{"as_of":"2026-08-15T10:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fa22874395eb70d4756b5b12d40fad6435953404c34ff571f9e6b7084e7e36f9","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":"2026-08-09T15:49:53.634233Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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":"2026-07-11T07:49:40.867148Z","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":"2026-07-08T01:14:27.453753Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"cited_work":{"arxiv_id":"2502.01303","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.01303","snapshot_observed_at":"2026-07-08T01:14:27.453753Z","title":"Partial Channel Network: Compute Fewer, Perform Better","venue":"cs.CV","work_id":"c7cc7321-5385-459e-8971-f3d9b4d6aa32","year":2025},"citing_paper":{"arxiv_id":"2607.05176","last_updated":"2026-07-07T08:16:00Z","snapshot_observed_at":"2026-08-12T22:27:51.917445Z","submitted_at":"2026-07-06T14:57:33Z","title":"FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-08T01:13:05.253777Z"},"links":{"cited_paper":"/paper/2502.01303","citing_paper":"/paper/2607.05176"},"observation_digest":"sha256:dc613e930003cb86e93a1e64b2e9a89d6e154cca39a99e01893f65919bb9a2c2","observation_id":"8a660241-7354-4ab4-ad8b-d903839f09c8","resolution":{"observed_at":"2026-07-08T01:14:27.455094Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01303","snapshot_observed_at":"2026-07-11T07:49:40.867148Z","title":"arXiv preprint arXiv:2502.01303 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.05176","last_updated":"2026-07-07T08:16:00Z","snapshot_observed_at":"2026-08-12T22:27:51.917445Z","submitted_at":"2026-07-06T14:57:33Z","title":"FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-11T07:49:40.867148Z"},"links":{"cited_paper":"/paper/2502.01303","citing_paper":"/paper/2607.05176"},"observation_digest":"sha256:73026d2537e13251236b2a37194e8078e824ee8b90010a7a7feeaef77e9e384a","observation_id":"06758165-883a-4be3-a3a6-abede08687e1","resolution":{"observed_at":"2026-07-11T07:49:40.867148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.01303/citation-record","integrity":"/paper/2502.01303/integrity","json":"/paper/2502.01303/citation-record.json","paper":"/paper/2502.01303"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T15:49:54.479059Z","title":"The kronecker product","venue":null,"work_id":"2636fca8-2dfd-41ba-bfbf-fee85fbc696f","year":2006},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.404048Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:17c1502058d2409f740bd9a9eacaff339ff65ba36d5caaba969116e306f09531","observation_id":"81f3c7f5-4a75-45aa-a1c5-96b6eff62974","resolution":{"observed_at":"2026-08-09T15:49:54.485299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.460416Z","title":"Efficientvit: Lightweight multi-scale attention for high- resolution dense prediction","venue":null,"work_id":"1eadc34f-47d1-47b9-b64d-fca19665645b","year":2023},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.410299Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:3229c0f306fc4c4436cb3e5b0d45899839f315b7694324bc35399cda43b0454c","observation_id":"89182a6c-0b1a-40e6-9260-df587e52e8b0","resolution":{"observed_at":"2026-08-09T15:49:54.465916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.441316Z","title":"Run, don’t walk: Chasing higher flops for faster neural networks","venue":null,"work_id":"6b7d8599-7d1b-4bdc-8a8c-b0a3362d67ef","year":2023},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.415761Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:c33f0a0fc932ad82a7ce35556f1aa0397fde0d88f94d6c08db43af0278b2370b","observation_id":"727943ba-3200-42bf-a130-fe02f2738b27","resolution":{"observed_at":"2026-08-09T15:49:54.446846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1602.02830","last_updated":"2016-03-17T14:54:25Z","snapshot_observed_at":"2026-08-15T07:00:41.403404Z","submitted_at":"2016-02-09T01:01:59Z","title":"Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.02830","snapshot_observed_at":"2026-08-09T15:49:53.421197Z","title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.421197Z"},"links":{"cited_paper":"/paper/1602.02830","citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:8c62f76007a9861006dcf55257f685d741217b185f7da9e5ee3701dc071230b7","observation_id":"1dbe592b-c24d-496f-af73-f3fb1042dc95","resolution":{"observed_at":"2026-08-09T15:49:53.421197Z","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":"2026-08-09T15:49:54.421293Z","title":"Scaling up your kernels to 31x31: Revisiting large kernel design in cnns","venue":null,"work_id":"fcd80d80-a1cb-46b4-b5df-2dac942957e1","year":2022},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.427237Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:10f24f8f885f27c431969e2912ebc57a9b75241d7098496eb5fbd18b768dc20f","observation_id":"13712661-2a74-4655-a8c2-bb20213c2b78","resolution":{"observed_at":"2026-08-09T15:49:54.427153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.402327Z","title":"Hawq: Hessian aware quantization of neural networks with mixed-precision","venue":null,"work_id":"77cc7e97-6a41-4968-9526-9a7985646b6e","year":2019},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.432560Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:711bbc9766841d39e3cd201872ae72c3765b6a6555051814305da486ebbf0ef5","observation_id":"658a7699-3beb-458d-8636-4e6d316b5e18","resolution":{"observed_at":"2026-08-09T15:49:54.408123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.384001Z","title":"Single- and multi-gpu computing on nvidia- and amd-based server platforms for solidification modeling application","venue":null,"work_id":"b8ab9938-8cea-476f-ae45-66e8ad45bc6f","year":2024},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.438016Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:0b7dcc7fa9120e25c7170e4f94d48c30508b59f8782dc4bfba579ee6170925c0","observation_id":"bbe8110c-2bec-4e2c-b11d-37215275ca97","resolution":{"observed_at":"2026-08-09T15:49:54.389582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.365581Z","title":"Ghostnet: More features from cheap operations","venue":null,"work_id":"5849e4f2-1f58-4b95-b1c8-a0973e73bdf1","year":null},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.444005Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:191298ead8ba427c2e641fd116fd612c5c21847bf4daabbe9a8b85ab7a5e5567","observation_id":"a88d08f9-ab13-4826-b028-c9dd9ff6b7f6","resolution":{"observed_at":"2026-08-09T15:49:54.371199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03385","last_updated":"2015-12-10T19:51:55Z","snapshot_observed_at":"2026-07-06T04:39:28.429064Z","submitted_at":"2015-12-10T19:51:55Z","title":"Deep Residual Learning for Image Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03385","snapshot_observed_at":"2026-08-09T15:49:53.449139Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.449139Z"},"links":{"cited_paper":"/paper/1512.03385","citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:17e8bfc5f770e2faadb160a65d94df9cb961ae4b3b5718561838768de33b00b9","observation_id":"4c9fb508-22ba-4b16-b975-39e200977f41","resolution":{"observed_at":"2026-08-09T15:49:53.449139Z","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":"2026-08-09T15:49:53.454929Z","title":"Mask r-cnn","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.454929Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:875166425819776f7fe252ea875900c2eee680d6a04a93f8cc737cbed3fe4add","observation_id":"7d9914c8-cb15-4955-b1c4-624d1614b367","resolution":{"observed_at":"2026-08-09T15:49:53.454929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.11943","last_updated":"2022-11-22T01:39:45Z","snapshot_observed_at":"2026-08-14T01:30:46.470820Z","submitted_at":"2022-11-22T01:39:45Z","title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.11943","snapshot_observed_at":"2026-08-09T15:49:53.460012Z","title":"Conv2former: A simple transformer-style convnet for visual recognition","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.460012Z"},"links":{"cited_paper":"/paper/2211.11943","citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:523274dbc89d79b84baf64bc6c3246dd6d1cac89de6441cf33fb0baae0dfa355","observation_id":"195f38ce-5853-420b-bd88-30d3af515f7f","resolution":{"observed_at":"2026-08-09T15:49:53.460012Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.02244","last_updated":"2019-11-20T17:26:40Z","snapshot_observed_at":"2026-08-14T16:36:30.006489Z","submitted_at":"2019-05-06T19:38:31Z","title":"Searching for MobileNetV3","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.02244","snapshot_observed_at":"2026-08-09T15:49:53.465874Z","title":"Le, and Hartwig Adam","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.465874Z"},"links":{"cited_paper":"/paper/1905.02244","citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:a6b12c532d6657ded0141720f06340d26784a23a8bb028192704fc5e0f4d87cf","observation_id":"67b909b2-b403-4775-bafd-5be0979d2968","resolution":{"observed_at":"2026-08-09T15:49:53.465874Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-09T15:49:53.471149Z","title":"Mobilenets: Efficient convolu- tional neural networks for mobile vision applications","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.471149Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:016af79410e4bf10ba000d1c344d606461d60307afaf517c2debbb9099b8448c","observation_id":"d31e7c38-b570-4f19-b79f-0db670f57ec8","resolution":{"observed_at":"2026-08-09T15:49:53.471149Z","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":"2026-08-09T15:49:54.332071Z","title":"Squeeze-and-excitation net- works","venue":null,"work_id":"ba226118-ba3c-4fa4-85bc-07e551c69e71","year":2018},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.476633Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:05bed7d58a515c2bd033d08b16470e2a51be361f29501b7aabb6ff37767ed582","observation_id":"0ad21170-ed3a-4800-892b-d554a7485744","resolution":{"observed_at":"2026-08-09T15:49:54.337931Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.313049Z","title":"Batch normalization: Accelerating deep network training by reducing internal co- variate shift","venue":null,"work_id":"d31d506f-35f2-4686-bca4-0e9547c06799","year":2015},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.481709Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:62cf08605770d99483a3af236693db4045799590f2c51bca0447e70ba5e2f0b0","observation_id":"a7da57b6-9818-4861-87da-674a84447ac1","resolution":{"observed_at":"2026-08-09T15:49:54.318860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.294850Z","title":"Programming mas- sively parallel processors: a hands-on approach","venue":null,"work_id":"4444de77-2ae7-4573-9198-fff2254e5e96","year":2016},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.486674Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:74db5dfb38c9361ef7c85e08358c1530c4543bbf478ddbb5a51c9b2ccb724519","observation_id":"2536722a-f091-48b7-8c33-fe06f8852d34","resolution":{"observed_at":"2026-08-09T15:49:54.300512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.271954Z","title":"Srm: A style-based recalibration module for convolutional neural networks","venue":null,"work_id":"ba079447-3113-48ce-aa7b-d206b168d77b","year":2019},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.496827Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:dd7502ba71705009ac01de1e81ba505bad67456758872534f24542308d765a27","observation_id":"cf33f261-da3d-43f3-b002-4a9515821949","resolution":{"observed_at":"2026-08-09T15:49:54.278399Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.248762Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":"c7e8f056-6096-4799-bf55-90ad8821f774","year":2021},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.501940Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:400eea301dcfdba69c1b894d86c827b70734c77e42c74ff0dc2e9122bc9348cd","observation_id":"ad87a2e3-38fc-4bf1-a47d-15566345ba04","resolution":{"observed_at":"2026-08-09T15:49:54.255449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:53.507388Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.507388Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:2fca9ea92fbde0f10c8631915a75453e43561387855aa9d306cdbc830693179e","observation_id":"91adaa80-8a3a-4628-a6fa-17ee11a52e81","resolution":{"observed_at":"2026-08-09T15:49:53.507388Z","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":"2026-08-09T15:49:54.212023Z","title":"Shufflenet v2: Practical guidelines for efficient cnn architec- ture design","venue":null,"work_id":"2914440a-958b-4176-8c98-2cf3091c1a1d","year":2018},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.512381Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:99929ae796d1b45f0d478fd4940bf26bd699be8fc4bf2c6e896d9d1fb03e53a0","observation_id":"5607f323-a45d-4997-b595-10625eddd9cb","resolution":{"observed_at":"2026-08-09T15:49:54.218380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.02178","last_updated":"2022-03-04T17:17:31Z","snapshot_observed_at":"2026-08-15T04:06:58.388670Z","submitted_at":"2021-10-05T17:07:53Z","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.02178","snapshot_observed_at":"2026-08-09T15:49:53.517569Z","title":"Mobilevit: light- weight, general-purpose, and mobile-friendly vision trans- former","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.517569Z"},"links":{"cited_paper":"/paper/2110.02178","citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:18c03e3470f29bf6e1cf21eda76483dc45e07efba28dc7a468730b26a7b116cc","observation_id":"9fd2719e-8a7e-46f0-a2fa-f3c08c7bcc7a","resolution":{"observed_at":"2026-08-09T15:49:53.517569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.02680","last_updated":"2022-06-06T15:31:35Z","snapshot_observed_at":"2026-08-13T15:29:23.546543Z","submitted_at":"2022-06-06T15:31:35Z","title":"Separable Self-attention for Mobile Vision Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.02680","snapshot_observed_at":"2026-08-09T15:49:53.522971Z","title":"Separable self- attention for mobile vision transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.522971Z"},"links":{"cited_paper":"/paper/2206.02680","citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:5f2833dd69ae18a8fa122a51a72cd5f7380194ca9378291b33851adc7a1b911d","observation_id":"4efe5668-7c42-4b1a-a5df-d2f1acd50a84","resolution":{"observed_at":"2026-08-09T15:49:53.522971Z","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":"2026-08-09T15:49:54.192380Z","title":"Edgevits: Competing light-weight cnns on mobile devices with vision transformers","venue":null,"work_id":"77d7ce0d-8e09-43fe-b28e-a554e34c7768","year":2022},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.528705Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:21d7fcff266ff0ca505f1a3b458857c65ec4309e731449f8ec6d0de8888544c4","observation_id":"16cc6d8c-4643-4db5-81ae-757bdd3e9d7b","resolution":{"observed_at":"2026-08-09T15:49:54.198239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.171589Z","title":"Vision transformers are robust learners","venue":null,"work_id":"e0011af6-0420-40dc-8afa-98cf2561f7a6","year":2022},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.533753Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:177111770fd13e2d24730f765bc9c9d87215a52cffafaf9d870ddeb5f1a1ea87","observation_id":"75835875-4460-468b-a26e-b829969d84f6","resolution":{"observed_at":"2026-08-09T15:49:54.179614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.151983Z","title":"Do vision trans- formers see like convolutional neural networks? Advances in Neural Information Processing Systems, 34:12116–12128,","venue":null,"work_id":"f0c6a723-03ed-4d5a-971a-7fa8b0938935","year":null},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.538867Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:68a9f5658c3fe85b8281311ff5ca5285ec7312e8085b86e5a74111d135ff8a87","observation_id":"6d8ab566-50a2-4823-bbf3-9316b29d6268","resolution":{"observed_at":"2026-08-09T15:49:54.158354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.127552Z","title":"Hornet: Efficient high- order spatial interactions with recursive gated convolutions","venue":null,"work_id":"894b24d2-c2e7-48f5-8f34-d0d093452955","year":2022},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.544127Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:27f26d834d3c7f165755b9b6a859d9f7a8932fa0749723e9a3456ce0970f4274","observation_id":"49b46897-2a37-4d17-96e9-f7f82690810b","resolution":{"observed_at":"2026-08-09T15:49:54.135487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.104817Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":"a4f60081-d510-486e-916a-0445ff04058e","year":2018},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.548955Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:a779967bc6c9473773702befb85721e5e19f291c61d23be78568c84e71004202","observation_id":"ef401895-9688-4307-a71f-3c8adffb40f2","resolution":{"observed_at":"2026-08-09T15:49:54.111174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:53.554292Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.554292Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:e02365987237193bcde59416a1b25cb8da30869857941d6180fccfa3ce9acccb","observation_id":"382cdd3f-8142-4f48-8b1f-d8214c916d16","resolution":{"observed_at":"2026-08-09T15:49:53.554292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15446","last_updated":"2023-07-25T19:56:00Z","snapshot_observed_at":"2026-08-13T12:15:24.807036Z","submitted_at":"2023-03-27T17:59:58Z","title":"SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15446","snapshot_observed_at":"2026-08-09T15:49:53.559625Z","title":"Swiftformer: Efficient additive attention for transformer- based real-time mobile vision applications","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.559625Z"},"links":{"cited_paper":"/paper/2303.15446","citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:d613819af9ef15210aaaf41e31708ad19641f1fbdffae917038a01be4fa633e1","observation_id":"66079d12-ddbd-4d88-aeaf-b025852c07a2","resolution":{"observed_at":"2026-08-09T15:49:53.559625Z","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":"2026-08-09T15:49:53.564982Z","title":"Efficientnet: Rethinking model scaling for convolutional neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.564982Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:52e46b398bb5a00da153d5b00c0061ea8c04f37f4ad3c9e85c8553011f5b9bd2","observation_id":"33cede07-bcd6-418e-b7cd-de44e79ae507","resolution":{"observed_at":"2026-08-09T15:49:53.564982Z","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":"2026-08-09T15:49:54.061771Z","title":"Efficientnetv2: Smaller models and faster training","venue":null,"work_id":"f9e76530-f375-42f4-a209-b0f482785a97","year":2021},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.570876Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:6e6f5cac54e3211a8d082d272493823c3cefe623330ec50ccf130d91c65a82c8","observation_id":"64aa353b-92c5-4673-9799-11a2f23c270f","resolution":{"observed_at":"2026-08-09T15:49:54.067387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.04768","last_updated":"2020-06-14T08:15:54Z","snapshot_observed_at":"2026-07-06T09:27:03.809621Z","submitted_at":"2020-06-08T17:37:52Z","title":"Linformer: Self-Attention with Linear Complexity","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.04768","snapshot_observed_at":"2026-08-09T15:49:53.576509Z","title":"Linformer: Self-attention with linear complexity","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.576509Z"},"links":{"cited_paper":"/paper/2006.04768","citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:19f6dc3b7274f109326bb74b397687691e7b38b68808d7c30c4a23c2bb7458ac","observation_id":"74dcfa27-59aa-4705-9305-c41bbbee195b","resolution":{"observed_at":"2026-08-09T15:49:53.576509Z","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":"2026-08-09T15:49:54.041514Z","title":"Pyramid vision transformer: A versatile backbone for dense prediction without convolutions","venue":null,"work_id":"fa6a8ea4-3739-4012-ac64-4203bab17b83","year":2021},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.581869Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:ec555b075f24dbf0fcb7ba7864c47a6c7ed99019bb65be0b483fe09e24e87748","observation_id":"526884ca-62ed-421b-ad4a-10b4848f115c","resolution":{"observed_at":"2026-08-09T15:49:54.048772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.020926Z","title":"Cbam: Convolutional block attention module","venue":null,"work_id":"3dceb0b5-4928-4798-b2f4-ff0c6920a55d","year":2018},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.587010Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:29deb5835403b7de3bed226ae1f3b3f4cd888bf26a368d4cd32846dd16f5788c","observation_id":"d54dd7c9-7d80-4807-8b47-102260207910","resolution":{"observed_at":"2026-08-09T15:49:54.027623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:54.001196Z","title":"Rethinking and improving relative posi- tion encoding for vision transformer","venue":null,"work_id":"fae9977a-c2c1-4d49-b3fa-d536cd32ef1c","year":2021},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.591966Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:938aaafb8dc303f117e43e593a2160c82d3d98d6bc71935a26d301bcfc04aee1","observation_id":"2ba88739-4010-4a7b-a824-b2e9795f1cd1","resolution":{"observed_at":"2026-08-09T15:49:54.007578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:53.597368Z","title":"Aggregated residual transformations for deep neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.597368Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:496019d78b945e7952931ffd69e74a796e76b72a74614f1fc6edd8f0cc03c66b","observation_id":"eb72910b-bf77-46b4-88eb-ee670f327bdc","resolution":{"observed_at":"2026-08-09T15:49:53.597368Z","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":"2026-08-09T15:49:53.965981Z","title":"Focal modulation networks","venue":null,"work_id":"672e2217-4976-49b7-888d-4a0d2a73df82","year":2022},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.602797Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:306a3c6e8fe3ddf585cfe6e7ba5848e7f53e5c3ad7c4acbae060c9f60acef5ec","observation_id":"13f6905c-7821-4f46-b15d-0d36309acbcc","resolution":{"observed_at":"2026-08-09T15:49:53.973670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:53.947466Z","title":"Metaformer is actually what you need for vision","venue":null,"work_id":"8cf4818e-1113-485c-baf1-0b4979a2f1bd","year":2022},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.608097Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:279a1edd421f3b64ee2a2fbd922d8488d20f94ac1108d845b1933f18d3ce2890","observation_id":"a56f74e5-a86a-417c-96bc-c4ee2e84183f","resolution":{"observed_at":"2026-08-09T15:49:53.952973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:53.928467Z","title":"Differ- entiable learning-to-group channels via groupable convolu- tional neural networks","venue":null,"work_id":"3ad75b9e-57bf-4a60-9416-ea6ef61159e0","year":2019},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.613081Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:9b50524b8e9fc86c4a917c8dbde4030d9c348d995c21be769f139c0848d13bbe","observation_id":"a1fbb722-ffbf-4b5a-be48-b4a0986c1d69","resolution":{"observed_at":"2026-08-09T15:49:53.933955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:53.908652Z","title":"• Firstly, we provide detailed explanations of our experi- mental setup, the specifics of the three PATConv blocks, and the different PartialNet variants","venue":null,"work_id":"f58fc715-b0ce-4998-a9e0-e656f8ee253a","year":null},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.618308Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:6b902ab8fb32d24e20a0c9ebe816a1465e6c0a862f0955c114d7259fb3c5103f","observation_id":"8df1e3d1-f13b-4243-8c3c-a1c6e4c2f7d1","resolution":{"observed_at":"2026-08-09T15:49:53.915091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:53.891120Z","title":null,"venue":null,"work_id":"abc38e59-dc92-41e6-b855-4e2bc0c7a31e","year":null},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.623759Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:7ae2457b486c347f6cd837b438806fa9a5946b3ee3211dd4c7af4d7f7455772d","observation_id":"c03d2dde-8a14-4bac-9d6f-0404bd6288da","resolution":{"observed_at":"2026-08-09T15:49:53.896334Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:53.870774Z","title":"For the full comparison of the classification task on the ImageNet-1k Benchmark, please refer to Tab","venue":null,"work_id":"56f9dbcf-28c0-47a8-9a83-76c7740b7409","year":null},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.629050Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:74a7eca76db8ca168480f791c25edc2f5e8a34f4c95be99baf5e7b256537b7ae","observation_id":"3d77cdab-43fc-4599-8f49-6c3dff1af346","resolution":{"observed_at":"2026-08-09T15:49:53.877990Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-09T15:49:53.849690Z","title":null,"venue":null,"work_id":"4f21bcef-14e7-4bf3-9977-8c26a13bee03","year":null},"citing_paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T15:49:53.634233Z"},"links":{"citing_paper":"/paper/2502.01303"},"observation_digest":"sha256:df230ddce124cf7e6958a18a85bd2fff400b42729d95c16bbbf4a67d96579768","observation_id":"d9fca5c7-6749-4565-a1be-b2f5138054f5","resolution":{"observed_at":"2026-08-09T15:49:53.856658Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.01303","last_updated":"2025-02-03T12:26:55Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T03:14:02.132045Z","submitted_at":"2025-02-03T12:26:55Z","title":"Partial Channel Network: Compute Fewer, Perform Better"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":0,"verified_fuzzy":27},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 2 inbound Pith citation observations for arXiv:2502.01303."}