{"as_of":"2026-08-10T11:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9194c72261e1995c86cc64058333e788f38109892361510d6c3eec02132e8504","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T15:55:23.421547Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.14802/citation-record","integrity":"/paper/2507.14802/integrity","json":"/paper/2507.14802/citation-record.json","paper":"/paper/2507.14802"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:55:23.724149Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":"7a4d7075-d2f5-471c-8249-88c199e8b71a","year":2020},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.337391Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:9ed18178bc09127aabb2ac919fd1bf3450346cb31efb0797d44afa8a570f306c","observation_id":"3060f1af-8aa4-42d7-af14-6afeee05fa6d","resolution":{"observed_at":"2026-08-06T15:55:23.726543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.716832Z","title":"BERT: Pre- training of deep bidirectional transformers for language understanding,","venue":null,"work_id":"2d8d0540-1794-4ee1-8638-b1a26a95b18c","year":2019},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.340039Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:79604aec98e5e23ce273a866798120d6b476f0af70144ed4a158062a04c508bb","observation_id":"366cbead-ebf9-44ac-986e-54ee3f3d6d9b","resolution":{"observed_at":"2026-08-06T15:55:23.719184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.342074Z","title":"Recent advances in natural language processing via large pre-trained language models: A survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.342074Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:3bf8c8f9a8f173de4c263bb872e50cf669a1c010611d1b0598a49c9ee2692549","observation_id":"e06c8607-9a9c-4b58-b8dd-8607e8ab2b87","resolution":{"observed_at":"2026-08-06T15:55:23.342074Z","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":"2026-08-06T15:55:23.704311Z","title":"Large language models and future of information retrieval: Opportunities and challenges,","venue":null,"work_id":"d4efef5c-7513-4f1f-a5b7-69081d9adeeb","year":2024},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.344263Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:c0f9b8a546d191817188a5f93ad41f153a8a58297603c667dfb1145a8f93dc5f","observation_id":"6120c4d5-c2b3-491f-8266-6ee57465e9f0","resolution":{"observed_at":"2026-08-06T15:55:23.706882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14371","last_updated":"2024-05-23T09:46:22Z","snapshot_observed_at":"2026-07-06T18:18:30.066741Z","submitted_at":"2024-05-23T09:46:22Z","title":"EdgeShard: Efficient LLM Inference via Collaborative Edge Computing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14371","snapshot_observed_at":"2026-08-06T15:55:23.346579Z","title":"Edgeshard: Efficient llm inference via collaborative edge computing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.346579Z"},"links":{"cited_paper":"/paper/2405.14371","citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:04dff51597ba39031b8af7ee155ddbed0e51e85da76c7e000c1e0b4231b34458","observation_id":"f7154ef5-dddf-43cd-af27-0219209281b5","resolution":{"observed_at":"2026-08-06T15:55:23.346579Z","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":"2026-08-06T15:55:23.697121Z","title":"MobileLLM: Optimizing sub-billion parameter language models for on-device use cases,","venue":null,"work_id":"63befd90-ec8e-481e-98b7-ecf3bdc5dc1d","year":2024},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.348918Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:af940e970ef15da1914f1cb24673d6b52203afcbc75cbf279f987ea452327789","observation_id":"b5efc77c-42d9-4e20-a430-af92ced0b5de","resolution":{"observed_at":"2026-08-06T15:55:23.699668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.689947Z","title":"To talk or to work: Flexible communication compression for energy efficient federated learning over heterogeneous mobile edge devices,","venue":null,"work_id":"b6698518-fb29-42bc-a4d2-6de09f8e8085","year":2021},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.351099Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:f5e392a6dbdf27879ef47dfb7422c719e2d3c2b33f9591dff1e1c8109743389f","observation_id":"1f6b5852-576b-4ac8-805f-3c2bb01ea697","resolution":{"observed_at":"2026-08-06T15:55:23.692406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.682464Z","title":"Dependency-aware microservice deployment for edge computing: A deep reinforcement learning approach with network representation,","venue":null,"work_id":"d36b0cd1-3ff6-46f3-bffa-f9228d133607","year":2024},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.353130Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:6e39bd674955a8bdd65582b325a76d74640e0118c55d8051e36a8272b021c04a","observation_id":"af1b174f-f373-4bf1-a270-8fc73c956e77","resolution":{"observed_at":"2026-08-06T15:55:23.684999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.675226Z","title":"Finch: Enhancing federated learning with hierarchical neural architecture search,","venue":null,"work_id":"9c5f687f-7865-4694-9bc7-22268bc1d813","year":2023},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.355054Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:98dd910639db126c9697ff2e39a2aea15d8e046a8b97606fe0bd7219c2066f40","observation_id":"9aa58c64-8fd7-4a32-bf3c-9dba0a2d2c4f","resolution":{"observed_at":"2026-08-06T15:55:23.677735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.356923Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.356923Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:901f3f69f0b9fb94b582f26c0e231f0c3a7e4a19636cdf75b88b41e8e2308fd0","observation_id":"52077777-ed7e-46c6-8b3c-f791ebd0dddf","resolution":{"observed_at":"2026-08-06T15:55:23.356923Z","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":"2026-08-06T15:55:23.663220Z","title":"Distributed pruning towards tiny neural networks in federated learning,","venue":null,"work_id":"9828765f-337a-472b-83b0-32cb01b3a777","year":2023},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.358828Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:f0532d84da3003ee5f07b35495e9669607642dc99372fe221d15ad68e06e831e","observation_id":"2db9d6ad-3323-49c5-b50d-61e4d2829c33","resolution":{"observed_at":"2026-08-06T15:55:23.665907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.656481Z","title":"Scalable federated learning with system heterogeneity,","venue":null,"work_id":"22a223a0-22c9-4b33-b99d-269fe7a64850","year":2023},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.360700Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:943498df34840ff6851e91449b9139d5d06ed715e7ec69ecdf27e4d05a7688f8","observation_id":"df2595be-4d05-40cd-91a0-eff3959d99f4","resolution":{"observed_at":"2026-08-06T15:55:23.658829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.649717Z","title":"Cur- CoEdge: Curiosity-driven collaborative request scheduling in edge-cloud systems,","venue":null,"work_id":"44f08e6b-b1bd-4901-8327-7f5557748797","year":2024},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.362570Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:95e28943b74639a4ff15afaa15389a5f7b7c39bb6322f8fbef5931b30d7ef275","observation_id":"3bf79188-7f4c-4f1a-9345-79c90ad836b6","resolution":{"observed_at":"2026-08-06T15:55:23.651981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.643206Z","title":"MG²FL: Multi- granularity grouping-based federated learning in green edge computing systems,","venue":null,"work_id":"99525f2b-8869-4dde-8784-0dfd8949e624","year":2023},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.364398Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:aeda69495e4169b8d711aa414670ef64811b214786d198e2c5c26d9796e401fb","observation_id":"cafbc1b6-6134-49f2-8439-2cc1b403d2e3","resolution":{"observed_at":"2026-08-06T15:55:23.645538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.636741Z","title":"Energy-efficient inference ser- vice of transformer-based deep learning models on gpus,","venue":null,"work_id":"276650e5-364f-4ee8-b529-0d873fb6ec0f","year":2020},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.366246Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:8e1a3cfc0761dfe930377cc65b3b74ef5ae05d7cc5bbe201e00fe6acc96bb58b","observation_id":"7df02a7c-fc7a-4970-b1a4-bd502442e595","resolution":{"observed_at":"2026-08-06T15:55:23.639057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.630294Z","title":"EfficientNet: Rethinking model scaling for convo- lutional neural networks,","venue":null,"work_id":"3f3603a1-5b2e-4e3b-9ba5-73511e3d50e1","year":2019},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.368118Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:69205fec3fd90afadf7decac4ac69a9115628e4f54721d9a07dbc816d49ecd2e","observation_id":"b11c58c9-9abb-4a54-a26f-3a3dbdc7e472","resolution":{"observed_at":"2026-08-06T15:55:23.632550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.623632Z","title":"Dyn- aBERT: Dynamic bert with adaptive width and depth,","venue":null,"work_id":"e29f13d7-ce72-4a94-9b6f-e9633aff2e5e","year":2020},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.369981Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:4817fa71a96931df5aa75c64cf9aacde20c758e04fcdf9b4745a672f685729d6","observation_id":"195bc80f-701a-42ea-805c-900c8b50f5c6","resolution":{"observed_at":"2026-08-06T15:55:23.625797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.616984Z","title":"A constrained decomposition approach with grids for evolutionary multiobjective optimization,","venue":null,"work_id":"c438510a-d795-4eff-a210-5562b5a3bae5","year":2017},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.371876Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:2086c9f486188b9ebfc1bd794aac11f1f90cf29d0580e445297fc18d8e28c01f","observation_id":"175a96f8-4e13-44d9-8d71-739e29b56fe6","resolution":{"observed_at":"2026-08-06T15:55:23.619361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.610641Z","title":"A pareto front grid guided multi-objective evolutionary algorithm,","venue":null,"work_id":"43bd8fc9-d933-4886-b028-a124738bb5bc","year":2023},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.373776Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:c375a9b0caa015d45680b8c325260a7a8ca59fbd0180040f87c5df762a1caec5","observation_id":"4a50d242-df03-4ad0-b39f-ae0200548500","resolution":{"observed_at":"2026-08-06T15:55:23.612860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.604181Z","title":"Progressive neural architecture search,","venue":null,"work_id":"ec727a2e-886d-4239-8e68-48c4f94094ff","year":2018},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.375654Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:0e00a4f1e9f11a35240f07533833f86ee72200dd9053c6a4200902b875a950b3","observation_id":"2131eb4d-7544-43c8-b9e6-fb6ced3931c2","resolution":{"observed_at":"2026-08-06T15:55:23.606406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.597655Z","title":"LGViT: Dynamic early exiting for accelerating vision transformer,","venue":null,"work_id":"74c3288d-9ff9-4812-a257-109523a34dec","year":2023},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.377625Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:35646f690c807a701ee6ed7740ed1dc434aced1a9431435e4e552f9db1a87685","observation_id":"87676e55-d6df-4535-9b10-c9b86dc8d3a9","resolution":{"observed_at":"2026-08-06T15:55:23.600015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.591173Z","title":"Single-layer vision trans- formers for more accurate early exits with less overhead,","venue":null,"work_id":"bbc2d874-a136-491e-95ac-15e3921a73b4","year":2022},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.379630Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:cc99fffbad18f012c66db474e99230272ac757ea2715ac31d7f7960144451531","observation_id":"eadc5eab-02e5-4ca1-b198-b8d2bc510edd","resolution":{"observed_at":"2026-08-06T15:55:23.593492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.584615Z","title":"Learning transferable architectures for scalable image recognition,","venue":null,"work_id":"cbf5bcdd-5226-459d-babc-38f2d14776bf","year":2018},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.381669Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:e1d6c68dc225ccb6f909b105a6fe4ec93abbb3167e1e3142ae804dd81f4b5e5e","observation_id":"dc9aad7e-196f-433c-9344-d2733726ed7d","resolution":{"observed_at":"2026-08-06T15:55:23.587025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.578038Z","title":"ENASFL: A federated neural architecture search scheme for heterogeneous deep models in distributed edge computing systems,","venue":null,"work_id":"5be953f7-9526-4a60-a459-5c95fad5d686","year":2023},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.383666Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:e152219d94b4fc54400918bc7c259a013cc9e649c2c57788e7b6fc9069725de0","observation_id":"22db16dd-157a-4331-9ac6-320fd49f9e70","resolution":{"observed_at":"2026-08-06T15:55:23.580401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.571701Z","title":"Efficient neural architecture search via parameter sharing,","venue":null,"work_id":"01108a99-db0e-45e1-93be-7d69298fc89b","year":2018},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.385502Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:265d8dc022476ecd933831eb749f3dc136a361d96540c18e8a74f2d8634ef062","observation_id":"ac6436a3-0cb5-4f1a-bcdc-8d84762a2776","resolution":{"observed_at":"2026-08-06T15:55:23.573891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.565017Z","title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning,","venue":null,"work_id":"28d4f78e-c58b-4ec6-a671-a4b3cc1a8285","year":1992},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.387360Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:11eeac68e6194512b514404b07ae7a741b5cf00196cd6b1477bc0d301afda9ae","observation_id":"41101bee-e2bd-4ef0-89cd-265ea8583def","resolution":{"observed_at":"2026-08-06T15:55:23.567559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.558001Z","title":"Importance estimation for neural network pruning,","venue":null,"work_id":"5186096e-a55b-4016-8acb-ad359460dc4c","year":2019},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.389230Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:5c29d105daa917d08b613f0b67d199b337ab58a70049f7fe917540ac03f451b5","observation_id":"97d31c6d-8902-4e69-bed5-9c769e1af53f","resolution":{"observed_at":"2026-08-06T15:55:23.560704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.551393Z","title":"Data valuation and detections in federated learning,","venue":null,"work_id":"d2a0e982-261c-45e3-bf57-6cd1dd91e2ff","year":2024},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.391024Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:14661f28d0a1b0fe9d0a9c9e4b8946023e7229b182fe19e82422498a48f825c5","observation_id":"e86a362f-5e1d-4b86-87ea-4d54558f3339","resolution":{"observed_at":"2026-08-06T15:55:23.553602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.544658Z","title":"Once-for-all: Train one network and specialize it for efficient deployment,","venue":null,"work_id":"8a4d2219-4a1d-4207-b0b4-b97a8fc6311c","year":2020},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.392971Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:34164d919eb8da31590273ce36259e01341c17590ae80c94b65df654ab613ce2","observation_id":"63186e27-17d4-4ed3-8cc0-465475edec5d","resolution":{"observed_at":"2026-08-06T15:55:23.547179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.537700Z","title":"BERxiT: Early exiting for BERT with better fine-tuning and extension to regression,","venue":null,"work_id":"4be6ee00-b648-4ae6-9d7f-c5c6fc5ef427","year":2021},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.394953Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:9c43c395039e74c4ebc9d7ad876993b77cd2cf6bedb7ec67f1efe4327339b587","observation_id":"6711a53f-3b22-4e8b-8bf7-4a68a2a5ded1","resolution":{"observed_at":"2026-08-06T15:55:23.540411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00518","last_updated":"2024-02-01T11:39:04Z","snapshot_observed_at":"2026-07-06T17:23:39.158867Z","submitted_at":"2024-02-01T11:39:04Z","title":"EE-Tuning: An Economical yet Scalable Solution for Tuning Early-Exit Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00518","snapshot_observed_at":"2026-08-06T15:55:23.397225Z","title":"EE-Tuning: An economical yet scalable solution for tuning early-exit large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.397225Z"},"links":{"cited_paper":"/paper/2402.00518","citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:eba52b08cfb1393c18decc538149ae4424538a29bdc15d509a20355873630066","observation_id":"7c727b8e-75eb-4908-b078-20f211a8b33e","resolution":{"observed_at":"2026-08-06T15:55:23.397225Z","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":"2026-08-06T15:55:23.531432Z","title":"A survey of visual transformers,","venue":null,"work_id":"30e6db45-8e01-43d1-b239-2d5b8329e3d9","year":2023},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.399502Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:65785543ea6973981e26866d68552478a5dc2eff0a59d106a6a64c451cc525f6","observation_id":"f83f73a7-552d-4f13-bb1d-0eabe2da0d87","resolution":{"observed_at":"2026-08-06T15:55:23.533588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.524608Z","title":"Efficient-ViT: A light-weight classification model based on CNN and ViT,","venue":null,"work_id":"235f6850-bec9-4d68-9790-6a5dba6787ed","year":2023},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.401452Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:e6074c0debb852386a59f005787cef660b0f41d02561ddb96a068057346aa9b4","observation_id":"30f74189-9410-4df3-b9e6-8ecdc938aae6","resolution":{"observed_at":"2026-08-06T15:55:23.526870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.517720Z","title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer,","venue":null,"work_id":"6a742784-cec9-4645-b131-74880cf0e6e4","year":2022},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.403452Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:b2e26c68b487387b6fa341bc020b31eeadc2f1abf82c6b8bd0928b772c0b3697","observation_id":"4692a5ff-49c5-4079-8832-c1f8b67c03d2","resolution":{"observed_at":"2026-08-06T15:55:23.520409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.510419Z","title":"Twins: Revisiting the design of spatial attention in vision transformers,","venue":null,"work_id":"348eb19c-b00f-4455-ae75-525231e475e3","year":2021},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.405355Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:0480ed0807a4398b7978592e9f654a2be65a6d321628d7a2f734bcd7300bd49a","observation_id":"efcad53d-3b0d-4522-9987-9a6b2b0e08c3","resolution":{"observed_at":"2026-08-06T15:55:23.512953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.503703Z","title":"DeViT: Decomposing vision transformers for collaborative inference in edge devices,","venue":null,"work_id":"4c6b358b-ddce-483c-8f61-cb83b6130f10","year":2023},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.407654Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:3b1413161f11209051035f75039d30937e1b870f95931487fc9732045d16c3f9","observation_id":"74e5d64f-bea9-4631-9a9b-ecdab2fab9ba","resolution":{"observed_at":"2026-08-06T15:55:23.506104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.496480Z","title":"Multi-exit vision trans- former for dynamic inference,","venue":null,"work_id":"4e0e63c2-c330-4f37-9ff6-a863b83d87bf","year":2021},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.409628Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:ba3d3471d9a85f2c80cdb6d4132b48cae73a01dcb7ffa336c400dbd4239e8ae3","observation_id":"f0247336-7eb8-416c-80b4-daf8895d0bb7","resolution":{"observed_at":"2026-08-06T15:55:23.499136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","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":"2026-08-06T15:55:23.411506Z","title":"MobileNets: Efficient convo- lutional neural networks for mobile vision applications,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.411506Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:02e6bb9341acc956d317a6625b0403add9f7e748191cba4c5069d9d255422701","observation_id":"e6ac4da0-7ad4-48c1-9af6-cdc99505bb6a","resolution":{"observed_at":"2026-08-06T15:55:23.411506Z","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":"2026-08-06T15:55:23.488389Z","title":"Morphnet: Fast & simple resource-constrained structure learn- ing of deep networks,","venue":null,"work_id":"0cb2deaa-26d0-47cb-93b0-371997d1c5f5","year":2018},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.413553Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:504831569157a49091c86788452c01c4b99f2e2bb1dcc20a07a8194651ad5ca2","observation_id":"7b92e1ac-f36a-4ae3-abc5-890328f41a2f","resolution":{"observed_at":"2026-08-06T15:55:23.491159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.481408Z","title":"Adaptive weighted sum method for multiobjective optimization: a new method for pareto front generation,","venue":null,"work_id":"f0d945e9-9428-4b44-a617-7f3dbba51110","year":2006},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.415829Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:61d12345e4c58459aa778b7d600aee5fe3b340df686af70f03eac67b418f095e","observation_id":"ff59767e-5a4f-46af-9eab-ded05a74f309","resolution":{"observed_at":"2026-08-06T15:55:23.483793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.474598Z","title":"3d object representations for fine-grained categorization,","venue":null,"work_id":"38e36b18-7413-426d-a25c-4ee45161ab03","year":2013},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.417732Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:bbce08dff4bb7da48add6202a9e68e57ec6332daea93a902e8dc88ace0ee83bd","observation_id":"912a253f-920d-4598-8000-07b84572aef6","resolution":{"observed_at":"2026-08-06T15:55:23.476900Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.467397Z","title":"Resource-aware federated neural architecture search over heteroge- neous mobile devices,","venue":null,"work_id":"023683e7-7dd2-41b9-af25-0a66f71db3b0","year":2022},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.419705Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:6340a8dc053c39a8261d6f7c2ed7805311d53b635d19e57b5ccf2f1614b0f6ad","observation_id":"3fbe7c29-952f-4775-9352-59d92e48bb89","resolution":{"observed_at":"2026-08-06T15:55:23.469760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T15:55:23.458517Z","title":"Toward tailored models on private aiot devices: Federated direct neural architecture search,","venue":null,"work_id":"7237bb8d-97a3-4ea9-858d-cba2d00e471d","year":2022},"citing_paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T15:55:23.421547Z"},"links":{"citing_paper":"/paper/2507.14802"},"observation_digest":"sha256:e94e087d35cfdab9c41fac767453da91bde71189f520546f73ae2910d7d1843f","observation_id":"f22f299e-b838-4cd6-81da-cc77d651576d","resolution":{"observed_at":"2026-08-06T15:55:23.462465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.14802","last_updated":"2025-07-20T03:30:24Z","latest_version":1,"primary_category":"cs.DC","snapshot_observed_at":"2026-08-08T09:29:45.495469Z","submitted_at":"2025-07-20T03:30:24Z","title":"ACME: Adaptive Customization of Large Models via Distributed Systems"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":38},"total_outbound_references":43},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2507.14802."}