{"as_of":"2026-08-21T06:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:71c041633b81916a18cddd90d1a4afef3c1b3af23caf053215dca0a5cea12af2","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:13:01.820101Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.06380/citation-record","integrity":"/paper/2507.06380/integrity","json":"/paper/2507.06380/citation-record.json","paper":"/paper/2507.06380"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.291683Z","title":"Eie: Efficient inference engine on compressed deep neural network,","venue":null,"work_id":"509a8df5-3e0f-4124-a939-c89d11e1bbb8","year":2016},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.693490Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:f4ae73244c62e396035e413f0349a2ad018bf38e26b7648364b8b35f9ba6c9f0","observation_id":"7c217ea7-5261-4d7d-ac6c-4b3dd51bca97","resolution":{"observed_at":"2026-08-06T19:13:02.296140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-06T19:13:01.698807Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.698807Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:c4f0cbf5ab1b439dfbb7cee3af79c66938526141987fa3f691eb4a5d4afc3e85","observation_id":"04641fc7-5f34-4d44-856e-b7f171380d75","resolution":{"observed_at":"2026-08-06T19:13:01.698807Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-06T19:13:01.704191Z","title":"Language models are few-shot learners,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.704191Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:d9f3ab53b41e77623d00e8738fc8b5a86d1dad48121a1691c1e160046c0b438c","observation_id":"34fb2d6f-e4ba-4c75-8b98-dd0fea7cffe5","resolution":{"observed_at":"2026-08-06T19:13:01.704191Z","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":"2026-08-06T19:13:02.276567Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"6df7153a-b5e7-4b60-a6e5-c0194eac7ade","year":2016},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.709159Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:ac9c21a77661b08da2f1da427abeccf557e43298d7534bcdf3238b725927bf88","observation_id":"07dd447e-efa5-4b35-87b9-5c724e854dc8","resolution":{"observed_at":"2026-08-06T19:13:02.281107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.261245Z","title":"Xnor- net: Imagenet classification using binary convolutional neu- ral networks,","venue":null,"work_id":"71bd8411-5b9a-45b6-8261-1419ea050083","year":2016},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.713951Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:13d9353b7fbaf9d3c25e14a06e3efe0ca255aaf7f73d00f0c3a66e54dee468ae","observation_id":"f83c0eea-22b0-4f71-a1b7-ce071d91ec34","resolution":{"observed_at":"2026-08-06T19:13:02.265640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.01878","last_updated":"2017-11-13T18:40:16Z","snapshot_observed_at":"2026-08-15T03:14:52.303459Z","submitted_at":"2017-10-05T04:26:49Z","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.01878","snapshot_observed_at":"2026-08-06T19:13:01.718617Z","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.718617Z"},"links":{"cited_paper":"/paper/1710.01878","citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:0e3fc7b4c75c014d13d753d3881e03a3855d53998b6fcbe469102e8061f7798c","observation_id":"beb5fc3d-5fae-453a-8b81-133fa10deae7","resolution":{"observed_at":"2026-08-06T19:13:01.718617Z","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":"2026-08-06T19:13:02.246079Z","title":"Low-rank matrix factorization for deep neu- ral network training with high-dimensional output targets,","venue":null,"work_id":"d417dacc-9295-4d54-95b1-d9db9e837b24","year":2013},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.723953Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:3de70e3a94bbcfec109eaf1d97b0bad6234a9db92ce2aa4260949ce30e109699","observation_id":"66e56dd8-4eeb-47fd-944c-72311774dc6b","resolution":{"observed_at":"2026-08-06T19:13:02.250862Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-08-20T09:32:02.065929Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-06T19:13:01.733030Z","title":"Mobilenets: Efficient convolutional neu- ral networks for mobile vision applications,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.733030Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:090de90cde8bb36c3f8df4be78b653c6cabb4dfb8357bc11693f372cb7bd6d90","observation_id":"4fc27185-6b63-4bba-ace9-feec2a734394","resolution":{"observed_at":"2026-08-06T19:13:01.733030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1602.07360","last_updated":"2016-11-04T21:26:08Z","snapshot_observed_at":"2026-08-14T22:09:04.541956Z","submitted_at":"2016-02-24T00:09:45Z","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.07360","snapshot_observed_at":"2026-08-06T19:13:01.737548Z","title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and¡ 0.5 mb model size,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.737548Z"},"links":{"cited_paper":"/paper/1602.07360","citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:aeb70bc0ca71df8f6bad47b7b53b60632e5f4a00b783b1692299b3283773d023","observation_id":"2a323e59-7fcb-4c09-b88c-733fd01a7284","resolution":{"observed_at":"2026-08-06T19:13:01.737548Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.09106","last_updated":"2016-12-01T10:08:15Z","snapshot_observed_at":"2026-08-14T14:43:47.411225Z","submitted_at":"2016-09-27T05:57:00Z","title":"HyperNetworks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.09106","snapshot_observed_at":"2026-08-06T19:13:01.741955Z","title":"Hypernetworks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.741955Z"},"links":{"cited_paper":"/paper/1609.09106","citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:25c37dbd27d904f48a3df9f0b249f3c03d7ec551fa47892f97844d93ca334be5","observation_id":"68f923d3-50d0-4724-b333-6c404ef08f60","resolution":{"observed_at":"2026-08-06T19:13:01.741955Z","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":"2026-08-06T19:13:02.216819Z","title":"Adaptive weight compression for memory-efficient neural net- works,","venue":null,"work_id":"d131c4af-eef1-4a14-b451-1907fa597ce8","year":2017},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.746615Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:2c8af6a09599a16838b57ec9804990cf4e0cab52d341af09a668d1f53fe58774","observation_id":"0bd3f7a9-af6e-493b-a586-57488ed08aff","resolution":{"observed_at":"2026-08-06T19:13:02.221342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1602.02830","last_updated":"2016-03-17T14:54:25Z","snapshot_observed_at":"2026-08-15T07:00:41.403404Z","submitted_at":"2016-02-09T01:01:59Z","title":"Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.02830","snapshot_observed_at":"2026-08-06T19:13:01.750947Z","title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.750947Z"},"links":{"cited_paper":"/paper/1602.02830","citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:e815020379e9766e2be28f7878c5bbd227c2e5c95068f93912cbc6dd75d4d5e9","observation_id":"34ebeef6-b9ec-46be-b591-08ebd593898c","resolution":{"observed_at":"2026-08-06T19:13:01.750947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1510.00149","last_updated":"2016-02-15T06:25:40Z","snapshot_observed_at":"2026-08-04T16:59:47.843960Z","submitted_at":"2015-10-01T09:03:44Z","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.00149","snapshot_observed_at":"2026-08-06T19:13:01.756224Z","title":"Deep compression: Com- pressing deep neural networks with pruning, trained quantiza- tion and huffman coding,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.756224Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:684c3da0de313bcbb44b0064238eff0eba696cba3128902bce53708afd8918c9","observation_id":"7b914718-3074-4635-b75f-71802163e1f0","resolution":{"observed_at":"2026-08-06T19:13:01.756224Z","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":"2026-08-06T19:13:02.201028Z","title":"Flipping bits in memory without accessing them: An experimental study of dram disturbance errors,","venue":null,"work_id":"5332838f-ab73-4adc-9f88-dbabcd945480","year":2014},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.760995Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:eac3636c4eeccad514d255ca760b134bc05d8441ac0053ad2ea8330c2e7cd81d","observation_id":"80751ea6-48ee-4047-b8da-e3ac80621412","resolution":{"observed_at":"2026-08-06T19:13:02.206120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.185849Z","title":"Exploiting correcting codes: On the effectiveness of ecc memory against rowhammer attacks,","venue":null,"work_id":"03f835ba-75fe-4575-934a-f430c5ca81e3","year":2019},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.765735Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:52201682f4505820898ff546e07708ed67874000faf667ee82022136ec261b92","observation_id":"a9884024-4801-4554-b69e-648a38885527","resolution":{"observed_at":"2026-08-06T19:13:02.190504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.170594Z","title":"Defending bit-flip attack through dnn weight reconstruction,","venue":null,"work_id":"544df8c9-89dc-491b-b214-4137074b4a30","year":2020},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.769983Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:c91768a2e5c02c366982d0d52d26f697b436dabffaecd1d01f8de2d9c9adfe52","observation_id":"affa8d60-6e8c-4329-be1a-08480e3b76d9","resolution":{"observed_at":"2026-08-06T19:13:02.175153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.154869Z","title":"Liii. on lines and planes of closest fit to systems of points in space,","venue":null,"work_id":"6e8d3a96-302a-45c1-8790-f7b2b25c1de7","year":1901},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.774079Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:946064035ec6ff6117fb10d6c80742e732950eda40d1e56d529bdeabf6d21eec","observation_id":"756f73bf-e189-4d88-af77-5b972da417e9","resolution":{"observed_at":"2026-08-06T19:13:02.159410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.139230Z","title":"A tutorial on support vector regression,","venue":null,"work_id":"b754e668-ee50-49e4-88f2-109ee784e2c1","year":2004},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.778078Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:64f2bd8e0794da1550715038d8a08c74ef5491cea24c220af341e28e8f863a90","observation_id":"e6e41732-0d9a-4b0d-a8cc-de899afb8bc2","resolution":{"observed_at":"2026-08-06T19:13:02.143879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.123838Z","title":"Secure ai systems: Emerging threats and defense mechanisms,","venue":null,"work_id":"5805e7d5-5da0-43fe-917d-274b543c8e4a","year":2024},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.782216Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:58d90703fcc455b122cad7821f8ab1445d36c6ce0ca55f62fa5bec0832dc4e1f","observation_id":"6a099c69-7759-4d2c-9019-e7f812812075","resolution":{"observed_at":"2026-08-06T19:13:02.128643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.107505Z","title":"Bit-flip attack: Crushing neural network with progressive bit search,","venue":null,"work_id":"b7bd0080-dea1-43e2-a781-2a48afea7781","year":2019},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.786495Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:373901b8290969bfe46e4d33b5140b66552a42f828d5b5f4aac118d080f655a1","observation_id":"b4821d4e-6446-4646-bc10-ff045042a6ec","resolution":{"observed_at":"2026-08-06T19:13:02.112763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.090573Z","title":"Low precision arithmetic for deep learning,","venue":null,"work_id":"66897eda-146e-4c98-b2d2-eeee8ebb88fd","year":2015},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.790629Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:805dcb9f899bda88cce3759794baf025d50862adc4725da2efb6d56aa0fc37c4","observation_id":"4344f63a-c289-4aac-a3c2-ae7a5de486db","resolution":{"observed_at":"2026-08-06T19:13:02.095383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.074377Z","title":null,"venue":null,"work_id":"540ca5aa-9e7c-4792-a0a8-06d119359786","year":2018},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.794832Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:1baf32f926c8939b18a74176b0333efedcbb70df0a48166b9f55fbeee4b73766","observation_id":"2cdf8adf-2fc1-4b32-9fac-9f8c2fb3ac91","resolution":{"observed_at":"2026-08-06T19:13:02.079139Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.056889Z","title":"Eyeriss: An energy-efficient reconfigurable accelerator for deep convo- lutional neural networks,","venue":null,"work_id":"340b4ab1-b910-4b9b-a4e6-f99d7d7e0b90","year":2016},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.798767Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:90bec084b8452d8ea8ebccf54818ea92ce8a0dd950f44a9de8de4fb9d9630304","observation_id":"05ff7f0b-458f-45ea-b099-a2223af92326","resolution":{"observed_at":"2026-08-06T19:13:02.062416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.040293Z","title":"Evolving neural networks in compressed weight space,","venue":null,"work_id":"db0a7ecb-6e4e-4931-9095-3be4d6894bf7","year":2010},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.802755Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:f374f5a44f63cfb052ebae1318fd39064811155d25c7aca449dfa8ade2fcc1e9","observation_id":"1b3bd218-4f4b-476a-9751-32dfd834065f","resolution":{"observed_at":"2026-08-06T19:13:02.045037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.231446Z","title":"Compressing convolutional neural networks in the frequency domain,","venue":null,"work_id":"f265736f-62f7-4a19-a825-db778a8b99b1","year":2016},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.806907Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:9d07fc871a195d39778bc1bc268c0e82533f3aa1e488a373a13467d0b546a3b0","observation_id":"421dd2c6-aa5e-4726-a8f9-7ed9d8b703d7","resolution":{"observed_at":"2026-08-06T19:13:02.235747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:02.023344Z","title":"Simplifying deep neural networks for neuromorphic architectures,","venue":null,"work_id":"2afed83d-a9d4-4285-8ad5-f0f13928effe","year":2016},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.811314Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:4a64605d95091306c363560dd3b77474f7821f45be46e86f8ebf803e8bab23ae","observation_id":"c6273426-5331-4e98-b752-4482581a8390","resolution":{"observed_at":"2026-08-06T19:13:02.028694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:13:01.815597Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.815597Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:c7d13120af3b9b4bd4cb580834c70af99b3e06f9e065f6a9b0ecd1fefbd629c9","observation_id":"30127c5a-9b5b-4ace-b64d-26741aca10df","resolution":{"observed_at":"2026-08-06T19:13:01.815597Z","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":"2026-08-06T19:13:01.993098Z","title":"Low precision arithmetic for deep learning","venue":null,"work_id":"78548723-f17e-4f56-8d1c-855a465e8956","year":2015},"citing_paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T19:13:01.820101Z"},"links":{"citing_paper":"/paper/2507.06380"},"observation_digest":"sha256:27ed2d5dae99e38376e83907b4387786d7992c3a3d6941a716b75a8789a8e5d0","observation_id":"f0059712-068d-4831-9b1f-971e7d65ec13","resolution":{"observed_at":"2026-08-06T19:13:02.000381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.06380","last_updated":"2025-07-08T20:33:02Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T07:41:29.734308Z","submitted_at":"2025-07-08T20:33:02Z","title":"Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":0,"verified_fuzzy":18},"total_outbound_references":28},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2507.06380."}