{"as_of":"2026-08-13T05:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:610df36cc438fc5c613040df9b6a538870b9110acb2b91ef9d3ef7cf8e4a455d","coverage":[{"denominator":68,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":68,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T05:09:32.743406Z","state":"measured"},{"denominator":68,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":68,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.00724/citation-record","integrity":"/paper/2412.00724/integrity","json":"/paper/2412.00724/citation-record.json","paper":"/paper/2412.00724"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T05:09:33.859505Z","title":"Autonomous driving assistance with dynamic objects using traffic surveillance cameras,","venue":null,"work_id":"7dd8d3f6-7a26-4d9f-9361-50d998a883ce","year":2022},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.422546Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:909cfa9c2e7bd9405a89b02a08642ec665b195cba87f16fecfe6f33f8019822e","observation_id":"04bc977c-8e79-4885-9a8b-011142fb6b71","resolution":{"observed_at":"2026-08-12T05:09:33.864344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.843382Z","title":"Roadside infrastructure support for urban automated driving,","venue":null,"work_id":"c4a1888d-ead6-44fe-99b0-d8077c0e823d","year":2023},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.427661Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:7b659421b5dbc454aee38507f5d7518849ce3c79e20fadcabea42545ce6cfb43","observation_id":"816160be-c6c1-4512-a3c3-69151fe132c3","resolution":{"observed_at":"2026-08-12T05:09:33.848907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.826036Z","title":"Enabling resource-efficient aiot system with cross-level optimization: A survey,","venue":null,"work_id":"1a2e2f0e-91ed-40eb-8d7a-d54c00c6a0b0","year":2023},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.432765Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:d855afa535984d36343693a22688cf9d9eb072ab246afdf800776a9449d84fa9","observation_id":"e4467cfb-9487-498c-95a7-8f61e9168af7","resolution":{"observed_at":"2026-08-12T05:09:33.832006Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.808331Z","title":"Surgical and medical applications of drones: A comprehensive review,","venue":null,"work_id":"7ad9e30f-8b7c-4ef6-bdc7-92e2e71cc7c7","year":2018},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.437465Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:1bbfd67e531a0e33039f1660aee488f45eccadab2f7fdad58102f012a10c12d0","observation_id":"1c4bb043-cbf7-4a0b-89ce-3f15ba30d204","resolution":{"observed_at":"2026-08-12T05:09:33.813615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.793147Z","title":"A survey on behav- ioral biometric authentication on smartphones,","venue":null,"work_id":"bb946aec-634d-49c7-a922-af6ad9e092b1","year":2017},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.443020Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:1619cb42c4279e808885bf8748e6a5fbae11d0803c3ce2e93630e6dfcc542d31","observation_id":"1b6d6f99-d125-4cdb-b1f1-c800404e08a3","resolution":{"observed_at":"2026-08-12T05:09:33.798034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.777610Z","title":"Moodexplorer: Towards com- pound emotion detection via smartphone sensing,","venue":null,"work_id":"ff4f3f9b-1b46-489f-ba11-8eb4ec584f03","year":2018},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.447700Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:089bbecb208d224736ed8d66bf73011a464e2bb16dbce9797e870b80f7ec9fe8","observation_id":"75554145-9361-49a5-8158-addb778cf266","resolution":{"observed_at":"2026-08-12T05:09:33.782569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.667071Z","title":"Attrleaks on the edge: Exploiting information leakage from privacy-preserving co- inference,","venue":null,"work_id":"67953471-78dc-4ac8-b99c-4f391b16af4a","year":2023},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.453211Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:28c4315531d05766908224ebe2bf7874f3c8763558662f0797c4cca31f790764","observation_id":"debd9c5b-8deb-4b98-ace9-2ac531a8cecf","resolution":{"observed_at":"2026-08-12T05:09:33.671823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.650359Z","title":"nnperf: Demystifying dnn runtime inference latency on mobile platforms,","venue":null,"work_id":"f214f675-6397-44d7-8a9d-a9c0f2f5afb1","year":2023},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.457912Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:ce6ddd87cac2c0ad01ba77426bac4b4ba11344f2d94436b871b0b02b73c60040","observation_id":"ad397744-e4e1-43ce-a2a5-a68d08e1cee2","resolution":{"observed_at":"2026-08-12T05:09:33.656087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:32.463004Z","title":"Deep learning on mobile and embedded devices: State-of-the-art, challenges, and future directions,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.463004Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:0e1fcc08dd78a2790846425c81575057360c332b9a04668a04f0a4a9c9760938","observation_id":"50092d7f-7187-4357-b10c-a5056dd7faf1","resolution":{"observed_at":"2026-08-12T05:09:32.463004Z","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":"2026-08-12T05:09:33.624641Z","title":"Adaspring: Context- adaptive and runtime-evolutionary deep model compression for mobile applications,","venue":null,"work_id":"d75a5bbe-7b92-4ceb-ba30-0213fb7aecfb","year":2021},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.467861Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:8a985c8e39e2f635055d8ad8743099455f8a39fb4ca9028beb4513e2f219d7f0","observation_id":"d3e85fbf-3c96-4b93-b2b3-8f1cfe3ff3c9","resolution":{"observed_at":"2026-08-12T05:09:33.629779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.609435Z","title":"Adaptive weight compression for memory-efficient neural networks,","venue":null,"work_id":"5ca96249-61e4-4fd3-af4c-b6741c765672","year":2017},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.473308Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:c459688590b40f95de9c706c9eec234508f354ec3770ce6cd3b83c9de77372ef","observation_id":"828f3f20-86ba-45b5-ae1f-e7a3a37c5310","resolution":{"observed_at":"2026-08-12T05:09:33.614233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.02861","last_updated":"2022-06-20T16:05:15Z","snapshot_observed_at":"2026-08-12T09:32:12.775317Z","submitted_at":"2021-10-06T15:43:20Z","title":"8-bit Optimizers via Block-wise Quantization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.02861","snapshot_observed_at":"2026-08-12T05:09:32.477647Z","title":"8-bit optimizers via block-wise quantization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.477647Z"},"links":{"cited_paper":"/paper/2110.02861","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:07ddb8c00ed1d8874b4be920b541c89f700bd8fd768977811dc78fb568ea467d","observation_id":"bf204469-eab7-4e1c-b3af-16f1d15f1dfe","resolution":{"observed_at":"2026-08-12T05:09:32.477647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.09595","last_updated":"2019-12-01T06:29:57Z","snapshot_observed_at":"2026-08-09T20:08:35.724977Z","submitted_at":"2019-07-22T21:49:25Z","title":"MixConv: Mixed Depthwise Convolutional Kernels","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.09595","snapshot_observed_at":"2026-08-12T05:09:32.482533Z","title":"Mixconv: Mixed depthwise convolutional kernels,","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.482533Z"},"links":{"cited_paper":"/paper/1907.09595","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:cf71edd169959785c956adf03b7bac77e53bead533c5e6f2a861618728898585","observation_id":"8d4721a6-2063-4ac3-913e-d8766d1ec2de","resolution":{"observed_at":"2026-08-12T05:09:32.482533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08256","last_updated":"2024-10-10T16:41:39Z","snapshot_observed_at":"2026-08-12T22:26:09.218283Z","submitted_at":"2024-10-10T16:41:39Z","title":"AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments","version":1},"cited_work":{"arxiv_id":"2410.08256","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.08256","snapshot_observed_at":"2026-08-12T05:09:32.974347Z","title":"AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments","venue":"cs.LG","work_id":"4947dece-f2c2-4f41-91a3-a45c6cbfc706","year":2024},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.487541Z"},"links":{"cited_paper":"/paper/2410.08256","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:566d984bbcfb3528fdb8d9c7c0d824000528761848ec017212506f2ea26fb8a5","observation_id":"79f52c2a-b0ee-41a8-86d7-a5d3a63aa9d4","resolution":{"observed_at":"2026-08-12T05:09:32.979939Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.592987Z","title":"Inceptionnext: When inception meets convnext,","venue":null,"work_id":"c1776235-dab7-4789-aa4d-9e032b19e506","year":2024},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.492801Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:ae56ff9be933315a1b021c8f663c18f6b42a7bc2a5da758abf193cb2cf518ec8","observation_id":"94771823-fc97-493e-96a9-5ade8875f6cf","resolution":{"observed_at":"2026-08-12T05:09:33.598834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:32.497924Z","title":"Dynamic convolution: Attention over convolution kernels,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.497924Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:dd0282317697b9d674abc08c3962c2f0c0bab7c12f2012b945ff40e2fb58a755","observation_id":"9e01a1bc-535f-4985-8e04-3d5be27b3e49","resolution":{"observed_at":"2026-08-12T05:09:32.497924Z","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":"2026-08-12T05:09:33.567119Z","title":"Deep guided attention network for joint denoising and demosaicing in real image,","venue":null,"work_id":"7abcb191-c134-4089-aa04-5f407c4b6e53","year":2024},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.502066Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:7298d4066e07b8dfbff137ae4899cf41ba095ce23af23abdec6742584058eded","observation_id":"e447b402-607e-4640-8439-9f952335c4f7","resolution":{"observed_at":"2026-08-12T05:09:33.572076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.550468Z","title":"Adaknife: Flexible dnn offloading for inference acceleration on heterogeneous mobile devices,","venue":null,"work_id":"4fe93eb2-da14-4bbb-83df-530dac0d154f","year":2024},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.507237Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:386fe8b4c892ca81ecdded620c6be86dce5cf7114b8e73906cc9f453b175b8fb","observation_id":"4300b69b-6ba1-4a9f-953f-ffccffdfb4f1","resolution":{"observed_at":"2026-08-12T05:09:33.555461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.533848Z","title":"Context-aware adaptive surgery: A fast and effective framework for adaptative model partition,","venue":null,"work_id":"21d39011-7b84-48c5-b25c-53b0c2c54316","year":2021},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.511592Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:78a1d73ace90ae7eb349a7bfb9010075618ecf77a13f32c3139f113d11a93bb6","observation_id":"4155a60e-a47f-4bab-a5c4-c0dc6af1c9d7","resolution":{"observed_at":"2026-08-12T05:09:33.539587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.09791","last_updated":"2020-04-29T20:49:05Z","snapshot_observed_at":"2026-08-11T01:59:17.823546Z","submitted_at":"2019-08-26T16:46:23Z","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.09791","snapshot_observed_at":"2026-08-12T05:09:32.516544Z","title":"Once-for-all: Train one network and specialize it for efficient deployment,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.516544Z"},"links":{"cited_paper":"/paper/1908.09791","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:4c6b72de51332c405a89c1b2c854824776ee6508bb316f6e451af2c0e399b032","observation_id":"186dd8cc-84a7-4290-afd7-b17851c39faa","resolution":{"observed_at":"2026-08-12T05:09:32.516544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00332","last_updated":"2019-02-23T01:36:47Z","snapshot_observed_at":"2026-08-10T08:54:59.663457Z","submitted_at":"2018-12-02T05:29:53Z","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00332","snapshot_observed_at":"2026-08-12T05:09:32.521617Z","title":"Proxylessnas: Direct neural architecture search on target task and hardware,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.521617Z"},"links":{"cited_paper":"/paper/1812.00332","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:1559b6fb5260b8388ca8f8bca8bac0d1d191851fdd095f4bcb93c56c84375b5e","observation_id":"299eacda-315f-46a4-bfd8-dbc035d9ecdd","resolution":{"observed_at":"2026-08-12T05:09:32.521617Z","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":"2026-08-12T05:09:32.526305Z","title":"Progressive neural architecture search,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.526305Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:0026aeefd8407fd5b768326694ae1399c9d7ec9d602afb2d9daec8449f5a12a9","observation_id":"04a2f2c0-917a-4fbd-98a3-f73d017d87da","resolution":{"observed_at":"2026-08-12T05:09:32.526305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.09055","last_updated":"2019-04-23T06:29:32Z","snapshot_observed_at":"2026-08-09T13:23:20.015254Z","submitted_at":"2018-06-24T00:06:13Z","title":"DARTS: Differentiable Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.09055","snapshot_observed_at":"2026-08-12T05:09:32.531623Z","title":"Darts: Differentiable architecture search,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.531623Z"},"links":{"cited_paper":"/paper/1806.09055","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:8b88f3880430118da8e98a7d5a6ec70a6eaa220c1bd0e94b8474e5b4d5113c59","observation_id":"1a39abe3-50e5-4733-9257-f39dd1e63c1a","resolution":{"observed_at":"2026-08-12T05:09:32.531623Z","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":"2026-08-12T05:09:33.508405Z","title":"Adaptivenet: Post-deployment neural architecture adaptation for diverse edge environments,","venue":null,"work_id":"1ca509a3-aef0-4d57-af3e-efd6593ea820","year":2023},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.536441Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:154e9ab06238c1cf770e780ce9f191e4865bffec6e7f23c72adecabf2e754a89","observation_id":"e190b2af-c730-4b06-96a2-8dadf74bb857","resolution":{"observed_at":"2026-08-12T05:09:33.513446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.492099Z","title":"Legodnn: block-grained scaling of deep neural networks for mobile vision,","venue":null,"work_id":"498600db-efa6-4259-87d2-f9509bf0fa9a","year":2021},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.541819Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:bb3fcc4a6f170524d620ef99f01768b32af9d573c0c4babe16876b57795ac6ac","observation_id":"31466478-58f0-499b-8bdc-e702d307847b","resolution":{"observed_at":"2026-08-12T05:09:33.497963Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.475374Z","title":"Neulens: spatial-based dynamic accel- eration of convolutional neural networks on edge,","venue":null,"work_id":"637e491a-49ae-4dbe-bfe4-d0c288bf8a85","year":2022},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.546031Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:763fe2eb7093409f20b70b6202d4b9a0f4f1a9d6e9884099e5128fd1a98652fa","observation_id":"a68f4727-3fa1-48c6-a801-3e2e5e80eb98","resolution":{"observed_at":"2026-08-12T05:09:33.481156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.458724Z","title":"Hardware- accelerated platforms and infrastructures for network functions: A survey of enabling technologies and research studies,","venue":null,"work_id":"3bc154ee-74a3-4eb1-9544-442092499c6b","year":2020},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.550254Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:d066ee7fab3bd62b0dff789ecf8920dae77a717ee322075a959f898d44ce020e","observation_id":"e95cf71a-ccb8-441a-955e-a310b1f31995","resolution":{"observed_at":"2026-08-12T05:09:33.464123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:32.554485Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.554485Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:af6854bd38726e9b34b34dddd0c22a9a84efce7e43e979243d58f95d7d940576","observation_id":"d37c0518-f476-4769-b058-18b49d79d455","resolution":{"observed_at":"2026-08-12T05:09:32.554485Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-12T14:19:29.389332Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-12T05:09:32.558965Z","title":"Very deep convolutional networks for large-scale image recognition,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.558965Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:ae048222dc173fbda5c0dbf205dd1ba6c703c8d766d382a2d65e0436144c4264","observation_id":"3d06d156-5c55-4b72-ad1f-1341e4751f28","resolution":{"observed_at":"2026-08-12T05:09:32.558965Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","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":"2026-08-12T05:09:32.564105Z","title":"Mobilenets: Efficient convo- lutional neural networks for mobile vision applications,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.564105Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:456669dec8c0394d2937369cbb6827c0caa5692c7d9de52b670ebc0556743be2","observation_id":"1a977706-f418-4387-9e86-065f18a2335d","resolution":{"observed_at":"2026-08-12T05:09:32.564105Z","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":"2026-08-13T03:23:43.612034Z","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":"2026-08-12T05:09:32.568597Z","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":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.568597Z"},"links":{"cited_paper":"/paper/1602.07360","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:43d0159c5540e1e504a6b099a554cab6d966221eba64b97fac2f6ee488cebffc","observation_id":"fbe6dbf7-5633-4204-97aa-7002000ab2be","resolution":{"observed_at":"2026-08-12T05:09:32.568597Z","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":"2026-08-12T05:09:32.573717Z","title":"Shufflenet: An extremely effi- cient convolutional neural network for mobile devices,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.573717Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:a74109cc1c7a4dfb57c9d4d7689bd98810374c8bb79d2c6542be9b71aca3bf60","observation_id":"9690617f-1906-4613-951a-d1ce43e0398c","resolution":{"observed_at":"2026-08-12T05:09:32.573717Z","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":"2026-08-12T05:09:32.578029Z","title":"Going deeper with convolutions,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.578029Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:c88c7177be7e0f173a9026c457d29f18b91837ca211ee0871fa02cd9e9f59f5b","observation_id":"73173d06-5eb6-4bba-9a5c-404cf53883a0","resolution":{"observed_at":"2026-08-12T05:09:32.578029Z","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":"2026-08-12T05:09:32.582307Z","title":"Rethinking the inception architecture for computer vision,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.582307Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:eb4a4dae718eaf4d7b336018d37973dd097e96a0a9199ab1c8c87bac85603608","observation_id":"426c3448-da19-423a-98f8-33ca00f9b693","resolution":{"observed_at":"2026-08-12T05:09:32.582307Z","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":"2026-08-12T05:09:32.586604Z","title":"Ghostnet: More features from cheap operations,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.586604Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:7ffa1e74e8ed945400c3c61d16b1db713fb61984e9d0cd7cf50dc4bd6eb69db2","observation_id":"b8903f8a-fb7e-4dd5-a654-6261d04c59f9","resolution":{"observed_at":"2026-08-12T05:09:32.586604Z","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":"2026-08-12T05:09:32.591172Z","title":"Efficientnet: Rethinking model scaling for con- volutional neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.591172Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:613ff684c11eec434c928abbb7a3d59e32b85048ad374330e1ddf49979c16c77","observation_id":"26f4d26a-cad3-4dd5-9945-f25f771aba25","resolution":{"observed_at":"2026-08-12T05:09:32.591172Z","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":"2026-08-12T05:09:32.595678Z","title":"Mnasnet: Platform-aware neural architecture search for mobile,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.595678Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:90c8e939952a9a60a189887d3264636a9fe3a055ade1df14ef0e606413fa466e","observation_id":"27521ec3-751f-43da-87a6-1c0d047791ee","resolution":{"observed_at":"2026-08-12T05:09:32.595678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1404.1869","last_updated":"2014-04-07T18:08:56Z","snapshot_observed_at":"2026-08-02T10:37:43.873349Z","submitted_at":"2014-04-07T18:08:56Z","title":"DenseNet: Implementing Efficient ConvNet Descriptor Pyramids","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1404.1869","snapshot_observed_at":"2026-08-12T05:09:32.599775Z","title":"Densenet: Implementing efficient convnet descriptor pyra- mids,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.599775Z"},"links":{"cited_paper":"/paper/1404.1869","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:8d82e601c15282b6fe708d8cc08566ce8c73d438bee5884989fa6a3f50de0c55","observation_id":"9fed6764-5840-486a-9912-bbe5d084dadc","resolution":{"observed_at":"2026-08-12T05:09:32.599775Z","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":"2026-08-12T05:09:33.371436Z","title":"Deep k-means: Re-training and parameter sharing with harder cluster assign- ments for compressing deep convolutions,","venue":null,"work_id":"571b374a-2cde-44a2-90c3-cc00990ef070","year":2018},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.605347Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:83bab5c6f9adea0d2355528c3f133f07c413db4a12921c90e6f05702a201fce3","observation_id":"0a6b0b03-b4e2-4bd4-a27d-c00d56467603","resolution":{"observed_at":"2026-08-12T05:09:33.376612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.355974Z","title":"Adadeep: A usage-driven, automated deep model compression framework for enabling ubiquitous intelligent mobiles,","venue":null,"work_id":"6a141fab-1f72-4235-bffe-fe5f0cdf9f42","year":2020},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.609918Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:494a7e5d76c7fa038eddb2530a368799d88b58431ce1620a7e32dedfab8b2bce","observation_id":"d895a1c6-9522-46d0-a65f-6f511747555b","resolution":{"observed_at":"2026-08-12T05:09:33.360786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.339240Z","title":"Enabling latency-sensitive dnn inference via joint optimization of model surgery and resource allocation in heterogeneous edge,","venue":null,"work_id":"b65e98e7-3d32-49f6-86aa-2e25579807e5","year":2022},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.615291Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:bfc3b3e69e2d53665e9c22c3ec138a23080392e7e5d62d064c339e3b857dd837","observation_id":"de4832f0-467b-4f0e-8ef8-2967fe6a8d99","resolution":{"observed_at":"2026-08-12T05:09:33.345333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:32.619705Z","title":"Branchynet: Fast inference via early exiting from deep neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.619705Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:c45dc59fa7094b2d82b7938494b6d7ac1592c09e7d29d50a853102040f5b7c12","observation_id":"2f83197e-3c52-4d07-92e3-7bae45133962","resolution":{"observed_at":"2026-08-12T05:09:32.619705Z","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":"2026-08-12T05:09:32.624173Z","title":"Learning both weights and con- nections for efficient neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.624173Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:115feab20431f74315c6745ad1734f21e17083523519901ad010104b1f9d5ec5","observation_id":"dcebb4cf-c9c2-40ea-9bbb-bc468e608c98","resolution":{"observed_at":"2026-08-12T05:09:32.624173Z","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":"2026-08-12T05:09:33.302589Z","title":"Nn-stretch: Automatic neural network branching for parallel inference on heterogeneous multi-processors,","venue":null,"work_id":"5d6a8109-24e3-40bc-9022-515909b025a6","year":2023},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.629385Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:1956f2cd520aba8194c87b1b932b4827f3d82c5fb06ad4253ca2fe80fd5fd899","observation_id":"5ab147e2-5151-4d96-b59d-43b763571f51","resolution":{"observed_at":"2026-08-12T05:09:33.308348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.284802Z","title":"Adaenlight: Energy-aware low-light video stream enhancement on mo- bile devices,","venue":null,"work_id":"2878c31e-c447-4ee2-ac19-8f7a9ba0b5c0","year":2023},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.634169Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:2818d6bfa03146d0f9f44bb34595e5c35eaca2e09403ded48ba35f889f108f0e","observation_id":"917d14d7-d132-448b-bb0b-7f8da6e9f4f1","resolution":{"observed_at":"2026-08-12T05:09:33.290733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.267346Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":"07416372-446a-4137-ab2b-5ea1e75cea4c","year":2009},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.638940Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:f7bf2fc1e0d2f214f84a81642a1e7b4fca9f63ac920f5a4945cfaa05aecf3c33","observation_id":"a74338fa-eb6e-41f1-894f-2c0cd2761340","resolution":{"observed_at":"2026-08-12T05:09:33.273468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.249747Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":"f4c20811-f456-440e-be5b-3b5b46595c61","year":2009},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.643231Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:9e7552417536b9eb2b6f9bbd6728d34826ec2f4188d4ce9c6b3588054095e01d","observation_id":"3168085a-345a-421f-bcdf-1a4d0ce05a60","resolution":{"observed_at":"2026-08-12T05:09:33.255511Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:32.648905Z","title":"Tiny imagenet visual recognition challenge,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.648905Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:9b3a8b5685a3687253670d414f4013895748c39bc294596d8c0a05fe9986b616","observation_id":"21d2f6e4-84ae-42aa-9143-264898d037a8","resolution":{"observed_at":"2026-08-12T05:09:32.648905Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01578","last_updated":"2017-02-15T05:28:05Z","snapshot_observed_at":"2026-07-06T05:17:29.499249Z","submitted_at":"2016-11-05T00:41:37Z","title":"Neural Architecture Search with Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01578","snapshot_observed_at":"2026-08-12T05:09:32.653324Z","title":"Neural architecture search with reinforcement learning,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.653324Z"},"links":{"cited_paper":"/paper/1611.01578","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:7defd83a3da83fc2256ef07c12585d1a86ae8643d47a6433a062ce14a7924d0c","observation_id":"80fda8cd-d80c-45f9-a762-eb8879be7bab","resolution":{"observed_at":"2026-08-12T05:09:32.653324Z","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":"2026-08-12T05:09:32.658391Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.658391Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:bbb83ea91aecd3f320dfedec99b727c4d731aede8b0508c262e001391ee72b70","observation_id":"26938082-4eb1-4589-92e6-32720bf066d6","resolution":{"observed_at":"2026-08-12T05:09:32.658391Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.17726","last_updated":"2025-01-13T12:38:41Z","snapshot_observed_at":"2026-08-13T00:44:41.310881Z","submitted_at":"2024-03-26T14:14:30Z","title":"Tiny Models are the Computational Saver for Large Models","version":4},"cited_work":{"arxiv_id":"2403.17726","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.17726","snapshot_observed_at":"2026-08-12T05:09:32.834685Z","title":"Tiny Models are the Computational Saver for Large Models","venue":"cs.AI","work_id":"294a8339-3365-409b-9cdd-9baa65f0d6e6","year":2024},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.662639Z"},"links":{"cited_paper":"/paper/2403.17726","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:8806dfd2d93689e0974fdf0d9b5d6d160949d6f046e9ff2902d48e706d51210e","observation_id":"6cb4bcce-8123-465c-94f5-c62c44f654db","resolution":{"observed_at":"2026-08-12T05:09:32.839530Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.214445Z","title":"Pmc: A privacy-preserving deep learning model customization framework for edge computing,","venue":null,"work_id":"50e3aa60-a32c-4935-93e0-8b54f1cce2aa","year":2020},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.667827Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:9bd29cf5ebc3c73a6a587d4be760b02aa7e4f701adfc77aad08adb98adc22879","observation_id":"eec07143-84c9-4d6c-8f7a-a9333cb88b01","resolution":{"observed_at":"2026-08-12T05:09:33.219307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.197031Z","title":"Distributed deep convolutional neural networks for the internet-of-things,","venue":null,"work_id":"9e9c6205-5690-473c-8388-132bdebd1136","year":2021},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.672579Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:ad07f0685c9c23e62cdc40fedf8e491388d1ffc1caab10bcdc0d377f61b72bc3","observation_id":"f777375b-f8d7-4fa5-9ea9-93039504547f","resolution":{"observed_at":"2026-08-12T05:09:33.203335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:32.677535Z","title":"Learning in the wild: When, how, and what to learn for on-device dataset adaptation,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.677535Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:c1cb4a551e3fd03cec76e3ee71ce65036df1a1595018438747da895f3784d3f6","observation_id":"5861111d-b243-4a4a-96ed-958627ccb268","resolution":{"observed_at":"2026-08-12T05:09:32.677535Z","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":"2026-08-12T05:09:32.682017Z","title":"A survey of quantization methods for efficient neural network infer- ence,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.682017Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:81c419bfc7d0e0c663c1f80da7948af95657a953c8d4f1cd740da3ff8eb88fec","observation_id":"5d272e39-9e85-4100-9890-0966f42e9a9b","resolution":{"observed_at":"2026-08-12T05:09:32.682017Z","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":"2026-08-12T05:09:32.686636Z","title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.686636Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:8e18c026f714b38bff5f84666a4941e8aa9c1b997063d1ddce2bd9d4f1164e15","observation_id":"c9ecbe0b-afae-4db9-83ec-747d0ff5bf2d","resolution":{"observed_at":"2026-08-12T05:09:32.686636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-12T05:09:32.691677Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.691677Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:2a0314ed3bc1ae36603a11a3c2113168f6497962562dd564c4bab7ebb36879d4","observation_id":"6df55371-3659-4626-89a3-b22896d3e784","resolution":{"observed_at":"2026-08-12T05:09:32.691677Z","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":"2026-08-12T05:09:33.160789Z","title":"Con- densenet: An efficient densenet using learned group convolutions,","venue":null,"work_id":"ee620dc6-b13b-474f-94c0-3603248cd473","year":2018},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.696206Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:e0dbec7305ae9f8e6e51606c3f3b2a0a63b156a81ceb8041cabea73c358e8566","observation_id":"8fe4eab7-8fdb-47c4-ae75-ac6032a3e782","resolution":{"observed_at":"2026-08-12T05:09:33.166105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.145547Z","title":"Squeezenext: Hardware-aware neural network design,","venue":null,"work_id":"a4f33ef4-e923-4901-960b-3528b1bcece6","year":2018},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.700632Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:3567dcf2a26a41cc6f899c00e083ddfd97621d4a0a0739a1c41144b61ec00bbe","observation_id":"25881ae0-df88-4b10-890d-f204edec34cb","resolution":{"observed_at":"2026-08-12T05:09:33.150222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:32.705796Z","title":"A com- prehensive survey on model compression and acceleration,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.705796Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:7349729240c9ec4302ddf03a7d286d2651e72134157793a1138f75785ca5fb88","observation_id":"53b55717-19b0-417d-8676-a0c2acc34b87","resolution":{"observed_at":"2026-08-12T05:09:32.705796Z","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":"2026-08-12T05:09:33.119935Z","title":"A survey on evolutionary neural architecture search,","venue":null,"work_id":"bb84933e-5062-4102-acd0-9c457710ad14","year":2021},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.710352Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:38168b912636f0885c403a22ec53825d71a1cacb24fc00df2b4e9d4eb8e65784","observation_id":"e77136f5-0879-4cd1-a727-ba88c439fc1c","resolution":{"observed_at":"2026-08-12T05:09:33.124592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.103636Z","title":"Edgecompress: Coupling multi-dimensional model compression and dynamic inference for edgeai,","venue":null,"work_id":"22d6ecf5-5d0e-4563-8d9e-c317864f1086","year":2023},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.715524Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:a50da9a17a4d988085f1766f8450fc95a689d1918d8f868ad3984c4bbe0dd8a5","observation_id":"846e6d25-2313-4895-847e-c9ae0d3645a4","resolution":{"observed_at":"2026-08-12T05:09:33.109172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.06392","last_updated":"2020-03-26T02:20:32Z","snapshot_observed_at":"2026-08-05T06:09:19.306204Z","submitted_at":"2020-01-17T15:55:21Z","title":"Latency-Aware Differentiable Neural Architecture Search","version":2},"cited_work":{"arxiv_id":"2001.06392","doi":null,"metadata_source":"pith","pith_arxiv_id":"2001.06392","snapshot_observed_at":"2026-08-12T05:09:32.780919Z","title":"Latency-Aware Differentiable Neural Architecture Search","venue":"cs.CV","work_id":"f448e6a8-b9ff-4939-8be6-dba3f8e3356e","year":2020},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.719786Z"},"links":{"cited_paper":"/paper/2001.06392","citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:d008d0370f18a8642016282d82dce6be78575e8a5559a1a5e63e70b5f81e9462","observation_id":"1a527aa3-9b91-4165-9f4c-2b1e40d0655c","resolution":{"observed_at":"2026-08-12T05:09:32.788080Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.086901Z","title":"Neuralpower: Predict and deploy energy-efficient convolutional neural networks,","venue":null,"work_id":"a2a19272-fa37-469a-acbb-45e9f118c241","year":2017},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.725293Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:2ac11bda938817e499cca9ee01a1fed14375431d34fe0ab7f3fe55c6455e6cdb","observation_id":"7ae2d0d8-a8ec-41fb-bdeb-7498d1640710","resolution":{"observed_at":"2026-08-12T05:09:33.091982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.070721Z","title":"Chamnet: Towards efficient network design through platform-aware model adaptation,","venue":null,"work_id":"ceeeb40d-56df-4bf5-b8fe-7bc5c5a7d176","year":2019},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.729451Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:d3aa26e7dd8b1a9bf3d857f98c88f28f03eed38a29166fa7d8b24c71ba92c98a","observation_id":"18b1f109-6f9a-4c1d-8174-cf24ffd519ca","resolution":{"observed_at":"2026-08-12T05:09:33.075885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.055266Z","title":"Nn-meter: Towards accurate latency prediction of deep-learning model inference on diverse edge devices,","venue":null,"work_id":"0fa4c3bf-5092-4691-ad31-991ea16279d6","year":2021},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.734403Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:eaa0df89e0908286937f79bc087f6d36cadadbebedff7adb254b74bbc9aab34d","observation_id":"14855eb0-2deb-49e6-ad43-632071b2c8b9","resolution":{"observed_at":"2026-08-12T05:09:33.060146Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.038436Z","title":"Searching the deployable convolution neural networks for gpus,","venue":null,"work_id":"e1779d16-4c32-4fa1-833f-e94959912856","year":2022},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.738917Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:e9a81108d975ef677e85b728736044f0f2016781d8e9b5711e520dfe71a66248","observation_id":"40263fcc-ed05-474f-bb29-80aa290c6842","resolution":{"observed_at":"2026-08-12T05:09:33.043445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T05:09:33.022501Z","title":"On-demand deep model compression for mobile devices: A usage-driven model selection framework,","venue":null,"work_id":"29e322dd-70ad-490c-bfe7-227dd0e7d44c","year":2018},"citing_paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T05:09:32.743406Z"},"links":{"citing_paper":"/paper/2412.00724"},"observation_digest":"sha256:676df8272930c4eab8754e9aed18ddf65a3c1519b2d4ae4f46d3cfc561da34e2","observation_id":"6d4a3f0f-0e20-40af-a97f-bdd525a7fa0d","resolution":{"observed_at":"2026-08-12T05:09:33.027425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.00724","last_updated":"2024-12-01T08:33:56Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-12T09:32:58.604895Z","submitted_at":"2024-12-01T08:33:56Z","title":"AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devices"},"reference_resolution":{"displayed":68,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":3,"verified_fuzzy":36},"total_outbound_references":68},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 0 inbound Pith citation observations for arXiv:2412.00724."}