{"as_of":"2026-08-09T05:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:74d2a49e7319321defb32d3305e8254f45460819db2ce584bebc976b7dcdab1b","coverage":[{"denominator":21,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":21,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T05:59:51.090955Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2509.04721/citation-record","integrity":"/paper/2509.04721/integrity","json":"/paper/2509.04721/citation-record.json","paper":"/paper/2509.04721"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2015.35021","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:59:51.575126Z","title":"Internet of Things (IoT): A Literature Review,","venue":null,"work_id":"0aa11b70-ad92-4bc7-8fb9-0af16e33aaf0","year":2015},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:50.996489Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:fc94740c7d74db3dbe84eab0bebc895beed6229e06877cc84dad24f64f48b0a8","observation_id":"ca938d77-92c5-4683-ab0e-b51896acdd09","resolution":{"observed_at":"2026-08-05T05:59:51.585582Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.001120Z","title":"Edge Computing: Vision and Challenges,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.001120Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:57d170268dbe3441110de0f314468bf510ae3d0409943d17812b97e94d02398a","observation_id":"737f1b78-4538-4752-8539-edf658f2d243","resolution":{"observed_at":"2026-08-05T05:59:51.001120Z","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":"2026-08-05T05:59:51.831140Z","title":"Warden and D","venue":null,"work_id":"b930a2b6-9e0d-48b5-b121-7781b29c724d","year":2019},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.005229Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:17fef17fc7a482ea51bccd57b5522d8dd8d52dc7bd777d853d8c6015636f36a9","observation_id":"6a4df998-1d13-4d79-9916-0b2aa2982eae","resolution":{"observed_at":"2026-08-05T05:59:51.836339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.009638Z","title":"Advancements in TinyML: Applications, Limitations, and Impact on IoT Devices,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.009638Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:ddb7fa0c9c1fb7b53465267919ec7566db8cfa2155d66e4db607bd05037f641a","observation_id":"bbfc3868-2792-46f7-b8dc-f8eeb6feac32","resolution":{"observed_at":"2026-08-05T05:59:51.009638Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.01878","last_updated":"2017-11-13T18:40:16Z","snapshot_observed_at":"2026-08-05T00:54:50.482913Z","submitted_at":"2017-10-05T04:26:49Z","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.01878","snapshot_observed_at":"2026-08-05T05:59:51.014101Z","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.014101Z"},"links":{"cited_paper":"/paper/1710.01878","citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:a38da782588e2d7acad4949db9bfd059d46f233e29c017ead1131a80bc8dd2d3","observation_id":"41d0df69-615c-4f8f-ae1a-e5962e33b5a4","resolution":{"observed_at":"2026-08-05T05:59:51.014101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.09068","last_updated":"2024-01-17T09:01:50Z","snapshot_observed_at":"2026-08-08T12:41:45.102817Z","submitted_at":"2024-01-17T09:01:50Z","title":"DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning","version":1},"cited_work":{"arxiv_id":"2401.09068","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.09068","snapshot_observed_at":"2026-08-05T05:59:51.379231Z","title":"DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning","venue":"cs.LG","work_id":"06452684-ae79-4bd3-b878-405f92f097fc","year":2024},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.018800Z"},"links":{"cited_paper":"/paper/2401.09068","citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:6ad65ea381d49d092687cee392b51d082bcf3df9f70031a778796af310ef9486","observation_id":"3c0355f5-22ad-405f-a709-efa4619f0fef","resolution":{"observed_at":"2026-08-05T05:59:51.385163Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11883","last_updated":"2023-11-20T16:20:13Z","snapshot_observed_at":"2026-07-06T16:50:02.155961Z","submitted_at":"2023-11-20T16:20:13Z","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.11883","snapshot_observed_at":"2026-08-05T05:59:51.024183Z","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.024183Z"},"links":{"cited_paper":"/paper/2311.11883","citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:b9cdc9f67809d6c89cba980e65504c4d645e5fe9fe611fac13e1f4bed9954e18","observation_id":"f9dc21af-7fdf-41c9-92aa-bfaefbbce044","resolution":{"observed_at":"2026-08-05T05:59:51.024183Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.03332","last_updated":"2023-04-28T22:33:47Z","snapshot_observed_at":"2026-08-07T06:19:29.561909Z","submitted_at":"2022-11-02T19:49:34Z","title":"Edge Impulse: An MLOps Platform for Tiny Machine Learning","version":3},"cited_work":{"arxiv_id":"2212.03332","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.03332","snapshot_observed_at":"2026-08-05T05:59:51.330778Z","title":"Edge Impulse: An MLOps Platform for Tiny Machine Learning","venue":"cs.DC","work_id":"dcb9a09d-6e92-4082-ac07-719742d5b1e1","year":2022},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.028552Z"},"links":{"cited_paper":"/paper/2212.03332","citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:752e646d83e7ce3289cfdb60c8e3e44490a0a28019aec7dafdabdb82d845ccce","observation_id":"7ccf0c99-4ce4-4e51-ac01-a64f43504ef5","resolution":{"observed_at":"2026-08-05T05:59:51.339196Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.809001Z","title":"Available: https: //www.raspberrypi.com/products/raspberry-pi-4-model-b/specifications/","venue":null,"work_id":"f389eaa0-1d67-4471-885c-8ca7536def25","year":null},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.033007Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:8fefd5b651385dfdb95a1d9d3bc12431ac897c0485097bb0ed7acada1a10f7ce","observation_id":"da8619d8-66e8-4255-8086-15716266b025","resolution":{"observed_at":"2026-08-05T05:59:51.814196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.794065Z","title":"Available: https:// docs.beagleboard.org/boards/beaglebone/ai-64/index.html","venue":null,"work_id":"ba62a1a1-e1c3-4f2d-9674-a83371665168","year":null},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.037456Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:cd58a57af866ece52212dbf86faf401a4a3df4a6cb0ce26453cd003257072dc3","observation_id":"d3e61630-0905-4eab-8f32-d4bdeb94cddd","resolution":{"observed_at":"2026-08-05T05:59:51.798291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.778689Z","title":"Available: https://github.com/tensorflow/examples/blob/master/lite/%examples/ gesture classification","venue":null,"work_id":"0281545b-9ab4-4b5b-b716-865b261121b8","year":null},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.041655Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:e13847c9a7ef1d2f97c5008544fbda73149f0380656ba1fabd62aa49e898227e","observation_id":"6ee6b146-a2e3-4afe-8993-8ae768d70071","resolution":{"observed_at":"2026-08-05T05:59:51.783908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.761059Z","title":"Available: https://siliconlabs.github.io/ mltk/ static/kws overview/index.html","venue":null,"work_id":"3e47d518-9f3a-44e7-803f-abf4b42d2798","year":null},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.046173Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:c569f2398588ccb7863d1717d292c691ae487a971478be8086d93239225c5610","observation_id":"f10f9fc8-da6a-4b54-b234-5aa7e64229cc","resolution":{"observed_at":"2026-08-05T05:59:51.767783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.739309Z","title":"Available: https://pytorch.org/hub/pytorch vision mobilenet v2/","venue":null,"work_id":"789d9bc2-292f-452b-a9c4-241c4d831cdb","year":null},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.051413Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:dc922e06e3b4f8cce1bf9661b2776fd9e1c0b52f7d6274d68050613ec2b76a9a","observation_id":"59774874-af4b-4191-8290-9d9b6211a3be","resolution":{"observed_at":"2026-08-05T05:59:51.744331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.716358Z","title":"[Online]","venue":null,"work_id":"a2039e07-703a-480b-9d9b-8ab42b6f34c3","year":2020},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.056033Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:413d81896761753d31eea766a9a9a4551f01e069193ed6467884696ffe3c4528","observation_id":"5326471f-1c39-4061-a6cf-dcf3df1a46f2","resolution":{"observed_at":"2026-08-05T05:59:51.721629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.059996Z","title":"Power-Performance Char- acterization of TinyML Systems,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.059996Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:296ab6b860cd124e855709c562842d51b90c8d22c50d05b5959e76c287b6ec87","observation_id":"30989447-ed14-4f20-8459-576ce694d663","resolution":{"observed_at":"2026-08-05T05:59:51.059996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07597","last_updated":"2021-08-24T19:12:29Z","snapshot_observed_at":"2026-08-03T14:46:30.239773Z","submitted_at":"2021-06-14T17:05:17Z","title":"MLPerf Tiny Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07597","snapshot_observed_at":"2026-08-05T05:59:51.067059Z","title":"[Online]","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.067059Z"},"links":{"cited_paper":"/paper/2106.07597","citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:e4c6c8991b3689ea930813826c54252a4119fea5a41ed7d7810c3fd2984547d2","observation_id":"5d4734d2-6541-4c7e-82c9-f425f9595bdc","resolution":{"observed_at":"2026-08-05T05:59:51.067059Z","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":"2026-08-05T05:59:51.695286Z","title":"TensorFlow Lite Runtime for inference execution,","venue":null,"work_id":"e549b86b-371c-4e2f-b503-1dbed07cd5f5","year":2023},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.072696Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:d2b14fee72ae4fd9862482598cf6dbdd760a275e28dca3c3c805d5ad1beebd7a","observation_id":"032b9bea-618f-4084-9809-1b156a8c19cc","resolution":{"observed_at":"2026-08-05T05:59:51.700412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.672583Z","title":"Arya, Hand Gesture Recognition Dataset, Kaggle,","venue":null,"work_id":"bc67d56f-78ef-4d3f-9dca-23fb8b8b2811","year":null},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.077024Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:4cc8a5daccf710fc3271e6f9783179a663b42106ef0b855ce90e8b611054af59","observation_id":"f9a80a37-7676-4ac3-9139-6e3db9355501","resolution":{"observed_at":"2026-08-05T05:59:51.680065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.622761Z","title":"Available: https://siliconlabs.github.io/mltk/docs/python api%/datasets/audio/ speech commands v2.html","venue":null,"work_id":"f73297d1-37cb-4dd3-8bfc-2ae02ad57bff","year":2021},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.086413Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:c19c7bb4b50d9960ab298d0cdd0d7525532ec57ff9ffcd430193771303f946ee","observation_id":"f925f283-d6c4-4af2-83f1-f36fabd5b0fb","resolution":{"observed_at":"2026-08-05T05:59:51.627983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.600931Z","title":null,"venue":null,"work_id":"b909e139-73eb-4e35-99e4-e5f52638960e","year":null},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.090955Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:a98a322e3e4f0fe78f45e5cfccf8e84ec7563508b035381635fe4bedce5d0940","observation_id":"d31c54d4-129a-4f49-867e-781cc8856d69","resolution":{"observed_at":"2026-08-05T05:59:51.609093Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-05T05:59:51.648441Z","title":null,"venue":null,"work_id":"c4bd6eba-5a5c-46ea-b938-57c862edde17","year":null},"citing_paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-05T05:59:51.081861Z"},"links":{"citing_paper":"/paper/2509.04721"},"observation_digest":"sha256:e75dae1ddaa21642387ea7306f57f24d7934312b08586f736770c6943c89f4b9","observation_id":"fdbee5cc-2556-4cae-8b57-68d2f2e8fea9","resolution":{"observed_at":"2026-08-05T05:59:51.656887Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.04721","last_updated":"2025-09-05T00:30:39Z","latest_version":1,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-08T12:41:17.489217Z","submitted_at":"2025-09-05T00:30:39Z","title":"Real-Time Performance Benchmarking of TinyML Models in Embedded Systems (PICO: Performance of Inference, CPU, and Operations)"},"reference_resolution":{"displayed":21,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":3,"verified_fuzzy":10},"total_outbound_references":21},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2509.04721."}