{"as_of":"2026-08-18T08:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:496028ff19a48ccf212542456d71b3992e2e216acfeaa4b3871f75122b07e502","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T14:15:23.971549Z","state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2501.15547/citation-record","integrity":"/paper/2501.15547/integrity","json":"/paper/2501.15547/citation-record.json","paper":"/paper/2501.15547"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1603.04467","last_updated":"2016-03-16T16:57:12Z","snapshot_observed_at":"2026-08-14T22:06:04.800050Z","submitted_at":"2016-03-14T20:50:20Z","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1603.04467","snapshot_observed_at":"2026-08-10T14:15:23.849031Z","title":"Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et al","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.849031Z"},"links":{"cited_paper":"/paper/1603.04467","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:0e9657201c5905950f6b05d22fb958c994ba77f5d3b22928c871ba4393c62ba9","observation_id":"c6dbc002-e3a2-4e75-9256-3509014bc558","resolution":{"observed_at":"2026-08-10T14:15:23.849031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1206.5533","last_updated":"2012-09-16T17:49:12Z","snapshot_observed_at":"2026-08-16T20:54:27.654526Z","submitted_at":"2012-06-24T19:17:35Z","title":"Practical recommendations for gradient-based training of deep architectures","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1206.5533","snapshot_observed_at":"2026-08-10T14:15:23.854332Z","title":"Practical recommendations for gradient-based training of deep architectures","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.854332Z"},"links":{"cited_paper":"/paper/1206.5533","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:ea7eff0498f0143891d1814db734338b2925e23db147180a92f5f380ffb3f400","observation_id":"92d4011f-fa79-4759-89c4-c0567d84d892","resolution":{"observed_at":"2026-08-10T14:15:23.854332Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.02243","last_updated":"2019-06-05T18:40:53Z","snapshot_observed_at":"2026-08-14T16:20:15.943278Z","submitted_at":"2019-06-05T18:40:53Z","title":"Energy and Policy Considerations for Deep Learning in NLP","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.02243","snapshot_observed_at":"2026-08-10T14:15:23.859159Z","title":"Machine learning at microsoft with ml.net","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.859159Z"},"links":{"cited_paper":"/paper/1906.02243","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:f196bd6392e3596b8603430349702e387a7ca540b13d35ac7f2e3611f6b1c91f","observation_id":"80b11d5b-1f86-4518-8e85-e26e6b7f4188","resolution":{"observed_at":"2026-08-10T14:15:23.859159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1404.0736","last_updated":"2014-06-09T15:53:55Z","snapshot_observed_at":"2026-08-17T23:44:04.204507Z","submitted_at":"2014-04-02T23:31:12Z","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","version":2},"cited_work":{"arxiv_id":"1404.0736","doi":null,"metadata_source":"pith","pith_arxiv_id":"1404.0736","snapshot_observed_at":"2026-08-10T14:15:24.592396Z","title":"Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation","venue":"cs.CV","work_id":"dc13ac84-e53f-447e-be58-57dcc0a0cca5","year":2014},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.864588Z"},"links":{"cited_paper":"/paper/1404.0736","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:8fa94168a7493f7a0d2d8c6d3a94ae890c93429ddd5b97e3783d1c4d2194eba2","observation_id":"9d369a8d-2d64-43ed-a5b7-bd66fc9d0af3","resolution":{"observed_at":"2026-08-10T14:15:24.597633Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T14:15:23.869869Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.869869Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:c37397feb684524347615ce2eb83a0d1c04e111331ddbb9f3e93cbc6f65c800b","observation_id":"e5aae9ce-d50f-4d46-9920-5de310a600b5","resolution":{"observed_at":"2026-08-10T14:15:23.869869Z","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":"10.3390/app14135898","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:15:24.087718Z","title":"Reducing model complexity in neural networks by using pyramid training approaches","venue":null,"work_id":"7d43c9f7-622b-4d31-aa65-f3389002199d","year":2024},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.874746Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:60c0f5502371e8a31885dcd2d1fd963418ed8b5999c01c704cc83e374c54b35c","observation_id":"c369e4b6-f9e9-4a7b-b1bf-570f848b1bd9","resolution":{"observed_at":"2026-08-10T14:15:24.093977Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1506.02626","last_updated":"2015-10-30T23:29:27Z","snapshot_observed_at":"2026-08-15T13:34:24.234242Z","submitted_at":"2015-06-08T19:28:43Z","title":"Learning both Weights and Connections for Efficient Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.02626","snapshot_observed_at":"2026-08-10T14:15:23.880389Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.880389Z"},"links":{"cited_paper":"/paper/1506.02626","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:abf457a43e368c0b3faf5a4170ca26bd63d0f64f91fef9e1978f0e1a62b8c612","observation_id":"e701cb2c-cb43-4b93-9a1d-8c3e7c52c795","resolution":{"observed_at":"2026-08-10T14:15:23.880389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.06146","last_updated":"2018-05-23T09:23:47Z","snapshot_observed_at":"2026-08-14T19:54:00.470999Z","submitted_at":"2018-01-18T17:54:52Z","title":"Universal Language Model Fine-tuning for Text Classification","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.06146","snapshot_observed_at":"2026-08-10T14:15:23.885109Z","title":"Universal language model fine-tuning for text classification","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.885109Z"},"links":{"cited_paper":"/paper/1801.06146","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:d00191689937c4e7f065b096d97a2cce834623c4e7aa0f4e14825da50f86861f","observation_id":"2361b84a-49d3-42ca-a89d-6ffad699f564","resolution":{"observed_at":"2026-08-10T14:15:23.885109Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.06993","last_updated":"2018-01-28T17:12:02Z","snapshot_observed_at":"2026-08-14T21:42:53.838437Z","submitted_at":"2016-08-25T00:44:55Z","title":"Densely Connected Convolutional Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.06993","snapshot_observed_at":"2026-08-10T14:15:23.890026Z","title":"Weinberger","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.890026Z"},"links":{"cited_paper":"/paper/1608.06993","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:9290f208dca0b01b887e4ab1e2bba0913c783a6459b3f64956589b0bbf8dfd03","observation_id":"ce0fbe07-d78d-48c0-8a35-6394a097bf14","resolution":{"observed_at":"2026-08-10T14:15:23.890026Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:15:23.894717Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.894717Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:7af0ef8beeabbfdeaa564fa8b447baec75915fb0a0f37e06989085c8476d69bb","observation_id":"9bc021f0-67c1-454a-a99a-a141d8ed1253","resolution":{"observed_at":"2026-08-10T14:15:23.894717Z","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":"2026-08-10T14:15:24.720813Z","title":"Efficient gpu usage tips","venue":null,"work_id":"21e226dc-2a51-4ef3-8305-964c8509e855","year":2025},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.899315Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:065c7c2bf6bd3fd516adad3d9e3460fc6e71455039d2f40fccb926e3bdb08bf2","observation_id":"42088542-7f6b-4a37-9772-e0c9ad5824eb","resolution":{"observed_at":"2026-08-10T14:15:24.725568Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T14:15:24.704652Z","title":"A study of cross-validation and bootstrap for accuracy estimation and model selection","venue":null,"work_id":"f3152f45-c00e-4c7c-83f9-c4c8d7251ccf","year":1995},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.904181Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:260b127d62a66d18d15982098fc3b214cf842823c4cfe33ea87cdd4af6db2bfa","observation_id":"7be8de0a-586e-4ad0-b434-123f48082b21","resolution":{"observed_at":"2026-08-10T14:15:24.710137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T14:15:23.908905Z","title":"Imagenet classification with deep convolutional neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.908905Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:c7700c772424863cd82f24911642a4903216dc0f709df3a791304b7bc6d0e7de","observation_id":"d021e134-c43c-4494-8609-790aeac2663c","resolution":{"observed_at":"2026-08-10T14:15:23.908905Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.09359","last_updated":"2023-10-10T05:31:01Z","snapshot_observed_at":"2026-08-16T16:15:29.579004Z","submitted_at":"2022-11-17T06:18:45Z","title":"How to Fine-Tune Vision Models with SGD","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.09359","snapshot_observed_at":"2026-08-10T14:15:23.913540Z","title":"How to fine-tune vision models with sgd","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.913540Z"},"links":{"cited_paper":"/paper/2211.09359","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:e6bf12f504a0e29e2ebe11aac5e004e92d7787252a1461d27ec842fcab266575","observation_id":"ea5be402-f2a6-4437-ab0e-e99b9a17df48","resolution":{"observed_at":"2026-08-10T14:15:23.913540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:15:23.918177Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.918177Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:87a12ac3e804b482a13bb7a8017b58c9c04570ee80d2f922e2f51a5690a62290","observation_id":"965d9bf5-ae1e-4133-a44d-1e3d46716196","resolution":{"observed_at":"2026-08-10T14:15:23.918177Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.11233","last_updated":"2018-05-29T03:36:40Z","snapshot_observed_at":"2026-08-14T19:10:07.890560Z","submitted_at":"2018-05-29T03:36:40Z","title":"Retraining-Based Iterative Weight Quantization for Deep Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.11233","snapshot_observed_at":"2026-08-10T14:15:23.922782Z","title":"Retraining-based iterative weight quantization for deep neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.922782Z"},"links":{"cited_paper":"/paper/1805.11233","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:5b771604faac710e603778b336b80f8f4e958bd55c158c63509489da7f649e72","observation_id":"7efd19bb-96d0-4565-9222-9bed8cef6dca","resolution":{"observed_at":"2026-08-10T14:15:23.922782Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07236","last_updated":"2024-04-12T09:34:38Z","snapshot_observed_at":"2026-08-16T14:02:49.402371Z","submitted_at":"2024-04-08T08:50:09Z","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07236","snapshot_observed_at":"2026-08-10T14:15:23.927846Z","title":"Lightweight deep learning for resource-constrained environments","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.927846Z"},"links":{"cited_paper":"/paper/2404.07236","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:2862fbf26b1b41f1e93db2f02c10d1aaa4bc63c98386a193facda0b024cf7ea0","observation_id":"86e2b82c-6632-4926-83b6-552ca5cc5832","resolution":{"observed_at":"2026-08-10T14:15:23.927846Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1411.4038","last_updated":"2015-03-08T22:16:40Z","snapshot_observed_at":"2026-08-14T23:11:33.960926Z","submitted_at":"2014-11-14T20:46:03Z","title":"Fully Convolutional Networks for Semantic Segmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1411.4038","snapshot_observed_at":"2026-08-10T14:15:23.932692Z","title":"Fully convolutional networks for semantic segmentation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.932692Z"},"links":{"cited_paper":"/paper/1411.4038","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:9ae8dae7bf5f4d21ff5fd7ec8a41c4be84b097c18ccc060999f04592362bb01b","observation_id":"f5f0a724-0f2c-462a-9925-47c4a8e3673d","resolution":{"observed_at":"2026-08-10T14:15:23.932692Z","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":"10.3390/e20040305","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:15:24.048583Z","title":"Maji and R","venue":null,"work_id":"d6e3e10c-b0be-4374-afa2-3989b486d225","year":2018},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.937567Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:444a4964a3b3f083ca953ba01a71dd3dcc472d8565641bf8481f6a79435eabfe","observation_id":"529c1293-cb51-4a37-91ff-550a46f589e4","resolution":{"observed_at":"2026-08-10T14:15:24.054793Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T14:15:23.942516Z","title":"A survey on transfer learning","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.942516Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:8018aba32dbd361da722f344554725b2b08729e75bc92774633e27f441dc7fe0","observation_id":"eec0e5e3-549e-455c-acc5-4f3ad6c16b04","resolution":{"observed_at":"2026-08-10T14:15:23.942516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:15:23.947161Z","title":"Khoshgoftaar","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.947161Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:9c6a2850a8e53a803ccfbb56e592c351ca5855be4c4624c5dd31b3154fd3a08a","observation_id":"9bc2d08a-e64a-447e-97c6-510ac25455d3","resolution":{"observed_at":"2026-08-10T14:15:23.947161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-17T19:17:06.411141Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-10T14:15:23.951302Z","title":"Very deep convolutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.951302Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:8573085e3adccb80fe460b7ac05641f5fc21c802af31433a22ca42af5bc45492","observation_id":"a67eb6fe-c4f9-4cd0-b2b2-0c0adc759f43","resolution":{"observed_at":"2026-08-10T14:15:23.951302Z","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":"2026-08-10T14:15:24.688457Z","title":"Dropout: A simple way to prevent neural networks from overfitting","venue":null,"work_id":"9d37779d-30d5-43e9-82ff-ae5aa6ba585b","year":1929},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.955641Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:e14e7f85d4276da6a6b6a18508277e2ffface3fbe01e3bd104a0993b38ea1437","observation_id":"d1d87ba6-f4f7-409b-9584-891a9f403832","resolution":{"observed_at":"2026-08-10T14:15:24.693936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T14:15:23.959762Z","title":"Rethinking the inception architecture for computer vision","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.959762Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:007a77f3fa1705a4249d894d5e004e06e6f9e1c60c11d88513a5b3f960fca9ec","observation_id":"56f071d1-46b8-4e46-b019-d224206c6492","resolution":{"observed_at":"2026-08-10T14:15:23.959762Z","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":"2026-08-10T14:15:24.673263Z","title":"Gpu kernel-tesla p100 gpu","venue":null,"work_id":"1e388aba-dcc7-4f96-88ab-3657617c9fa9","year":2025},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.963788Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:350c35d0481dde8ea1ed08a5834855db24186028c0810768e6cf4091b12c6bbb","observation_id":"13757034-3949-47a5-94cc-d12c35c240ca","resolution":{"observed_at":"2026-08-10T14:15:24.677923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2023.10168","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:15:24.199062Z","title":"Lcrm: Layer-wise complexity reduction method for cnn model optimization on end devices","venue":null,"work_id":"24fd71af-acd2-4146-817a-8b97a882335e","year":2023},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.967634Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:e3e542a8378b81d7194d2d731ee7f6c75132ac0200202880a38642cd349b0894","observation_id":"0fbcc01e-278c-455b-81e2-f0e76520bfbc","resolution":{"observed_at":"2026-08-10T14:15:24.208119Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-10T14:15:24.657941Z","title":"The correct way to measure inference time of deep neural networks","venue":null,"work_id":"20af2eb4-9030-4fed-81a7-efc80bce836a","year":2020},"citing_paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-10T14:15:23.971549Z"},"links":{"citing_paper":"/paper/2501.15547"},"observation_digest":"sha256:0ce087dbec4ae1fb87b6ef7ed5bd1e08a7e12fe56059d64f0d63d0fb6aae9327","observation_id":"80c924a0-a359-48e5-80ac-44bdd34a9b4b","resolution":{"observed_at":"2026-08-10T14:15:24.662780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.15547","last_updated":"2025-01-26T14:39:01Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T03:57:43.145950Z","submitted_at":"2025-01-26T14:39:01Z","title":"Building Efficient Lightweight CNN Models"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":18,"verified_exact":3,"verified_fuzzy":5},"total_outbound_references":27},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2501.15547."}