{"as_of":"2026-08-08T03:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:350948a12d8b6924b2dd0e6459ea7652a031386c8bb605cda6738e2391b248ae","coverage":[{"denominator":53,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":53,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T05:07:36.359971Z","state":"measured"},{"denominator":53,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":53,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2508.02313/citation-record","integrity":"/paper/2508.02313/integrity","json":"/paper/2508.02313/citation-record.json","paper":"/paper/2508.02313"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T05:07:31.270439Z","title":"Mask r-cnn,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:31.270439Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:ca1c3116ebc522c43285864442712d6e11dda12d94fed4a784ccaf0133a7faa3","observation_id":"dbd1fd61-f92b-4299-97ef-7f54422ae08c","resolution":{"observed_at":"2026-08-06T05:07:31.270439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-06T05:07:31.352049Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:31.352049Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:ebe160450bbb1547f121a7f857c098969ffc3c7c7c3a77371335fac4ba425900","observation_id":"43403454-551f-4aba-905d-9ad98ce32889","resolution":{"observed_at":"2026-08-06T05:07:31.352049Z","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":"2026-08-06T05:07:31.419584Z","title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:31.419584Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:1eb9104745d8fbeb1a5b833dff280ccf4be2be9641de6196a8520c30d2fa25c3","observation_id":"dc395176-2262-4296-b144-0d56a14fbdf2","resolution":{"observed_at":"2026-08-06T05:07:31.419584Z","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":"2026-08-06T05:07:31.538928Z","title":"An energy-and-area-efficient cnn accelerator for universal powers-of- two quantization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:31.538928Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:e5c7fc6f2146888507f54fae026a5d45cd9e7207b125696fb5012a36d890a45a","observation_id":"5415d469-8468-4b20-af33-3b3c1deedf73","resolution":{"observed_at":"2026-08-06T05:07:31.538928Z","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":"2026-08-06T05:07:31.603936Z","title":"Remap: A spatiotemporal cnn accelerator optimization methodology and toolkit thereof,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:31.603936Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:4898b414982447ce3b1616faa1d28971d708387499cd663c2945c539405fb296","observation_id":"bdfdd33e-66e7-4c1a-a351-389f6bde408a","resolution":{"observed_at":"2026-08-06T05:07:31.603936Z","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":"2026-08-06T05:07:31.695329Z","title":"Hipu: A hybrid intelligent processing unit with fine-grained isa for real-time deep neural network inference applications,","venue":null,"work_id":null,"year":1980},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:31.695329Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:26606c0c63a87ff972612811368a6de594485f85d28aed1eb0e3f21124288a9e","observation_id":"9a5a660d-e9ea-4cc8-98ce-0b23aef736b2","resolution":{"observed_at":"2026-08-06T05:07:31.695329Z","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":"2026-08-06T05:07:31.791235Z","title":"Efficient dataset distillation using random feature approximation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:31.791235Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:8d71c0ad9548e39c3c1a14d239616acc10db3f6a1d367c1ed170cb90809f2a59","observation_id":"804fc491-009e-4157-b4e2-21311207dd24","resolution":{"observed_at":"2026-08-06T05:07:31.791235Z","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":"2026-08-06T05:07:31.856541Z","title":"Scaling up dataset distillation to imagenet-1k with constant memory,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:31.856541Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:89e436a1ca07a23d0c22db5e3d8aa917a625291b96bfec6cdb250813bae2d286","observation_id":"2cb090b6-bbd8-44da-bf7a-4399d65b9a0c","resolution":{"observed_at":"2026-08-06T05:07:31.856541Z","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":"2026-08-06T05:07:31.945880Z","title":"Improved distribution matching for dataset condensation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:31.945880Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:f12f74377b5d55d811d58a9a2c47e933ed2b31d51bd83ff01b9a0e46eecfa5d1","observation_id":"be3ec822-b08a-4985-bcfb-da444af19298","resolution":{"observed_at":"2026-08-06T05:07:31.945880Z","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":"2026-08-06T05:07:32.020444Z","title":"Gen- eralizing dataset distillation via deep generative prior,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:32.020444Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:5da40e46e091424bdc24cb5f2d547d67ad34294177f5ee9c3b9748f0bf645a65","observation_id":"7ffb85eb-d709-4a1b-aadd-2387f1d43012","resolution":{"observed_at":"2026-08-06T05:07:32.020444Z","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":"2026-08-06T05:07:32.070751Z","title":"Dataset condensation with distribution match- ing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:32.070751Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:695c9fa19f1755951709fc931f017cb88ee83a06b7ed56c842fdce5344152ab7","observation_id":"3a514740-8fe1-47ec-a1e3-b4c54972a68e","resolution":{"observed_at":"2026-08-06T05:07:32.070751Z","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":"2026-08-06T05:07:32.075436Z","title":"Dataset quantization,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:32.075436Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:f47d76608cc663aa97b73f8166abcdd45cf31b1f5e2cc14827e7dfd3ded34310","observation_id":"074369bc-a293-4f16-ac38-8bb7e58fbf5a","resolution":{"observed_at":"2026-08-06T05:07:32.075436Z","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":"2026-08-06T05:07:32.164645Z","title":"Nonlinear manifold learning in functional magnetic resonance imaging uncovers a low-dimensional space of brain dynamics,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:32.164645Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:2155ad2f5f8c9a78b9878ada34a2565ff619ea798f0f302c288b528d73a46c84","observation_id":"6785768e-caed-44d8-a854-df642063aab1","resolution":{"observed_at":"2026-08-06T05:07:32.164645Z","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":"2026-08-06T05:07:32.262070Z","title":"The manifold ways of perception,","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:32.262070Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:5990f9dba8bc72c55b350346a8d960322b7c141603acc749d53db44b8a070e94","observation_id":"8df2ed58-d99c-484d-bef5-cb890d6498fc","resolution":{"observed_at":"2026-08-06T05:07:32.262070Z","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":"2026-08-06T05:07:32.412199Z","title":"Nonlinear dimensionality reduction by locally linear embedding,","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:32.412199Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:9ffd43d6f80876f5a3f7660a85d45d51e324aebf42334f977ecbe4b61581aa19","observation_id":"155acea7-94d3-4abd-b605-87db3b7ea948","resolution":{"observed_at":"2026-08-06T05:07:32.412199Z","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":"2026-08-06T05:07:32.494948Z","title":"A global geometric framework for nonlinear dimensionality reduction,","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:32.494948Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:7be54e50fcee43e89278aeed5c9625a68fedb15c06ea71db4102ecbfd47cfe89","observation_id":"6d2b763c-e8de-42a7-9ad0-8c913874490e","resolution":{"observed_at":"2026-08-06T05:07:32.494948Z","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":"2026-08-06T05:07:32.584462Z","title":"Decoding brain states on the intrinsic manifold of human brain dynamics across wakefulness and sleep,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:32.584462Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:9f3dea896ff20dd2db29dc9a10778d3d2f5930327908c7ce7dc317bc59dc473e","observation_id":"9f63de14-e4a2-4a75-bbaf-2a9055c5a405","resolution":{"observed_at":"2026-08-06T05:07:32.584462Z","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":"2026-08-06T05:07:32.682701Z","title":"Visualizing data using t-sne","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:32.682701Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:d281d0ca23fca1af82d4315312733ba55c34239537fe7dffabf03a9942a7f87f","observation_id":"3504c83f-a9b1-4aec-bac8-84327ecabaa0","resolution":{"observed_at":"2026-08-06T05:07:32.682701Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.10959","last_updated":"2020-02-24T23:25:50Z","snapshot_observed_at":"2026-07-06T07:17:20.813296Z","submitted_at":"2018-11-27T13:17:45Z","title":"Dataset Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.10959","snapshot_observed_at":"2026-08-06T05:07:32.797187Z","title":"Dataset distillation,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:32.797187Z"},"links":{"cited_paper":"/paper/1811.10959","citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:c424e63ca04ed618aeee665d2b02c9c0bd9ac59acec553239638546e74b8cc99","observation_id":"c7432ae8-5c02-4023-9f3d-ef5140f46b63","resolution":{"observed_at":"2026-08-06T05:07:32.797187Z","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":"2026-08-06T05:07:32.906769Z","title":"Remember the past: Distilling datasets into addressable memories for neural networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:32.906769Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:e1aa8e66b3411bbc00dd03918408edac6c7b70711d20e2fd086160d5bba8ce6c","observation_id":"61138910-cd05-44cc-abf7-adaf2ef5a3c6","resolution":{"observed_at":"2026-08-06T05:07:32.906769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05929","last_updated":"2021-03-08T13:31:22Z","snapshot_observed_at":"2026-08-06T01:24:57.284854Z","submitted_at":"2020-06-10T16:30:52Z","title":"Dataset Condensation with Gradient Matching","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.05929","snapshot_observed_at":"2026-08-06T05:07:33.022330Z","title":"Dataset condensation with gradient matching,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:33.022330Z"},"links":{"cited_paper":"/paper/2006.05929","citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:7863fca6ac8f464681c29b78c527a53a0d5246a10054e29487e068fe62ab8ad9","observation_id":"de36f59c-c5ec-4c9c-9777-d64385dc0e8e","resolution":{"observed_at":"2026-08-06T05:07:33.022330Z","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":"2026-08-06T05:07:33.098902Z","title":"Dataset condensation via efficient synthetic-data parame- terization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:33.098902Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:76b5cb1677d365516a07c181f85cf798c595bc0ebc7d538f06ec7ce5d80167d9","observation_id":"13350724-02c0-43ae-9043-3c0f3f33635d","resolution":{"observed_at":"2026-08-06T05:07:33.098902Z","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":"2026-08-06T05:07:33.253964Z","title":"Dream: Efficient dataset distillation by representative matching,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:33.253964Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:4a80549b2b49068d7c17015f0d1efb73a1b825f092d87dd53617a7ad2a2b9ef4","observation_id":"bffcd85c-cd07-4998-b03c-aa8d6b337ba9","resolution":{"observed_at":"2026-08-06T05:07:33.253964Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.00489","last_updated":"2018-06-01T10:17:23Z","snapshot_observed_at":"2026-07-06T05:53:39.440274Z","submitted_at":"2017-08-01T19:50:53Z","title":"Active Learning for Convolutional Neural Networks: A Core-Set Approach","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.00489","snapshot_observed_at":"2026-08-06T05:07:33.419803Z","title":"Active learning for convolutional neural networks: A core-set approach,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:33.419803Z"},"links":{"cited_paper":"/paper/1708.00489","citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:411fbbf4db3c502b37d86fa43a928c911b78dbedf543b7384313f5c26b70da68","observation_id":"ba8f8318-8b2e-4792-9fda-480f59329d97","resolution":{"observed_at":"2026-08-06T05:07:33.419803Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1203.3472","last_updated":"2012-03-15T11:17:56Z","snapshot_observed_at":"2026-07-06T02:44:38.546504Z","submitted_at":"2012-03-15T11:17:56Z","title":"Super-Samples from Kernel Herding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1203.3472","snapshot_observed_at":"2026-08-06T05:07:33.593042Z","title":"Super-samples from kernel herding,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:33.593042Z"},"links":{"cited_paper":"/paper/1203.3472","citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:c48c004c13136afc51518890891deab862cb7aec0e56491b04b748ee254c9d75","observation_id":"c02c6498-463f-4bc7-93c2-c4354ab4e364","resolution":{"observed_at":"2026-08-06T05:07:33.593042Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.05159","last_updated":"2019-11-15T17:08:30Z","snapshot_observed_at":"2026-08-01T06:33:25.731787Z","submitted_at":"2018-12-12T21:24:15Z","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.05159","snapshot_observed_at":"2026-08-06T05:07:33.758978Z","title":"An empirical study of example forgetting during deep neural network learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:33.758978Z"},"links":{"cited_paper":"/paper/1812.05159","citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:84a24f8d2c6d0575f8c8afdcb2104f2912c84baf7228528aa4e1f8eedc4ca86f","observation_id":"49129e65-821b-4ebc-b249-e4768b896a5a","resolution":{"observed_at":"2026-08-06T05:07:33.758978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.03764","last_updated":"2021-09-08T16:40:18Z","snapshot_observed_at":"2026-08-06T03:32:43.504624Z","submitted_at":"2021-09-08T16:40:18Z","title":"Active Learning by Acquiring Contrastive Examples","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.03764","snapshot_observed_at":"2026-08-06T05:07:33.937652Z","title":"Active learning by acquiring contrastive examples,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:33.937652Z"},"links":{"cited_paper":"/paper/2109.03764","citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:25c321715b2e2fff085096646cc0135ef636d41226be8367673cfe948fdab698","observation_id":"c326f030-54f7-4cc0-b9ac-32a087157bad","resolution":{"observed_at":"2026-08-06T05:07:33.937652Z","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":"2026-08-06T05:07:34.039384Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:34.039384Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:e26847c157e0d6bc389852a6decb72389d22ee198bd5b0e406f7cc33d5c8ccda","observation_id":"b717d086-62b1-41ce-a6fa-bb36fda38222","resolution":{"observed_at":"2026-08-06T05:07:34.039384Z","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":"2026-08-06T05:07:34.149737Z","title":"Nessa: Near-storage data selection for accelerated machine learning training,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:34.149737Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:b20a8c354717cbca116e9ef1b220fea8a753ea75a4a897e15ee4fc4ad206f4c9","observation_id":"19d69843-cdfd-4cbb-af1f-ac16addd4ef6","resolution":{"observed_at":"2026-08-06T05:07:34.149737Z","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":"2026-08-06T05:07:34.323987Z","title":"Principal components analysis (pca),","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:34.323987Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:8f6297e25bbf0520bbac2faa1f0cef02eb67b1199b4b8b56aa0c5d019355f567","observation_id":"809ffe6b-9656-4131-bc46-c0fb2c63e407","resolution":{"observed_at":"2026-08-06T05:07:34.323987Z","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":"2026-08-06T05:07:34.441996Z","title":"Linear discriminant analysis,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:34.441996Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:1f0c712eaf9638af29d411619d1d06195068474737777a0d4ba8c4a1c621e686","observation_id":"11184579-a69b-46bd-9b41-f9b3a1be2cf3","resolution":{"observed_at":"2026-08-06T05:07:34.441996Z","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":"2026-08-06T05:07:34.542496Z","title":"Development of a multi-dimensional scale for measuring the perceived value of a service,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:34.542496Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:151d5fde7f83ca67e20f3df7e3baaab8d8facb6b53ad63e2ffb0b79a723791b6","observation_id":"43e68f70-601e-401e-9157-2c18ce1a7676","resolution":{"observed_at":"2026-08-06T05:07:34.542496Z","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":"2026-08-06T05:07:34.674041Z","title":"Selection of the optimal parameter value for the isomap algorithm,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:34.674041Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:9fa8a172e7a1273ef6ff973dbff307ebeb91ce75b5d5170443b44a14d260c5a6","observation_id":"1248b2ae-bc73-44aa-911f-f6b38bf2bfdf","resolution":{"observed_at":"2026-08-06T05:07:34.674041Z","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":"2026-08-06T05:07:34.725110Z","title":"Nonlinear dimensionality reduction by locally linear embedding,","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:34.725110Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:f05d65180a8d1fd9b6d5091f604bed14c992f8112783cf58f64950972947a968","observation_id":"9ed2d5d9-c330-4a52-a2c6-a57429e984c1","resolution":{"observed_at":"2026-08-06T05:07:34.725110Z","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":"2026-08-06T05:07:34.821738Z","title":"Laplacian eigenmaps for dimensionality reduction and data representation,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:34.821738Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:63b1e9c044f9cd0eb97290c3fd486a7160d4c348e9a001dce6a7e71fc4c6de10","observation_id":"6e242bb5-4b5a-47cd-b325-447c52e9bd83","resolution":{"observed_at":"2026-08-06T05:07:34.821738Z","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":"2026-08-06T05:07:34.886627Z","title":"Feoktistov, Differential evolution","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:34.886627Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:b7681263a16c0c1115047a6a4e4e172447fa3ae9ebfc40e1a5b6658474545ffc","observation_id":"ffd72804-e600-41d5-b461-dcc4dba19231","resolution":{"observed_at":"2026-08-06T05:07:34.886627Z","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":"2026-08-06T05:07:34.948461Z","title":"Resource-aware distributed dif- ferential evolution for training expensive neural-network-based controller in power electronic circuit,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:34.948461Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:8bc2ca9395f10027cb5308881ac4c6d878739fd6c25570730ebdc62e0194261d","observation_id":"82f45ec5-7676-4354-b904-e3728cf85b5d","resolution":{"observed_at":"2026-08-06T05:07:34.948461Z","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":"2026-08-06T05:07:35.040702Z","title":"Hardware implemen- tation of multi-objective differential evolution algorithm: a case study of spectrum allocation in cognitive radio networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.040702Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:3dfc75bbd030ef55574785c1735ae754e9911b21427197d5f9596e6840c80d4e","observation_id":"2f7beb24-4274-414c-b506-64a104b8ae44","resolution":{"observed_at":"2026-08-06T05:07:35.040702Z","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":"2026-08-06T05:07:35.112281Z","title":"Field programmable gate arrays-based differential evolu- tion coprocessor: a case study of spectrum allocation in cognitive radio network,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.112281Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:f16377c14c5dfc5a11524af04af6ee4daeb518bdb3e2deb2e59544bf9a4a3804","observation_id":"3fa3e39a-711b-4224-8548-d0a92f1cf1d3","resolution":{"observed_at":"2026-08-06T05:07:35.112281Z","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":"2026-08-06T05:07:35.172080Z","title":"Soc based floating point implementation of differential evolution algorithm using fpga,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.172080Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:fdca54f615d45455ecb08361177dc6f7367486a2d31e91b58bba2fb9c6a46008","observation_id":"20b26573-0f6e-4309-b51d-54485d4f827c","resolution":{"observed_at":"2026-08-06T05:07:35.172080Z","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":"2026-08-06T05:07:35.261391Z","title":"Performance evalua- tion of floating point differential evolution hardware accelerator on fpga,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.261391Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:01ee12408ebe11d10e39323f9bc41d8b2ed547c76fdfc96d06f1cc2349ee1ab5","observation_id":"7108d477-3eb3-41fa-acad-29488cd471b3","resolution":{"observed_at":"2026-08-06T05:07:35.261391Z","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":"2026-08-06T05:07:35.327264Z","title":"Solving the nonlinear power flow equa- tions with an inexact newton method using gmres,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.327264Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:c1193afb2faf53f8162c084f8c0f818eedc07b5261600d1be3f7dec10ea822e8","observation_id":"0c23d3af-d6a9-4ac9-a208-89535136c904","resolution":{"observed_at":"2026-08-06T05:07:35.327264Z","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":"2026-08-06T05:07:35.446662Z","title":"Universal chiplet interconnect express (ucie): An open industry standard for innovations with chiplets at package level,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.446662Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:65861d706626f96d224db740d6cd53f80e9431663651a535622fcf2b9bfb301a","observation_id":"58856997-5ecd-4d68-bb44-b2e7fde05ea9","resolution":{"observed_at":"2026-08-06T05:07:35.446662Z","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":"2026-08-06T05:07:35.539726Z","title":"Pci express*(pcie*) 3.0 accelerator features,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.539726Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:e0e6fb7152cae583857500b891704db31904d6dc5ed86c53c8222a43531ab8eb","observation_id":"1c870db3-c046-440f-b8db-3a3438e7152d","resolution":{"observed_at":"2026-08-06T05:07:35.539726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07268","last_updated":"2024-07-09T23:09:18Z","snapshot_observed_at":"2026-08-08T02:44:29.961173Z","submitted_at":"2024-07-09T23:09:18Z","title":"Dataset Quantization with Active Learning based Adaptive Sampling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07268","snapshot_observed_at":"2026-08-06T05:07:35.639610Z","title":"Dataset quantization with active learning based adaptive sampling,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.639610Z"},"links":{"cited_paper":"/paper/2407.07268","citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:86665fb0e84d0aca24244d45a573e7bf3cb11164e2a37b544133e0da83301fe2","observation_id":"5bacc2a3-0e62-4c31-9a0b-3d9efb94533d","resolution":{"observed_at":"2026-08-06T05:07:35.639610Z","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":"2026-08-06T05:07:35.740602Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.740602Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:be6f1c831543ac149faf0fb7e2b0eeac53159f85cbed8ba134d81735ddb5187b","observation_id":"0e5b865d-c5d4-425d-a88e-2290cf1e3ede","resolution":{"observed_at":"2026-08-06T05:07:35.740602Z","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":"2026-08-06T05:07:35.836222Z","title":"Cacti 7: New tools for interconnect exploration in innovative off-chip memories,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.836222Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:96f5598d30fd3797fcc7f5ce52a4d1fe841e1eb824fb262c74c1ce30d46a2803","observation_id":"e6a59fcf-f78a-46bc-88bd-929c015ee938","resolution":{"observed_at":"2026-08-06T05:07:35.836222Z","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":"2026-08-06T05:07:35.905870Z","title":"Theta: A high-efficiency training accel- erator for dnns with triple-side sparsity exploration,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.905870Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:6a2f6fcd1c08295f387cd58246a60089b5c98e53c75536e89e2259a70cdeaacd","observation_id":"2ac17e99-7db4-4ab3-9d52-9ec0acd83e39","resolution":{"observed_at":"2026-08-06T05:07:35.905870Z","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":"2026-08-06T05:07:35.993625Z","title":"Generalized binary search,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:35.993625Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:c1817b571642e574d1ae1ac90f327247136841202d29ea7eaf6e13ba2b8307be","observation_id":"a9f041bc-26fb-48aa-b54f-4ce5327322df","resolution":{"observed_at":"2026-08-06T05:07:35.993625Z","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":"2026-08-06T05:07:36.086624Z","title":"Simulated annealing,","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:36.086624Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:e099ed1fc2ea6886cc49b138fd6af95a3448ae8b17cbf91f71e76e4a96bf5aa9","observation_id":"7a1878ac-0a1c-4147-a94f-f306849b7c5d","resolution":{"observed_at":"2026-08-06T05:07:36.086624Z","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":"2026-08-06T05:07:36.191772Z","title":"Genetic algorithms,","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:36.191772Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:4ef63d4c568539422d8d795016be2f0ea9aaab9bc5850f478e5976c85c79359b","observation_id":"0864228a-da81-4ca1-abe0-2da743c254f8","resolution":{"observed_at":"2026-08-06T05:07:36.191772Z","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":"2026-08-06T05:07:36.288240Z","title":"Particle swarm optimization,","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:36.288240Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:f9e9118888d89a40f188f5556cbc91eaeccf1f043917f99e65f8c7899949fafb","observation_id":"c66744fa-79b9-4da2-94c2-a5f35207653b","resolution":{"observed_at":"2026-08-06T05:07:36.288240Z","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":"2026-08-06T05:07:36.359971Z","title":"Ant colony optimization,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T05:07:36.359971Z"},"links":{"citing_paper":"/paper/2508.02313"},"observation_digest":"sha256:d3319614630be0b254f7bd14b1c3d49aa2db91d38f6af11bb45404f8a4f08423","observation_id":"ad1be703-d25a-4fae-8c26-e6a9e7a9bb0a","resolution":{"observed_at":"2026-08-06T05:07:36.359971Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2508.02313","last_updated":"2025-08-04T11:29:47Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T05:07:28.806194Z","submitted_at":"2025-08-04T11:29:47Z","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds"},"reference_resolution":{"displayed":53,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":53,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":53},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 0 inbound Pith citation observations for arXiv:2508.02313."}