{"as_of":"2026-08-16T12:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:012662a89eedfa699db001038428f4fdeae40a0331de7060e35b87c06bf3cc14","coverage":[{"denominator":69,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":69,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T19:37:18.543647Z","state":"measured"},{"denominator":69,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":69,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2412.06566/citation-record","integrity":"/paper/2412.06566/integrity","json":"/paper/2412.06566/citation-record.json","paper":"/paper/2412.06566"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:37:19.675857Z","title":"Protean: An energy-efficient and heterogeneous platform for adaptive and hardware-accelerated battery-free computing","venue":null,"work_id":"9c092d7d-e0f6-46c5-aa82-b8bcfe30747d","year":2022},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.197113Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:e422f7deb4e823d36859cb646b657e0805b7a00ae55d38b45b3a2b75c10b108a","observation_id":"9cd6359c-74e2-45c4-85eb-204e0d5cba72","resolution":{"observed_at":"2026-08-11T19:37:19.680916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.202874Z","title":"Food-101 – mining discriminative components with random forests","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.202874Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:6975894cb691837768908c4c441abf44e456c2df30dad334b6998f88399c7b28","observation_id":"748508e2-1847-4abc-ba55-d6747a90f03c","resolution":{"observed_at":"2026-08-11T19:37:18.202874Z","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":"2026-08-11T19:37:19.645092Z","title":"Large-scale machine learning with stochastic gradient descent","venue":null,"work_id":"89e162ca-3975-4784-964c-0ac5b4d5bf5d","year":2010},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.208290Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:d0e82fd45c7961277052d0fa526568b7a545ff86e6939f0c8c25d39a2e0795e4","observation_id":"8ce90154-c517-4059-aed9-a15bee7c6d51","resolution":{"observed_at":"2026-08-11T19:37:19.650841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.627727Z","title":"Once-for-all: Train one network and specialize it for efficient deployment","venue":null,"work_id":"f97fad65-4174-4d2f-b5a6-0a0addb48946","year":2020},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.214094Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:9f23785ffe5323672a6528b4196ffff0ba63831868ede9b6d1d976dade86fc48","observation_id":"2aaa555f-a907-4f30-86e3-8c8054844e20","resolution":{"observed_at":"2026-08-11T19:37:19.632921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.609376Z","title":"Proxylessnas: Direct neural architecture search on target task and hardware","venue":null,"work_id":"3d975eea-7e82-47d1-b65c-bfd9fd5e766e","year":2019},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.219087Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:d34f6ea1b8225a5a4cb2ce95fe50be00b63cc1eb28d0c001052bb08ae9ec9e45","observation_id":"5296c404-fb2b-40ce-b6cf-c05b9042ceb7","resolution":{"observed_at":"2026-08-11T19:37:19.615346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.589174Z","title":"Fine-grained hardware acceleration for efficient batteryless intermittent inference on the edge","venue":null,"work_id":"9497b274-6614-47da-861a-8ae7342a9823","year":2023},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.224152Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:2c353a7c96c32281ca1cf3727cde0887d763211c5e68b5b628737ab25c99b014","observation_id":"45ce68e8-46f1-4015-9dec-803c9e14f5fc","resolution":{"observed_at":"2026-08-11T19:37:19.595329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.06085","last_updated":"2018-07-17T07:33:19Z","snapshot_observed_at":"2026-08-14T19:14:52.069991Z","submitted_at":"2018-05-16T01:19:43Z","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.06085","snapshot_observed_at":"2026-08-11T19:37:18.230066Z","title":"Pact: Parameterized clipping activation for quantized neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.230066Z"},"links":{"cited_paper":"/paper/1805.06085","citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:40c8c1e189febc1dc6b8071ac64e2d48288b6b1fde9a6fd6736a1eb552cc3a29","observation_id":"2163e527-0e10-4d9e-823a-396c6a5375d6","resolution":{"observed_at":"2026-08-11T19:37:18.230066Z","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":"2026-08-11T19:37:19.569560Z","title":"https://coral.ai/products/dev-board-micro/","venue":null,"work_id":"da3d4c75-0ecd-4b1b-b3eb-ea66d38491d0","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.235077Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:0fa222011b0e17a57926d5bd895520aaaa4e4f1adca286f1b6a05042242cf91a","observation_id":"568da7e8-a8e6-46fe-8498-e46220a9078c","resolution":{"observed_at":"2026-08-11T19:37:19.574981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.239979Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.239979Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:02b3103fccb060597959acfb21477c702bc7e32734ff11685980896e7376bae6","observation_id":"3d0d7720-f956-409a-ac06-8c4122449467","resolution":{"observed_at":"2026-08-11T19:37:18.239979Z","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":"2026-08-11T19:37:19.537916Z","title":"Sparse: Sparse architecture search for cnns on resource-constrained microcontrollers","venue":null,"work_id":"54a9b961-883f-4302-871a-6bfe9619bb26","year":2019},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.244774Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:80b49a7576b8baedcfe399e20a64514f5d6371422cc64fa2e71eb54a3a0c05c8","observation_id":"a45f4e72-0c63-4f2f-9933-ba42326ca16c","resolution":{"observed_at":"2026-08-11T19:37:19.543602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.250015Z","title":"Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.250015Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:bd172722bb846e33b468de8b0ff04b0fe2e86364aa84a50617c47c37ed620919","observation_id":"2d902d15-81b9-4ca7-8ef7-a7bc17badd09","resolution":{"observed_at":"2026-08-11T19:37:18.250015Z","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":"2026-08-11T19:37:19.505715Z","title":"https://greenwaves-technologies.com/ low-power-processor/","venue":null,"work_id":"89462f83-4047-441a-9093-fa8a6456c898","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.254769Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:f6592c4c03e4d6efd4b47d75707c9fb83254279794ffba29d4b21b72361643e1","observation_id":"c3d7b64f-a5e2-4ffc-a619-d8f56cead6ce","resolution":{"observed_at":"2026-08-11T19:37:19.511566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08637","last_updated":"2025-04-23T10:44:56Z","snapshot_observed_at":"2026-08-13T05:04:38.927836Z","submitted_at":"2023-12-11T23:30:01Z","title":"Synergy: Towards On-Body AI via Tiny AI Accelerator Collaboration on Wearables","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08637","snapshot_observed_at":"2026-08-11T19:37:18.259371Z","title":"Collab- orative inference via dynamic composition of tiny ai accelerators on mcus","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.259371Z"},"links":{"cited_paper":"/paper/2401.08637","citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:aec2d36037e2f34e0ccccd9dafa6b6750d2f0873dc5d3a33991283440db1e18d","observation_id":"77c4ae56-3ede-42a6-8282-367440db21b9","resolution":{"observed_at":"2026-08-11T19:37:18.259371Z","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":"2026-08-11T19:37:18.264469Z","title":"Caltech-256 object category dataset","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.264469Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:9f5290c935b2844eb416bbcfea70b46dcd690650616a28cc1c3da177ab9713ac","observation_id":"cc813137-c92e-474d-932a-7bfc72311cbe","resolution":{"observed_at":"2026-08-11T19:37:18.264469Z","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":"2026-08-11T19:37:18.269478Z","title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.269478Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:331dd93a2a3a1559fb57ee31fe17973e75864b6eb07a6d1a97e9e3d1267235e1","observation_id":"2239e4e5-4dbf-47b1-b85e-3e5c2c74067e","resolution":{"observed_at":"2026-08-11T19:37:18.269478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.06037","last_updated":"2023-04-27T16:20:03Z","snapshot_observed_at":"2026-08-15T18:38:43.738451Z","submitted_at":"2016-08-22T02:50:57Z","title":"Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.06037","snapshot_observed_at":"2026-08-11T19:37:18.274823Z","title":"Lets keep it simple, using simple architectures to outperform deeper and more complex archi- tectures","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.274823Z"},"links":{"cited_paper":"/paper/1608.06037","citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:a0a03dfad0242ecf751b5829b628abd11e5062e62f43c2a69ac7ddfb80b3c7e4","observation_id":"24f6d80e-579a-4b50-9967-3220ecd22cca","resolution":{"observed_at":"2026-08-11T19:37:18.274823Z","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":"2026-08-11T19:37:19.464688Z","title":"Channel pruning for accelerating very deep neural networks","venue":null,"work_id":"43a391b3-cdad-4940-a6e5-8a253fbc84a8","year":2017},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.279939Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:7672c7ab4db686015c4deaf2b6f87f1b43ab3f9011f327c44ac17cd6610dc123","observation_id":"f2afcacf-d353-4487-bcda-fd4ba7b65a0a","resolution":{"observed_at":"2026-08-11T19:37:19.470424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.446778Z","title":"Imagenette","venue":null,"work_id":"3bfa7924-6b2f-4a4c-80ef-e95860668b5c","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.284512Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:818164606e9c9719bb6cca8f090594dfb45486411d253033c5cdbbac6768781c","observation_id":"03a3a7be-82a7-494f-9977-7e1383f1abed","resolution":{"observed_at":"2026-08-11T19:37:19.452222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.429802Z","title":"Ai8x synthesis repository","venue":null,"work_id":"45d993fe-fe10-4ed1-b7eb-15e1fa7d9f1e","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.290117Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:c4299132169bc22d4912d2c06ebf4bddc9aa647972078ea5ba8784b26f527c98","observation_id":"676527f0-7376-4c49-bc44-84294bf28a20","resolution":{"observed_at":"2026-08-11T19:37:19.435003Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.413005Z","title":"Ai8x training repository","venue":null,"work_id":"b64aea5b-417c-47bc-8244-d32c09a18bdd","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.294698Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:2546bbfc5870e182d51b462e9f2b0f33e8cb7db78ad286b7ef134a47c91f9474","observation_id":"2184d3ec-5ebf-4e33-9430-c11aba931745","resolution":{"observed_at":"2026-08-11T19:37:19.418361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.299325Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.299325Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:9ded34999306c91406e89cbe8d2158d45839ae29e4a982b610eec8a956ea1c75","observation_id":"368099dd-00c2-4412-b7cf-a11e890573f3","resolution":{"observed_at":"2026-08-11T19:37:18.299325Z","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":"2026-08-11T19:37:18.304293Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.304293Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:4dc04b07e1392e33f68f1a1db4a36942882b6ec1f6eec1cac66ca065585ee46f","observation_id":"c03919ac-30b1-4031-95d9-f172deff3bdd","resolution":{"observed_at":"2026-08-11T19:37:18.304293Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09988","last_updated":"2024-06-10T20:57:14Z","snapshot_observed_at":"2026-08-13T10:52:36.483251Z","submitted_at":"2023-07-19T13:49:12Z","title":"TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09988","snapshot_observed_at":"2026-08-11T19:37:18.308864Z","title":"Tinytrain: Deep neural network training at the extreme edge","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.308864Z"},"links":{"cited_paper":"/paper/2307.09988","citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:062da2f0ff0e12513a03adb066dd1f3c840bdc7497e236ec816127423a902823","observation_id":"f66d7a8c-3dff-448a-81d7-adcdcbb92e36","resolution":{"observed_at":"2026-08-11T19:37:18.308864Z","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":"2026-08-11T19:37:19.375967Z","title":"µnas: Constrained neural architecture search for microcontrollers","venue":null,"work_id":"4c48d7fe-4971-4c24-bf89-1b1df307a4df","year":2021},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.314045Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:54fa42142e8fee7e9fa67aa39d51a75068c5fdd0545ac82873867e949897a293","observation_id":"c5b9bf62-9d2e-4577-8823-cb47ed9ac1ef","resolution":{"observed_at":"2026-08-11T19:37:19.381669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.359714Z","title":"Differentiable neural network pruning to enable smart applications on microcontrollers","venue":null,"work_id":"11d65bd5-52e7-4d57-a1b4-f8812faabbc8","year":2023},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.318651Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:62ecc425429638768c222d3b83219e59b47ebc24ce68b83952c0305b1f10ce15","observation_id":"578739a1-4cb9-49be-8ec7-4501f9a4777b","resolution":{"observed_at":"2026-08-11T19:37:19.365008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.15352","last_updated":"2024-04-03T03:12:53Z","snapshot_observed_at":"2026-08-15T03:25:57.445392Z","submitted_at":"2021-10-28T17:58:45Z","title":"MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.15352","snapshot_observed_at":"2026-08-11T19:37:18.323608Z","title":"Mcunetv2: Memory-efficient patch-based inference for tiny deep learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.323608Z"},"links":{"cited_paper":"/paper/2110.15352","citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:8ef727dea19306cb7ad8bde5525ff897cf5b2ded0eda919527d6c10866ac810f","observation_id":"b86ac08a-dd40-4135-b922-0fdbbfe228c8","resolution":{"observed_at":"2026-08-11T19:37:18.323608Z","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":"2026-08-11T19:37:19.343327Z","title":"Runtime neural pruning","venue":null,"work_id":"0df7af5a-16ba-49e8-b936-6b84126480f5","year":2017},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.328592Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:956429f58ec5d2879f363a9f89c4860d2c3902347f4fef39bd92767189f6355e","observation_id":"7cd43c6e-70f9-470c-9c28-b959a803e435","resolution":{"observed_at":"2026-08-11T19:37:19.348895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.333306Z","title":"On- device training under 256kb memory","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.333306Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:985e4d3bd2f1674d97162a5a8ab09fa92b26e938913c1ac51a95d005483a29bb","observation_id":"1db157fa-c549-4979-8fef-eb6f91a6e2bb","resolution":{"observed_at":"2026-08-11T19:37:18.333306Z","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":"2026-08-11T19:37:19.316972Z","title":"An intriguing failing of convolutional neural networks and the coordconv solution","venue":null,"work_id":"30569107-5e6b-4ec2-8de1-1a8adb28e1f7","year":2018},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.338257Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:83113e4e0bd09875c54acee837f3a2e4af6fef813cfba5230cad8ea41bb7910a","observation_id":"b2e7f1f0-7081-48e2-bd7b-038bb40c80d5","resolution":{"observed_at":"2026-08-11T19:37:19.322208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.00075","last_updated":"2017-11-30T20:54:49Z","snapshot_observed_at":"2026-08-14T20:08:09.117026Z","submitted_at":"2017-11-30T20:54:49Z","title":"Multi-Channel CNN-based Object Detection for Enhanced Situation Awareness","version":1},"cited_work":{"arxiv_id":"1712.00075","doi":null,"metadata_source":"pith","pith_arxiv_id":"1712.00075","snapshot_observed_at":"2026-08-11T19:37:18.626512Z","title":"Multi-Channel CNN-based Object Detection for Enhanced Situation Awareness","venue":"cs.CV","work_id":"3e50e4da-53a6-4981-b659-371c7632f65d","year":2017},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.342971Z"},"links":{"cited_paper":"/paper/1712.00075","citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:e1e5c38042ffb6fd4afdb36c738f255cf084ea2e9091eba9c5581fb6a3b14e5f","observation_id":"e929617c-adc8-4aa2-9c92-518ccfbd26af","resolution":{"observed_at":"2026-08-11T19:37:18.632761Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.300102Z","title":"Metapruning: Meta learning for automatic neural network channel pruning","venue":null,"work_id":"29f40c1c-a753-422b-9e7f-df9143cc210e","year":2019},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.348048Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:f1dbe0ad7ef3ab7e694f5f6a67d8d68abbf3bb7d5727f1ef9290d15fbe2a9754","observation_id":"2d5b7655-844c-44d0-8174-74f9be2b6397","resolution":{"observed_at":"2026-08-11T19:37:19.305653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.352724Z","title":"Learning efficient convolutional networks through network slimming","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.352724Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:e2c199054da2d36b7273757de4029c338e261e6dc2be977e165d8434d73c6a09","observation_id":"582c8468-cd28-49cc-a533-2ddd6ce79269","resolution":{"observed_at":"2026-08-11T19:37:18.352724Z","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":"2026-08-11T19:37:19.274064Z","title":"https://www.analog.com/en/products/max32650.html","venue":null,"work_id":"52488426-a7bb-485a-a080-5d759d9d4ea3","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.357957Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:7889cb24eaf6c0b37cf88adfa5f0bd1acef247420f12c2e89d4fc99f1672951f","observation_id":"a8c5f43c-43c2-4170-8a9e-5da921b20bd8","resolution":{"observed_at":"2026-08-11T19:37:19.279130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.258262Z","title":"https://www.analog.com/en/products/max78000.html","venue":null,"work_id":"bccf8c7d-5f99-485c-9c00-4190319df144","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.362716Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:db97ec613312ce8d83d77aa0078a94967c54b216790b2d4df4af5f7e6ab05d9b","observation_id":"06266bb0-bb7b-492c-baa2-8d483bf21835","resolution":{"observed_at":"2026-08-11T19:37:19.263070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.241800Z","title":"https: //cms.tinyml.org/wp-content/uploads/talks2020/tinyML_Talks_Kris_Ardis_ and_Robert_Muchsel_-201027.pdf","venue":null,"work_id":"76f3eade-20dd-464d-8b7d-eaf0e4f9ee5a","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.367347Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:7fd54cda18e024b63d2ea8d7c720e8d67b1cc4f45ea7ff17fe317547835cb0ec","observation_id":"5f5b863e-0f3e-49fe-86d4-301b5ea108e6","resolution":{"observed_at":"2026-08-11T19:37:19.247386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.224094Z","title":"https://www.analog.com/en/design-center/ evaluation-hardware-and-software/evaluation-boards-kits/max78000fthr","venue":null,"work_id":"f32c83f9-87c9-42aa-aa13-3a6d5d246849","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.373997Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:7c9473aeb28e033fed4f2067b0f1e1d55fdf7ad89bc35fc871cac12583bb5429","observation_id":"2e5e28e4-7be0-4810-bccf-b1005d9a514e","resolution":{"observed_at":"2026-08-11T19:37:19.229704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.206296Z","title":"https://www.analog.com/en/products/max78002.html","venue":null,"work_id":"4b40a530-646a-4fc2-80aa-5d33f3a8d1db","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.379311Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:afc92f521089fb5731901edc49896baf2eaea7e2c02e64068aecf709d7e7d92a","observation_id":"dac7671a-7d1c-43a4-8140-642c50d0ffdc","resolution":{"observed_at":"2026-08-11T19:37:19.211820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.189328Z","title":"https://www.analog.com/en/design-center/ evaluation-hardware-and-software/evaluation-boards-kits/max78002evkit","venue":null,"work_id":"a521064c-91eb-4845-a6f9-92158142037e","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.384234Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:5f4353210555e5a088014095a462f8fc6b2efdb0a18138ae6f5737719d67dc8c","observation_id":"4f8662c5-81de-41d8-bb98-554f29e6be8e","resolution":{"observed_at":"2026-08-11T19:37:19.194756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.172878Z","title":"Tinyissimoyolo: A quantized, low-memory footprint, tinyml object detection network for low power microcon- trollers","venue":null,"work_id":"d82be488-e0b9-43c5-adef-74a205aa88e6","year":2023},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.389012Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:11d3a818a4afe87b46a6218b94138e8f0dc0f02c42e772b4bd436362d8e996d5","observation_id":"bcf8b4c8-7248-4651-adee-911c46cd3273","resolution":{"observed_at":"2026-08-11T19:37:19.178132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.156694Z","title":"Ultra-low power dnn accelerators for iot: Resource characterization of the max78000","venue":null,"work_id":"77a3e8b2-4051-4ca8-90d7-7713062f560e","year":2022},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.393804Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:0224b05f9eb4c87cdf2cb1421200d65e158f04455f2aa888a02a1c54fce4e3fa","observation_id":"d4c8c226-8190-44e2-970a-01e5f5a3b92c","resolution":{"observed_at":"2026-08-11T19:37:19.161960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.398469Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.398469Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:388d4db071f26a8f8d0a1d78a68780c76e31abb707bfc8f1877505c652e1cd17","observation_id":"6f9f8101-3318-41fd-86f5-06f7ffbb9919","resolution":{"observed_at":"2026-08-11T19:37:18.398469Z","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":"2026-08-11T19:37:19.128370Z","title":"Xnor-net: Imagenet classification using binary convolutional neural networks","venue":null,"work_id":"fa4ff5cc-3823-4326-8bec-6d27d5357e3f","year":2016},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.403361Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:b178fac3e5678d194da04f8dafd66f984d9914db33e9a42f186fd0921a3f7cb3","observation_id":"1e460df1-4c81-4393-88b7-aac3324aff09","resolution":{"observed_at":"2026-08-11T19:37:19.133983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.111370Z","title":"Kp2dtiny: Quantized neural keypoint detection and description on the edge","venue":null,"work_id":"ca3614ce-8d4d-4ea8-8111-ed445be247c6","year":2023},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.408394Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:35e51456e6c8ef474d4c2d4896fc4ad63c1bf907e3233065566a28e3eadec28a","observation_id":"b27617ad-37b7-4c96-a0d9-fee10003bee0","resolution":{"observed_at":"2026-08-11T19:37:19.116675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.094866Z","title":"Memory-driven mixed low precision quantization for enabling deep network inference on microcontrollers","venue":null,"work_id":"988f4150-93e9-4416-b1b7-db8e4a00013f","year":2020},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.413351Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:565067fa45e14ee7c8537a1c19086919ea2b57a71845a80f4a6b28674743e250","observation_id":"210f110a-5326-4a1c-951e-27f6fe5315ee","resolution":{"observed_at":"2026-08-11T19:37:19.100298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.418754Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.418754Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:32444c866f265b1d63340c69e03cd4df8c1729d19c0ccc7219d9eba9cb27db86","observation_id":"c13374f2-9505-447b-aed5-4b812e1aef01","resolution":{"observed_at":"2026-08-11T19:37:18.418754Z","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":"2026-08-11T19:37:19.067865Z","title":"Smith, and Oren Etzioni","venue":null,"work_id":"cb79ca3d-993f-46d4-8d78-4e7c2733fe5a","year":2020},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.423681Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:99fcea6400275a6d3b95701654c1d3c7e9566aa2144dad5418125f9e41f1ec54","observation_id":"7736aa70-1140-4aa6-b147-7f6999eeb484","resolution":{"observed_at":"2026-08-11T19:37:19.072878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.052331Z","title":"https://www.st.com/en/microcontrollers-microprocessors/ stm32f7-series.html","venue":null,"work_id":"92a1ad55-4293-459f-bd32-5e4327854434","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.428376Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:dc9c6be6e4ce4ef60f55fcbbce68df58d9292f1c84b765fb6de5bc1918fd4d3e","observation_id":"20f4d1db-91a8-4528-b1f0-b970602f6f87","resolution":{"observed_at":"2026-08-11T19:37:19.057100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.432926Z","title":"Efficientnetv2: Smaller models and faster training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.432926Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:c16c9dadf259cd6ef45e51b2b8f2714de7932648656bc57d917dd50557a2fa52","observation_id":"76aadd0b-f5be-4c65-a052-847966f8b328","resolution":{"observed_at":"2026-08-11T19:37:18.432926Z","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":"2026-08-11T19:37:19.026772Z","title":"Haq: Hardware-aware automated quantization with mixed precision","venue":null,"work_id":"bae720be-5ba8-480d-b6c6-5dd77e6a6248","year":2019},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.437980Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:0df8d27bcb3d9615e9986c801c2a80ecd14d0e6aeeff30f0a63da02cc502afbd","observation_id":"c494b8b5-6ed4-45fb-bf4d-2a78bcf9f5b6","resolution":{"observed_at":"2026-08-11T19:37:19.031747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:19.011668Z","title":"Depth-aware cnn for rgb-d segmentation","venue":null,"work_id":"98129c95-ca0f-4904-9c9d-af6f5a3826ba","year":2018},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.443193Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:7d974ee3fe199cec1712b2772fa124db75ad55272b49147ea48c2e754456af64","observation_id":"b5579167-59ed-4bf2-8859-2d08b939d7c5","resolution":{"observed_at":"2026-08-11T19:37:19.016503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.07044","last_updated":"2018-10-14T23:57:51Z","snapshot_observed_at":"2026-08-14T18:50:23.566801Z","submitted_at":"2018-07-18T17:16:42Z","title":"Location Augmentation for CNN","version":3},"cited_work":{"arxiv_id":"1807.07044","doi":null,"metadata_source":"pith","pith_arxiv_id":"1807.07044","snapshot_observed_at":"2026-08-11T19:37:18.602925Z","title":"Location Augmentation for CNN","venue":"cs.CV","work_id":"78617fe1-78e0-4426-be88-46026272f196","year":2018},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.448807Z"},"links":{"cited_paper":"/paper/1807.07044","citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:3c9b0afff00f1d22fd0841656ed4dd22403fa699320d660c305cfd09eaa1e1cd","observation_id":"0d109d45-6a24-447d-be56-8960c567dab8","resolution":{"observed_at":"2026-08-11T19:37:18.609194Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.996358Z","title":"Streamnet: Memory- efficient streaming tiny deep learning inference on the microcontroller","venue":null,"work_id":"3b75aec7-ad15-45a5-8ee0-fca65a848412","year":2024},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.454250Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:aa4ab07f8fd4407ef965009d6dbd3c8e3a56342fab203bfc949f32090e3dc1f6","observation_id":"38c5141b-bb98-47fc-be3d-036e0a16976e","resolution":{"observed_at":"2026-08-11T19:37:19.001795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.06160","last_updated":"2018-02-02T01:43:54Z","snapshot_observed_at":"2026-08-15T08:38:24.917341Z","submitted_at":"2016-06-20T15:02:31Z","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.06160","snapshot_observed_at":"2026-08-11T19:37:18.459036Z","title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients.arXiv preprint arXiv:1606.06160, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.459036Z"},"links":{"cited_paper":"/paper/1606.06160","citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:602bdc65d1210186418ec48ebc643803a7d589d79e68c68d8409f02b568895d0","observation_id":"31bfe258-e341-4250-8cba-34bbf9322035","resolution":{"observed_at":"2026-08-11T19:37:18.459036Z","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":"2026-08-11T19:37:18.979989Z","title":"[Yes] \" is generally preferable to","venue":null,"work_id":"fe8247a0-145e-42bb-b721-dce09585ff2a","year":2016},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.464349Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:db3bffb6ed685dcfff6431799fa1d644470c1761de665b926204d5ddf2a00141","observation_id":"34ba50dc-db55-46bd-99fe-e9b9806c8ebd","resolution":{"observed_at":"2026-08-11T19:37:18.985565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.961498Z","title":"Guidelines: • The answer NA means that the abstract and introduction do not include the claims made in the paper","venue":null,"work_id":"e3b1ac6b-8f67-46fe-ac2e-3cc107fa159e","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.470225Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:7e699cff19eabd84738b322046a75c70ba3a42adb9e5c887a56e01aca75355dd","observation_id":"a3ff37e8-7435-4c4d-8ee5-ffe75d7817e2","resolution":{"observed_at":"2026-08-11T19:37:18.968141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.942833Z","title":"Limitations","venue":null,"work_id":"d035805b-1f02-4caf-aef4-d16f33329e0f","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.475159Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:1b493aced2e9be3f38d25a22736ef93c268555c528f6313d40fd3af4008f99f5","observation_id":"216ab173-ea94-47c2-a5e8-fd687ef183a7","resolution":{"observed_at":"2026-08-11T19:37:18.949073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.924052Z","title":"Guidelines: • The answer NA means that the paper does not include theoretical results","venue":null,"work_id":"71b68fd5-5582-4441-978c-645c3735edf2","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.481345Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:e720b454867f2624fc0fd555dbd35d814ec73f4ec9356970d08342aad160ff17","observation_id":"f9a28a38-c122-42a5-9528-85b0d2a239af","resolution":{"observed_at":"2026-08-11T19:37:18.929636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.906112Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"7df64ffa-e3cb-4932-8d86-ab365c38a3b9","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.486739Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:b8a0ba29b5a63069c0972820fcdf1f894ad3f864e2e3cdb61a3a6fd2b868673e","observation_id":"3b1e8b3d-efd7-44bd-b1a0-5a0345c8b1b8","resolution":{"observed_at":"2026-08-11T19:37:18.911427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.890173Z","title":"Guidelines: • The answer NA means that paper does not include experiments requiring code","venue":null,"work_id":"67a12e55-e36e-4720-b032-2c6f324659f6","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.492830Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:bc04f8abdb56db7a94b2135ed23dfaaa698d0f2b287b4a4fdb3c00422ae9f2d0","observation_id":"934ff035-c35b-4863-bb48-199d504e5480","resolution":{"observed_at":"2026-08-11T19:37:18.895838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.873402Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"076a0032-914b-4f6b-a4a5-c94b0806958d","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.498668Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:c8ea4752cfb118537f60a5427e0f717f8cd56927caff775738faea675ef33f56","observation_id":"67ed210b-4a9e-4c58-ba24-c271ca4999d6","resolution":{"observed_at":"2026-08-11T19:37:18.878623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.857351Z","title":"We ran the experiments with three random seems (0,1,2) and reported the standard deviations","venue":null,"work_id":"573fa317-a236-446c-8f46-7168fe8d5f57","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.504104Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:a259db5f927f711ed737fbfa9dbfc4099f6d74f0fab55e1634893603f86d6d94","observation_id":"9b6f5f4b-041d-49e2-ba28-0c3f92940957","resolution":{"observed_at":"2026-08-11T19:37:18.862445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.838882Z","title":"Guidelines: • The answer NA means that the paper does not include experiments","venue":null,"work_id":"31a820b4-2d7e-462d-a850-32a000cd0d22","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.509016Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:6fde1f280bed2cb954ad770aa47fe7a16075ec16e71d6639e2eea549c75fe227","observation_id":"e9692f5f-4fe8-454a-adc5-150f715c9367","resolution":{"observed_at":"2026-08-11T19:37:18.844813Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.514005Z","title":"Guidelines: • The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.514005Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:abf15fd2ee0b3d9caa2582e90a72a622593120240c8e272669719dbb58b74673","observation_id":"307001d1-6016-430b-b89a-ec2a68c5a9f9","resolution":{"observed_at":"2026-08-11T19:37:18.514005Z","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":"2026-08-11T19:37:18.810914Z","title":"Guidelines: • The answer NA means that there is no societal impact of the work performed","venue":null,"work_id":"9f018017-0bfb-4437-9712-af056f0a4413","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.518539Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:4991b5d69368838a45cc7b56761a74938cc981847f7011da5ecefdb7f2cc36d0","observation_id":"ffccc775-02d2-4571-8e16-538047360e1c","resolution":{"observed_at":"2026-08-11T19:37:18.816708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.793249Z","title":"Guidelines: • The answer NA means that the paper poses no such risks","venue":null,"work_id":"8e78426c-f69c-438d-a448-cc98a8770e06","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.523487Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:032cf058a95baf3f79a91c25018c97eb612f571dfbe0a4e57575d92c238cd468","observation_id":"be752fee-6af3-457d-90f2-58f45abc5f92","resolution":{"observed_at":"2026-08-11T19:37:18.798658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.775518Z","title":"Guidelines: • The answer NA means that the paper does not use existing assets","venue":null,"work_id":"79e04490-e929-41ec-a50a-a7ae1b2ee508","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.528469Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:f2b9c2591e09dbaddba3b5be872c3d84146882e947acc7e907e9eceb95d44dd2","observation_id":"75f5d750-dbe8-497a-8579-91169a68c9f8","resolution":{"observed_at":"2026-08-11T19:37:18.781389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.759116Z","title":"Guidelines: • The answer NA means that the paper does not release new assets","venue":null,"work_id":"58cb5023-51c7-4c27-9dab-e3fa5a790175","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.532966Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:75942db52188c8e9172c5375641ea66411b48fef36d3cb05aed40e3e6d5d9acc","observation_id":"02fe5aaa-d3bf-4e0a-b813-1c04ee8e0618","resolution":{"observed_at":"2026-08-11T19:37:18.764395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.742005Z","title":"26 Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"7dc33924-542a-4883-be8a-715a25f7a639","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.538298Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:848c09e987c705fe4c45a7259c5351414dbf91df555ed647d497fc75f2f21704","observation_id":"4eceef94-e294-4dfa-bbe0-e15d3aebcf91","resolution":{"observed_at":"2026-08-11T19:37:18.747323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T19:37:18.725035Z","title":"Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"517fed0b-556b-4fc3-b8ca-5962adfb42e0","year":null},"citing_paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T19:37:18.543647Z"},"links":{"citing_paper":"/paper/2412.06566"},"observation_digest":"sha256:0e246ef7a85b7ce0483617326b5c2707ba71e0a42d62872848540426b7c55e7c","observation_id":"480ffaa4-b67f-42f8-8ce1-399cb6297893","resolution":{"observed_at":"2026-08-11T19:37:18.730859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.06566","last_updated":"2024-12-09T15:18:04Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T23:46:37.657464Z","submitted_at":"2024-12-09T15:18:04Z","title":"DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators"},"reference_resolution":{"displayed":69,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":2,"verified_fuzzy":48},"total_outbound_references":69},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 0 inbound Pith citation observations for arXiv:2412.06566."}