{"as_of":"2026-08-18T16:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8189a431c6037b0de65b798f55a0ac36e3d63d6494fa9cd5201800c3b6deeb1b","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T21:57:13.675007Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:26:47.130594Z","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":"2026-08-15T20:26:47.164540Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"cited_work":{"arxiv_id":"2501.18953","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.18953","snapshot_observed_at":"2026-08-15T20:26:47.164540Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","venue":"cs.AR","work_id":"1b49159d-d141-4713-ab73-735cf3cd029c","year":2025},"citing_paper":{"arxiv_id":"2505.13060","last_updated":"2025-05-19T12:51:02Z","snapshot_observed_at":"2026-08-18T02:42:11.323945Z","submitted_at":"2025-05-19T12:51:02Z","title":"Automatic mixed precision for optimizing gained time with constrained loss mean-squared-error based on model partition to sequential sub-graphs","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T20:26:47.130594Z"},"links":{"cited_paper":"/paper/2501.18953","citing_paper":"/paper/2505.13060"},"observation_digest":"sha256:a16e16ed9b59c763d9bc55795092f5b50bf087babd5fa21be88d2bb54b1f1745","observation_id":"f3a63e34-f40d-4ec6-a3b0-cdf127599aa8","resolution":{"observed_at":"2026-08-15T20:26:47.170372Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2501.18953/citation-record","integrity":"/paper/2501.18953/integrity","json":"/paper/2501.18953/citation-record.json","paper":"/paper/2501.18953"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.09026","last_updated":"2024-04-11T23:26:33Z","snapshot_observed_at":"2026-08-16T14:09:59.351673Z","submitted_at":"2024-03-14T01:39:12Z","title":"FlexNN: A Dataflow-aware Flexible Deep Learning Accelerator for Energy-Efficient Edge Devices","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.09026","snapshot_observed_at":"2026-08-09T21:57:13.484732Z","title":"FlexNN: A dataflow-aware flexible deep learning accelerator for energy-efficient edge devices,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.484732Z"},"links":{"cited_paper":"/paper/2403.09026","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:5749c7a512f87524aeceeb28aad67ada9e03beefc502ddaa79c9bf1f7b9f63a2","observation_id":"dd328713-eee6-457f-8390-3e5972f57adc","resolution":{"observed_at":"2026-08-09T21:57:13.484732Z","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":"2026-08-09T21:57:14.490231Z","title":"Going deeper with convolutions,","venue":null,"work_id":"c73bd470-402d-4866-8402-1a5ff7545d49","year":2015},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.490271Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:fad75cf0a664b65e39668b7383128abd084429bf76cd1b6de9029e17d732e6fc","observation_id":"0dd107dd-ec48-4909-94d4-27d7e36b4071","resolution":{"observed_at":"2026-08-09T21:57:14.496215Z","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":{"arxiv_id":"1602.07360","last_updated":"2016-11-04T21:26:08Z","snapshot_observed_at":"2026-08-14T22:09:04.541956Z","submitted_at":"2016-02-24T00:09:45Z","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.07360","snapshot_observed_at":"2026-08-09T21:57:13.495517Z","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.495517Z"},"links":{"cited_paper":"/paper/1602.07360","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:bf886688f51e59599a9f129a3f020b320bfdc7f2f7890157d8a89b46c4c5ea97","observation_id":"2bcabf49-3a9f-4ecc-9881-b9d94d69b5f6","resolution":{"observed_at":"2026-08-09T21:57:13.495517Z","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":"2026-08-09T21:57:13.501237Z","title":"MobileNets: Efficient convolutional neural networks for mobile vision applications,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.501237Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:d46cea3a466a77586affdcc9a79bd72e22537804c2d6abd92d2cd9dfb477d37e","observation_id":"5b299349-2fef-4291-8c7f-bdbd3077a797","resolution":{"observed_at":"2026-08-09T21:57:13.501237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00298","last_updated":"2021-06-23T22:04:56Z","snapshot_observed_at":"2026-08-16T18:34:34.624252Z","submitted_at":"2021-04-01T07:08:36Z","title":"EfficientNetV2: Smaller Models and Faster Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00298","snapshot_observed_at":"2026-08-09T21:57:13.506533Z","title":"EfficientNetV2: Smaller models and faster training,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.506533Z"},"links":{"cited_paper":"/paper/2104.00298","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:c63968e7d784db9b09f464833a56e80afb082ff5464296a179340e0ba73864c3","observation_id":"b396912e-7a3d-4a69-bf50-25f1cf43abac","resolution":{"observed_at":"2026-08-09T21:57:13.506533Z","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":"2026-08-09T21:57:13.511881Z","title":"Shufflenet: An extremely efficient convolutional neural network for mobile devices,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.511881Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:a17557ab4ff5f25350a0286fe0c265f4b25b658464ec94bee5bd934fa99dda88","observation_id":"4a20139a-6ad0-4395-936f-cd02737bfee1","resolution":{"observed_at":"2026-08-09T21:57:13.511881Z","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":"2026-08-09T21:57:13.517612Z","title":"Xception: Deep learning with depthwise separable convolu- tions,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.517612Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:c19de0bf8554b83a4d1f0cf1243a1868233f27a913bc6b6ca79b90d49563b2d7","observation_id":"99eb3ceb-3337-4c0c-b389-1a8aedb07746","resolution":{"observed_at":"2026-08-09T21:57:13.517612Z","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":"2026-08-09T21:57:14.422866Z","title":"Neural architecture search with reinforcement learning,","venue":null,"work_id":"3f790492-0dc7-408c-a670-fac96cc49696","year":null},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.522288Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:fd820738dfa8ea8fb9407db1aa6a89ceeec6a3acdd1323fd8787e837699b1ac7","observation_id":"9d970deb-bd8c-4791-9039-b2c4765ef508","resolution":{"observed_at":"2026-08-09T21:57:14.431192Z","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":"2026-08-09T21:57:14.376956Z","title":"ProxylessNAS: Direct neural architecture search on target task and hardware,","venue":null,"work_id":"900f31c8-111b-48b4-ae0f-6aa82c91244b","year":2019},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.533109Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:f20418f82bce584c4cedfc46c40280450358f65ec35344ce03d402c488a6bb7d","observation_id":"c53a4148-5265-4da3-95c5-6037fdbd2dbe","resolution":{"observed_at":"2026-08-09T21:57:14.382626Z","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":"2026-08-09T21:57:14.346170Z","title":"MnasNet: Platform-aware neural architecture search for mobile,","venue":null,"work_id":"f80a52c6-ad16-4c46-ad29-09385ec7ce5f","year":2019},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.538236Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:5a923adfc715b48bae69c76700996cb9d4f736889d45d9e3555af9c6e4fb775f","observation_id":"616c33a3-414f-4245-95d6-e4b7397e3c2c","resolution":{"observed_at":"2026-08-09T21:57:14.356784Z","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":{"arxiv_id":"1606.06160","last_updated":"2018-02-02T01:43:54Z","snapshot_observed_at":"2026-08-15T08:38:24.917341Z","submitted_at":"2016-06-20T15:02:31Z","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.06160","snapshot_observed_at":"2026-08-09T21:57:13.543297Z","title":"DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.543297Z"},"links":{"cited_paper":"/paper/1606.06160","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:2eb9d6dabaaa68953bcae3db7f29edd38e820dfcaa6424c53ae04ff1c92721e6","observation_id":"8d1032ff-d9d2-4ad0-bb6c-5a11554d3b7a","resolution":{"observed_at":"2026-08-09T21:57:13.543297Z","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":"2026-08-09T21:57:14.324452Z","title":"Binarized neural networks,","venue":null,"work_id":"6f50e049-ec6b-46b9-8faa-2f235d752cad","year":2016},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.548807Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:30196ee868b44a2c343b4ecdc8e312fa5976b855d462bcb3fa261039be0159ba","observation_id":"94d24f96-326f-4173-a5f0-5134aa0ebbe6","resolution":{"observed_at":"2026-08-09T21:57:14.330911Z","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":"2026-08-09T21:57:14.301030Z","title":"FINN: A framework for fast, scalable binarized neural network inference,","venue":null,"work_id":"88fb5f5a-a4d9-487f-95bf-4d445f56abec","year":2017},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.553757Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:fb90fd2e579d59837d8b7b8974bcb38de9832b71f8921ea36a3731ce7aeafe1a","observation_id":"14c23fe6-8865-4c64-8965-769223b690dd","resolution":{"observed_at":"2026-08-09T21:57:14.307678Z","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":"2026-08-09T21:57:14.275664Z","title":"Highly efficient 8-bit low precision inference of convolutional neural networks with IntelCaffe,","venue":null,"work_id":"c511cc5d-2393-4d1e-b91e-5a9af9b2205b","year":2018},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.558564Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:eabc1e1f5d33590af9a722c53a2e41f22f9304942eeea03218e70e9d599b971c","observation_id":"de65f252-ad0a-4136-86aa-1102d93c5c57","resolution":{"observed_at":"2026-08-09T21:57:14.281672Z","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":"2026-08-09T21:57:14.253564Z","title":"Trained quantization thresholds for accurate and efficient fixed-point inference of deep neural networks,","venue":null,"work_id":"906296d5-097e-43cc-aab9-0ce41fa84b4c","year":2019},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.565288Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:735e45ce6e706576c6cd6373437ad57430e779b720159264f3ab5147e9cec5aa","observation_id":"687e22c4-b3f1-4802-b0d9-6f33d152133f","resolution":{"observed_at":"2026-08-09T21:57:14.259889Z","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":"2026-08-09T21:57:14.231852Z","title":"XOR-Net: An efficient computation pipeline for binary neural network inference on edge devices,","venue":null,"work_id":"8175cda1-a897-48bd-8645-9d6e02c654dd","year":2020},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.571361Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:c74bfb8ee09fa2cf2b5ebf4a476e8899ba0dd82f27e8d200cf7693fc07c694ba","observation_id":"99315b25-d468-4e1a-a40b-5f0edb9decbb","resolution":{"observed_at":"2026-08-09T21:57:14.238399Z","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":{"arxiv_id":"1510.00149","last_updated":"2016-02-15T06:25:40Z","snapshot_observed_at":"2026-08-04T16:59:47.843960Z","submitted_at":"2015-10-01T09:03:44Z","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.00149","snapshot_observed_at":"2026-08-09T21:57:13.576311Z","title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.576311Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:aed10bbd6d7601153453e320efd748f2abb4d268ba41d62697fc3a235383146f","observation_id":"a1064a96-8d65-4d42-81ea-8885b161df39","resolution":{"observed_at":"2026-08-09T21:57:13.576311Z","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":"2026-08-09T21:57:13.581923Z","title":"Learning both weights and connections for efficient neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.581923Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:09de10d8d0e8320d90e03dee50259c7a5e06592d99ca73e5cb0cb1bb5b2027bb","observation_id":"7dd8a13b-5c57-4499-8604-169f6dcbefec","resolution":{"observed_at":"2026-08-09T21:57:13.581923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.08710","last_updated":"2017-03-10T17:57:56Z","snapshot_observed_at":"2026-08-14T21:42:03.106939Z","submitted_at":"2016-08-31T02:29:59Z","title":"Pruning Filters for Efficient ConvNets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.08710","snapshot_observed_at":"2026-08-09T21:57:13.590533Z","title":"Pruning filters for efficient ConvNets,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.590533Z"},"links":{"cited_paper":"/paper/1608.08710","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:cfa59d3d9307afc30560d906d862b8305f98c920d7c593349c43f94b1869b604","observation_id":"a120ec7c-2357-4abb-90ff-70f42c771708","resolution":{"observed_at":"2026-08-09T21:57:13.590533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.02782","last_updated":"2017-11-08T00:57:54Z","snapshot_observed_at":"2026-08-17T20:58:34.430517Z","submitted_at":"2017-11-08T00:57:54Z","title":"Block-Sparse Recurrent Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.02782","snapshot_observed_at":"2026-08-09T21:57:13.596161Z","title":"Block-sparse recurrent neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.596161Z"},"links":{"cited_paper":"/paper/1711.02782","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:3df194410a9d35d3b28a52822f936f5150d1da4463e0811f2e0ebd24b030f33f","observation_id":"2df30c03-476f-44bb-b276-aaeed1b384c7","resolution":{"observed_at":"2026-08-09T21:57:13.596161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.09224","last_updated":"2018-06-07T14:59:11Z","snapshot_observed_at":"2026-08-18T05:13:39.431122Z","submitted_at":"2017-11-25T09:34:12Z","title":"CondenseNet: An Efficient DenseNet using Learned Group Convolutions","version":2},"cited_work":{"arxiv_id":"1711.09224","doi":null,"metadata_source":"pith","pith_arxiv_id":"1711.09224","snapshot_observed_at":"2026-08-09T21:57:13.767027Z","title":"CondenseNet: An Efficient DenseNet using Learned Group Convolutions","venue":"cs.CV","work_id":"22f30c80-e925-4b44-96b4-dc6fb32463e9","year":2017},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.602093Z"},"links":{"cited_paper":"/paper/1711.09224","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:f3304426789d18707cddbe9f0ffb411decddf9fbfed843c295aa92959a743302","observation_id":"1d969325-7e88-42c8-86d4-f9246e1d54f1","resolution":{"observed_at":"2026-08-09T21:57:13.777345Z","resolver_source":"local_arxiv","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":{"arxiv_id":"2104.08378","last_updated":"2021-04-16T21:27:32Z","snapshot_observed_at":"2026-08-16T18:30:58.242028Z","submitted_at":"2021-04-16T21:27:32Z","title":"Accelerating Sparse Deep Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08378","snapshot_observed_at":"2026-08-09T21:57:13.609137Z","title":"Accelerating sparse deep neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.609137Z"},"links":{"cited_paper":"/paper/2104.08378","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:9a671d3813a8fe1bb7bbaa3c9940c2979be426492465cc1dc6d9b006f6fd59eb","observation_id":"9dbad7b4-98c2-4fac-9311-f7e3c29f698a","resolution":{"observed_at":"2026-08-09T21:57:13.609137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.21015","last_updated":"2025-02-07T23:27:07Z","snapshot_observed_at":"2026-08-16T13:47:20.570866Z","submitted_at":"2024-05-31T17:04:18Z","title":"The rising costs of training frontier AI models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.21015","snapshot_observed_at":"2026-08-09T21:57:13.615293Z","title":"The rising costs of training frontier AI models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.615293Z"},"links":{"cited_paper":"/paper/2405.21015","citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:c2f6388b07b099878a0bf28d508694670c3d8b9f9e3490080321e3b3eb5e951a","observation_id":"9cd8c37a-c20a-45e0-8843-11f7d050315b","resolution":{"observed_at":"2026-08-09T21:57:13.615293Z","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":"2026-08-09T21:57:14.193885Z","title":"XVDPU: A high performance cnn accelerator on versal platform powered by ai engine,","venue":null,"work_id":"f4bb6dea-64cc-4bd5-b0fd-9350fc757913","year":2022},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.619917Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:9be6d01b61e532371f0a1c4a2dce2cacbfd69c31d2222624b75f388cef1bfb2c","observation_id":"5a482670-dc83-43eb-aef6-1aa994da0be4","resolution":{"observed_at":"2026-08-09T21:57:14.201764Z","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":"2026-08-09T21:57:13.624492Z","title":"Nvidia hopper h100 gpu: Scaling performance,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.624492Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:8edb9119e00b236653c15e11729b0d121d73505c34cd9654bb4712ff61d56b25","observation_id":"4aecdd22-9567-420b-8a6e-122a24aa1f31","resolution":{"observed_at":"2026-08-09T21:57:13.624492Z","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":"2026-08-09T21:57:14.151738Z","title":"ThiNet: A filter level pruning method for deep neural network compression,","venue":null,"work_id":"09ff1f04-1194-48d6-b9b6-f81a59b2eb1e","year":2017},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.629059Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:5335ee69d81b1def59510ae824efd47d68365133a3bffd822253027ead644e14","observation_id":"ece1ef8c-5f37-427b-9d47-3c6f008c08c8","resolution":{"observed_at":"2026-08-09T21:57:14.157621Z","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":"2026-08-09T21:57:14.131205Z","title":"Reconciling sparse and structured pruning: A scientific study of block sparsity,","venue":null,"work_id":"25c8c40e-b307-48d0-9b71-0960137d21c3","year":2021},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.635432Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:f6507ff60f3cb69a6877572ee29ff6d9fcea1dec30d79ad80bb8cd64d31645b8","observation_id":"1f278d14-2c8c-4c99-a975-ac6d56c17081","resolution":{"observed_at":"2026-08-09T21:57:14.137763Z","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":"2026-08-09T21:57:14.111089Z","title":"Accelerating sparsity in the NVIDIA Ampere architecture,","venue":null,"work_id":"052e0031-b641-4fcd-ad5e-32dfea885fdb","year":2020},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.640667Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:00e303828fa212126f03970192752c268f72a6308b0b88f1c12b012e0964caf9","observation_id":"42f366af-534b-485c-94ef-71d46f90689a","resolution":{"observed_at":"2026-08-09T21:57:14.116127Z","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":"2026-08-09T21:57:14.093444Z","title":"Deep neural network compression by in-parallel pruning-quantization,","venue":null,"work_id":"ab22d9ba-5b96-4ba8-bb49-296702b74d67","year":2018},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.645881Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:bed7513be13c738f68a2fe860db2b78e7bee4ee2d85143991f32489e118d275d","observation_id":"818b2671-e640-4497-b805-684f2a898a02","resolution":{"observed_at":"2026-08-09T21:57:14.098944Z","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":"2026-08-09T21:57:14.073626Z","title":"LogNet: Energy-efficient neural networks using logarithmic computation,","venue":null,"work_id":"d42a2d6f-437f-46e1-b5f2-c62613f523b8","year":2017},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.651877Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:fbaf9d67b76f96e6541fbfb2c5c6ec25e580487c643806923ef2a9c1c5e5aab9","observation_id":"9dc40482-5b30-4376-963c-0cf20d17abd9","resolution":{"observed_at":"2026-08-09T21:57:14.078794Z","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":"2026-08-09T21:57:14.055082Z","title":"Deepshift: Towards multiplication-less neural networks,","venue":null,"work_id":"39ee4ee7-10eb-4f9f-b745-c5b022de3914","year":2021},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.657819Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:899f0f9c5ed567c26fd1d2b855bff0ded23afe82669c6597f50829eceab3111c","observation_id":"4e401a2a-cf60-4d8c-ab95-d695c7c4433a","resolution":{"observed_at":"2026-08-09T21:57:14.060859Z","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":"2026-08-09T21:57:14.032925Z","title":"DRQ: Dynamic region-based quantization for deep neural network acceleration,","venue":null,"work_id":"35203b42-8077-4101-85de-7f88ebb8ab7a","year":2020},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.663133Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:f5c789f4aa1e8faa54ebaf12677d06ef9f75601162d74beca63f897c1fdb27f7","observation_id":"7176dbd4-8196-4c83-b0d1-fce4752d798e","resolution":{"observed_at":"2026-08-09T21:57:14.043016Z","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":"2026-08-09T21:57:14.010251Z","title":"HAQ: Hardware-aware automated quantization with mixed precision,","venue":null,"work_id":"06b6f6a1-7b29-4a7e-8f89-e9677cfe0d85","year":2019},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.669100Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:200bb569a218fac1257c142821cbafb0d0772e2ad29095fd4c267c22f732e6f9","observation_id":"36e7b1bf-b71f-4bd4-a197-8b9b0c3c41e6","resolution":{"observed_at":"2026-08-09T21:57:14.016142Z","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":"2026-08-09T21:57:13.987195Z","title":"Chisel: constructing hardware in a scala embedded language,","venue":null,"work_id":"0c6c51bf-e493-4de4-b21f-36b5a8e5b75d","year":2012},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.675007Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:b5841e58ca455628f67fe2c3bb0e4a0dd5252cfe3986058c610f7281ad5ededa","observation_id":"480dfdbe-3357-470e-add0-7e9797dea23e","resolution":{"observed_at":"2026-08-09T21:57:13.996462Z","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":"2026-08-09T21:57:14.398858Z","title":"Available: https://openreview.net/forum?id=r1Ue8Hcxg","venue":null,"work_id":"eb58aaf4-1cdf-46d5-81aa-4171a9075372","year":null},"citing_paper":{"arxiv_id":"2501.18953","last_updated":"2025-05-17T07:51:43Z","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-09T21:57:13.527448Z"},"links":{"citing_paper":"/paper/2501.18953"},"observation_digest":"sha256:ab428a8998707a5a4df2a29bed24138a71db4acc2edbb0a8bc504b3f892e3194","observation_id":"d97f63a5-844a-4e8d-91f5-067b764936ab","resolution":{"observed_at":"2026-08-09T21:57:14.405932Z","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":"2501.18953","last_updated":"2025-05-17T07:51:43Z","latest_version":2,"primary_category":"cs.AR","snapshot_observed_at":"2026-08-15T21:58:55.715987Z","submitted_at":"2025-01-31T08:26:45Z","title":"StruM: Structured Mixed Precision for Efficient Deep Learning Hardware Codesign"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":20},"total_outbound_references":35},"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 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2501.18953."}