{"as_of":"2026-08-23T15:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cfd2c86f2e0ba119db4583a0fad27a22abf7e37d6aa18458e4f344af50667f7f","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:59:30.459655Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T16:20:59.826611Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-03T17:28:44.128150Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.03303","snapshot_observed_at":"2026-08-05T16:20:59.826611Z","title":"Comparative analysis of lightweight deep learning models for memory-constrained devices,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.18725","last_updated":"2025-08-26T06:50:11Z","snapshot_observed_at":"2026-08-20T03:55:31.552070Z","submitted_at":"2025-08-26T06:50:11Z","title":"Toward Edge General Intelligence with Agentic AI and Agentification: Concepts, Technologies, and Future Directions","version":1},"reference_index":152,"source":"pdf_text","source_observed_at":"2026-08-05T16:20:59.826611Z"},"links":{"cited_paper":"/paper/2505.03303","citing_paper":"/paper/2508.18725"},"observation_digest":"sha256:b64189e2c49350529858b79d717b4b8a4673384eeee446584edf3c51a4905ca4","observation_id":"38aca280-74e8-479b-9ac3-d8b8351dfb1e","resolution":{"observed_at":"2026-08-05T16:20:59.826611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"cited_work":{"arxiv_id":"2505.03303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.03303","snapshot_observed_at":"2026-07-03T17:28:44.128150Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","venue":"cs.CV","work_id":"27e327dc-54c4-43eb-9edb-d46a7aca4adb","year":2025},"citing_paper":{"arxiv_id":"2607.01984","last_updated":"2026-07-02T10:14:07Z","snapshot_observed_at":"2026-08-12T02:10:48.870426Z","submitted_at":"2026-07-02T10:14:07Z","title":"Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-03T17:20:34.043658Z"},"links":{"cited_paper":"/paper/2505.03303","citing_paper":"/paper/2607.01984"},"observation_digest":"sha256:d5764d7d9770b8160a67377382893d57831e6a5bb59299bbf36f05661fece193","observation_id":"f66ecfcf-250e-4fd5-9d29-441b3ce6e9bf","resolution":{"observed_at":"2026-07-03T17:28:44.129484Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.03303/citation-record","integrity":"/paper/2505.03303/integrity","json":"/paper/2505.03303/citation-record.json","paper":"/paper/2505.03303"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:59:30.335512Z","title":"Deep learning,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.335512Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:b398daf13d134650bf6d08d68471a8dfd9d14599e37fd307de6fcde0f9924f93","observation_id":"7662cc45-ed02-4e41-b4a0-a8e3b18453db","resolution":{"observed_at":"2026-08-15T23:59:30.335512Z","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":"2026-08-15T23:59:30.911260Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":"0d383f87-fbb6-4a1f-a05e-2327c3828cc1","year":2009},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.341146Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:d01324719362d7695ba0fba0ef8d514b6425d57eaf345c23ade307022d02f4b2","observation_id":"cac40c40-4c57-4058-9726-1f78f08a5c06","resolution":{"observed_at":"2026-08-15T23:59:30.917379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.893161Z","title":"Learning both weights and connections for efficient neural networks,","venue":null,"work_id":"37795450-d590-43cd-8933-e41328d4a77c","year":2015},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.346027Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:84bd3818749b54c61c856cbd6808aa58ac857fd6648008bb24e5ab40d5d04be2","observation_id":"005df05f-fbcb-497a-a4cc-7b19d143e51c","resolution":{"observed_at":"2026-08-15T23:59:30.898737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-08-20T09:32:02.065929Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-15T23:59:30.351123Z","title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.351123Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:825734aab666e75699410851fd4ba0c164f9afa8cbef37d8dcaf4929fca039ce","observation_id":"4c21d54a-a825-49d6-b47b-9b18505937e2","resolution":{"observed_at":"2026-08-15T23:59:30.351123Z","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":"2026-08-15T23:59:30.875001Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks,","venue":null,"work_id":"815ed320-5158-4796-bc89-435aa089d048","year":2018},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.357132Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:2a4674a4b27a26d504f6f87394a64f8165d87a928d4fffbde821943055ad3571","observation_id":"3545655f-7c5f-485a-b70b-db82175cdf3e","resolution":{"observed_at":"2026-08-15T23:59:30.880395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.855501Z","title":"Searching for mobilenetv3,","venue":null,"work_id":"049ff5f2-e647-4686-ab0e-af6f8cd83492","year":2019},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.362355Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:995f507dfb69ff562c032509d720367d4e28cd90cef76ce2074fd64010e7cf98","observation_id":"009eb234-0d55-4001-9f34-f3a06da679b2","resolution":{"observed_at":"2026-08-15T23:59:30.862154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1602.07360","last_updated":"2016-11-04T21:26:08Z","snapshot_observed_at":"2026-08-14T22:09:04.541956Z","submitted_at":"2016-02-24T00:09:45Z","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.07360","snapshot_observed_at":"2026-08-15T23:59:30.367785Z","title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and ¡0.5mb model size,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.367785Z"},"links":{"cited_paper":"/paper/1602.07360","citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:ca3e155b26c259281bafb5d607ccc5e50dd801b03d4ddf5008397ebe1b6232c9","observation_id":"1b6baf1c-25e6-4179-b573-1357fd64836f","resolution":{"observed_at":"2026-08-15T23:59:30.367785Z","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":"2026-08-15T23:59:30.833383Z","title":"Efficientnetv2: Smaller models and faster training,","venue":null,"work_id":"375d81da-63b2-4ff9-b525-8f790c4fc321","year":2021},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.372896Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:5fabaf94969f2947291742f72bbbadb30c27a2fcc798acd03c5dee8989a56ceb","observation_id":"8e8afc5a-35ce-4b34-b5aa-5a5041e9e42c","resolution":{"observed_at":"2026-08-15T23:59:30.838970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.816210Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"bb0e7341-c660-4ac5-b3f4-1a8b6aa49e6c","year":2016},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.377881Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:20aa8035d4418085eb64753fd9bf523033e37df4719bfd0e3afeac0d8dd552bb","observation_id":"047e9596-5f9b-4ebd-9aaa-12a879facf9d","resolution":{"observed_at":"2026-08-15T23:59:30.822032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.798387Z","title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design,","venue":null,"work_id":"e9094b7c-4672-4916-bb6b-bcbecb0be6fa","year":2018},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.382873Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:9ece7d230585426eebf67a7184f16d1b9d48847cdafae691c491b9f879c94094","observation_id":"15045054-42e2-4bfe-9db5-98e2cae240b1","resolution":{"observed_at":"2026-08-15T23:59:30.804348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.780794Z","title":"Do better imagenet models transfer better?","venue":null,"work_id":"0b442419-490f-4506-aee1-314753af09f6","year":2019},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.387834Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:dc964e8e466c26d81e6820c6ab423ec8da7aea3d19bd7d2308ca9fbeef19aa51","observation_id":"2ce95985-d8c9-4652-9506-c2ee14fa33e2","resolution":{"observed_at":"2026-08-15T23:59:30.786193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.762040Z","title":"Regnet: Designing network design spaces,","venue":null,"work_id":"a53e2865-3083-4748-981c-e0bb0011f0ae","year":2020},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.392960Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:19a035c0725c2c5c6a0e7dd11cb209c9ca8d55ad4c796369c771f131b88c9b40","observation_id":"0118a06f-e4cd-4462-a811-8aad135b6448","resolution":{"observed_at":"2026-08-15T23:59:30.767431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.397511Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.397511Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:65695d667af1f1e90ec9fe03aea68f011cf94fccae15a672a935e8fa29d6809f","observation_id":"90898625-73c2-4fe1-b1d3-a362476851d2","resolution":{"observed_at":"2026-08-15T23:59:30.397511Z","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":"2026-08-15T23:59:30.734665Z","title":"Mixup: Beyond empirical risk minimization,","venue":null,"work_id":"4d62bc35-cfe6-4d59-82f0-9c0d755f6552","year":2018},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.402061Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:78cd3dfdb1f5a84da3b42265699fb1b4faa3984623d79caa9bb4670a72f078bd","observation_id":"8afc0576-061f-4eef-a96f-73cbbea68abb","resolution":{"observed_at":"2026-08-15T23:59:30.739675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.717590Z","title":"A survey on image data augmentation for deep learning,","venue":null,"work_id":"c55ab9f9-bdda-4328-9633-b8de7e56740f","year":2019},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.406579Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:beb7c3c634020efb5c260a1420ced0264460bf064ed9657311640c5b17e87a3a","observation_id":"c327c2e7-914d-4bce-b518-7c112df7edf3","resolution":{"observed_at":"2026-08-15T23:59:30.722890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.700032Z","title":"Cutmix: Regularization strategy to train strong classifiers with localizable features,","venue":null,"work_id":"090375b6-d054-4057-ab2f-bc1da2da798f","year":2019},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.410944Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:ad6d7ddca7be13fef5e1f2eb800fbf4ff85848ea81d1a93a14a7818251258a9c","observation_id":"48b2f7e8-4d42-4d30-a60d-4983c7f817f8","resolution":{"observed_at":"2026-08-15T23:59:30.705094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.680885Z","title":"Efficient deep learning for edge computing platforms,","venue":null,"work_id":"86b98b29-ba2a-4093-8a06-1c81e07df7c5","year":2021},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.415341Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:1d9b542fec134238a15477381f33c65150c3c4630900bfea25612d65bcc64c9f","observation_id":"c33aa027-96d9-4854-a09a-109fe0514e2f","resolution":{"observed_at":"2026-08-15T23:59:30.687044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.661876Z","title":"Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search,","venue":null,"work_id":"c0d1f2d4-b4d1-487d-a0b1-dacf992bfb59","year":2019},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.419636Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:b92d4c5751539823a2a6d24fbed5f816dc108d446a5cd866f7682d73496c41d6","observation_id":"8640b267-8cbc-452f-947b-fcd4b18b8742","resolution":{"observed_at":"2026-08-15T23:59:30.668162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.644749Z","title":"A comprehensive survey of deep learning-based lightweight object detection models for edge devices,","venue":null,"work_id":"6f1c198a-edae-4c24-aa4c-d8556c9283e9","year":2024},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.424425Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:84377c714f384a7e1215834cf87025c202d65b6190e46857197a66615d05466c","observation_id":"7cdd7144-432a-41aa-919f-4cb9b2777802","resolution":{"observed_at":"2026-08-15T23:59:30.649639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.627844Z","title":"Evolution toward intelligent communications: Impact of deep learning applications on the future of 6g technology,","venue":null,"work_id":"a4405a5e-7ffc-4d78-b46d-2a8224309f30","year":2024},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.429060Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:5f10871e0b9cd559dcef33b3f70297f27173bee77b2ec127cffba65f3e60f53a","observation_id":"81bf0fd4-4ddb-419b-9c0d-bd5876110826","resolution":{"observed_at":"2026-08-15T23:59:30.633555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.609303Z","title":"Image super- resolution using generative adversarial networks with efficientnetv2,","venue":null,"work_id":"cc01f094-5302-41cf-909d-24acce3b2493","year":2023},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.433806Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:2329d51b745d85dae949f320218f46b4dfe8ed44255b3a24d2e6a2038cc222c7","observation_id":"5acc1211-5ffb-4f89-8e07-6f127207d20d","resolution":{"observed_at":"2026-08-15T23:59:30.615282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.591672Z","title":"Pneumonia detection using deep convolutional neural net- works,","venue":null,"work_id":"a51ec5f2-1bfb-4dbd-87e5-d45af79136d6","year":2023},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.439166Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:edf419e2ae9c379b218f46b528608e84990d0478658b9ca145c803a008e6f8c2","observation_id":"5b8bc819-2dba-4109-ab48-008ce892aa1e","resolution":{"observed_at":"2026-08-15T23:59:30.597116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.444802Z","title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.444802Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:126d6e6cedd30ead99ae6043509398133d4d5821aa17ff97c526fc0f53f1b61b","observation_id":"287c8217-2d9e-410a-86ac-dd23573ce867","resolution":{"observed_at":"2026-08-15T23:59:30.444802Z","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":"2026-08-15T23:59:30.562881Z","title":"Randaugment: Practical automated data augmentation with a reduced search space,","venue":null,"work_id":"987c6de8-1cf9-47c1-9b83-f9e2eaa9bc63","year":2020},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.449532Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:fd1e1a026b80bffccd00a3c04d8ccd79d3b0c5696390d4ad5ae1ad667e90d7bc","observation_id":"9cfa9b3a-649d-4ba1-b32d-ba812073f298","resolution":{"observed_at":"2026-08-15T23:59:30.568485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.545490Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization,","venue":null,"work_id":"374205d8-9e33-4d79-8464-ffcb7fea87a9","year":2017},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.454903Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:eea468a65a476081063094d1170d70bfab9f03252eae94ae9de4380501fae306","observation_id":"ee4fbed2-f3ed-4d8e-9458-1ae65ab6273c","resolution":{"observed_at":"2026-08-15T23:59:30.550704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-15T23:59:30.525325Z","title":"A unified approach to interpreting model predictions,","venue":null,"work_id":"4546548e-1916-4ecc-850f-320d65ad7df6","year":2017},"citing_paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects","version":5},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T23:59:30.459655Z"},"links":{"citing_paper":"/paper/2505.03303"},"observation_digest":"sha256:1db8c23ff43baf8be78152301bd2fb624c8a8f886564389da58dcbca55f3aa99","observation_id":"0c474336-ea2c-4656-909c-84ee0f88c5e9","resolution":{"observed_at":"2026-08-15T23:59:30.532652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.03303","last_updated":"2026-07-02T10:25:36Z","latest_version":5,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T23:52:35.855808Z","submitted_at":"2025-05-06T08:36:01Z","title":"Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":21},"total_outbound_references":26},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 2 inbound Pith citation observations for arXiv:2505.03303."}