133382939f38","resolution":{"observed_at":"2026-08-15T14:23:07.266146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.506672Z","title":"Forecasting gpu performance for deep learning training and inference","venue":null,"work_id":"9e7c15aa-27f5-41ae-bbc3-12a7ccda3400","year":2025},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.269775Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:f1b516ad4c803707c208494237b4fd39610dc72749ddb945140aefb54a093870","observation_id":"6733598b-2381-42bf-a785-aa526d3eed91","resolution":{"observed_at":"2026-08-15T14:23:07.510501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.495132Z","title":"fvcore: Facebook’s core library for computer vision research, 2020","venue":null,"work_id":"90c57fcc-d3a2-4790-bf68-482550e87f8d","year":2020},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.273321Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:7249c3aea688f6c86477a048801d46fc4855617b73b5d2b86b38e82bb4874136","observation_id":"46a315fa-3003-482b-b5ce-8443d05fb21a","resolution":{"observed_at":"2026-08-15T14:23:07.499344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.276594Z","title":"Pytorch: An imperative style, high- performance deep learning library.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.276594Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:e5708a8ecb4bb93c18726eefbfa4a4ce45e1cb3621cbaedbfb93aa84436e2152","observation_id":"41d07fa1-5132-49f9-8777-1f61c8dc4435","resolution":{"observed_at":"2026-08-15T14:23:07.276594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19241","last_updated":"2024-12-26T14:51:24Z","snapshot_observed_at":"2026-08-20T13:31:23.433203Z","submitted_at":"2024-12-26T14:51:24Z","title":"Latenrgy: Model Agnostic Latency and Energy Consumption Prediction for Binary Classifiers","version":1},"cited_work":{"arxiv_id":"2412.19241","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.19241","snapshot_observed_at":"2026-08-15T14:23:07.346107Z","title":"Latenrgy: Model Agnostic Latency and Energy Consumption Prediction for Binary Classifiers","venue":"cs.LG","work_id":"8d79852e-e331-42e1-9839-6f0b3e0f8f11","year":2024},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.280331Z"},"links":{"cited_paper":"/paper/2412.19241","citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:178818f1df23208b71f8b25378b5b3a476db26fccd8efddf7f0194c60d5912b1","observation_id":"cd1d2355-1d8e-4831-b2d5-b73a7f5dfd37","resolution":{"observed_at":"2026-08-15T14:23:07.352515Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.476526Z","title":"Fine- grained energy profiling for deep convolutional neural networks on the jetson tx1","venue":null,"work_id":"ec939a14-e464-44cb-a344-c0e9c3d6c9b5","year":2017},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.284004Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:db152dcb11f28a5c152a22e1858261973d5d42dee6a0834f6c9d8b9d6af53271","observation_id":"02c62f4b-b812-4757-b30f-70b548e17060","resolution":{"observed_at":"2026-08-15T14:23:07.480637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.465871Z","title":"Memory requirements for convolutional neural network hardware accelerators","venue":null,"work_id":"04a4d641-4abc-4e1b-8c01-d8880e570e96","year":2018},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.287438Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:7a2913c7cbfc97ac87e6c22917688d949301f436a7d69a6cf57e43dcc21d9d18","observation_id":"57fca482-711e-48cd-99e4-3f06de413677","resolution":{"observed_at":"2026-08-15T14:23:07.469560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.454439Z","title":"Multi-target regression via input space expansion: treating targets as inputs.Machine Learning, 104(1):55–98, Feb 2016","venue":null,"work_id":"0f5c3f5f-16ba-48c7-8d5b-d155e8e1f1cc","year":2016},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.290919Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:1be2726a07b7fad5a8360e63c21511fec7e7d55bc45918fc3d681cca90cbd096","observation_id":"f121320c-d1e9-4d1b-8a17-0ef6daeeba69","resolution":{"observed_at":"2026-08-15T14:23:07.458576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.442807Z","title":"Hyperpower: Power-and memory-constrained hyper- parameter optimization for neural networks","venue":null,"work_id":"86a19144-23a0-442b-8159-0e8bf4549e4e","year":2018},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.294386Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:b74037f74eb12a9688e2a6bdb12d8a2bc860409d8c635496d55ee37f61cbdde6","observation_id":"080350da-7f6e-4453-9bbc-a5a80a853bb5","resolution":{"observed_at":"2026-08-15T14:23:07.446686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.298211Z","title":"Energy and policy considerations for deep learning in nlp","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.298211Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:5176ad61355f0f2841434d599a003cf34b490deb49def54cc1d3ab3ec945ab53","observation_id":"ace4d919-74ce-4800-b0df-e56028ff8b6b","resolution":{"observed_at":"2026-08-15T14:23:07.298211Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.424686Z","title":"Characterizing deep learning training workloads on alibaba-pai","venue":null,"work_id":"5d6c8358-7b65-4a55-8cb6-8a4190997c03","year":2019},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.301565Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:26d863f0d274a5a537ec5543900b8fa2be4e6bded140a774faaea1160a51fc96","observation_id":"60f08f81-5083-4ccb-9f9e-9004b447955a","resolution":{"observed_at":"2026-08-15T14:23:07.428797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.305414Z","title":"Roofline: an insightful visual performance model for multicore architectures","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.305414Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:287531418f050a9de7f2b20e4b4349eb4468197a4152aac7ffd1d0f53cf476b0","observation_id":"d8cfca72-d0df-4813-9f25-1a09818d1db0","resolution":{"observed_at":"2026-08-15T14:23:07.305414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.406803Z","title":"Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search","venue":null,"work_id":"65f7bad7-2dd4-4302-8d42-7cdac7264d2e","year":2019},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.309132Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:76ad83ff574eb0e9553f982a7392c293bb960cb38315ec9e5b0c2c29ff394b30","observation_id":"8b752f7e-d408-474a-8ea6-7ef168d9a6fb","resolution":{"observed_at":"2026-08-15T14:23:07.411071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.395034Z","title":"Designing energy- efficient convolutional neural networks using energy-aware pruning","venue":null,"work_id":"b19626d9-97de-44e2-8d7a-1e5a06f36b08","year":2017},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.312755Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:d53d66f42bec03a1c6ef363e7a5eb3e951969a986c14a0f028c6703ffd496852","observation_id":"ec8457e1-b2ac-4536-b924-4d8bba0c71db","resolution":{"observed_at":"2026-08-15T14:23:07.399015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:23:07.382997Z","title":"Nn-meter: Towards accurate latency prediction of deep-learning model inference on diverse edge devices","venue":null,"work_id":"cb8919c3-ae1a-461b-a295-e3e15dbb1963","year":2021},"citing_paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T14:23:07.316138Z"},"links":{"citing_paper":"/paper/2608.10506"},"observation_digest":"sha256:9816f9f9621718bcb466ebafd14c67ff26e24971af4d10b787932fb012451f87","observation_id":"466ccb7b-993b-40ee-80f3-3e758a9cd0fa","resolution":{"observed_at":"2026-08-15T14:23:07.387016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.10506","last_updated":"2026-08-11T05:27:53Z","latest_version":1,"primary_category":"cs.AR","snapshot_observed_at":"2026-08-19T22:23:34.191644Z","submitted_at":"2026-08-11T05:27:53Z","title":"CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":1,"verified_fuzzy":15},"total_outbound_references":26},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2608.10506."}