{"as_of":"2026-08-13T11:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:515e0cb24290d2ecee0fb8ac00903d5e111319e287099fdc22fe83dad88a825c","coverage":[{"denominator":75,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":75,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T07:54:50.503515Z","state":"measured"},{"denominator":75,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":75,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2511.00044/citation-record","integrity":"/paper/2511.00044/integrity","json":"/paper/2511.00044/citation-record.json","paper":"/paper/2511.00044"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T07:54:43.340449Z","title":"Deep learning.nature, 521(7553):436–444, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:43.340449Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:034eda84e48b776304d52bcc5ef5a3dd83e986970994b12f1c0141f8b08a9170","observation_id":"d1bccea3-4b58-4179-9eff-46347e291523","resolution":{"observed_at":"2026-08-04T07:54:43.340449Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-12T14:19:29.389332Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-04T07:54:43.450596Z","title":"Very deep convolutional networks for large-scale image recognition.arXiv preprint arXiv:1409.1556, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:43.450596Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:e6aa977091e60f2e15479e9e9a15cda57d6824830d193ce61bf88a67dda26386","observation_id":"4ee00410-b0d0-43a0-81bf-599f5a9b9a83","resolution":{"observed_at":"2026-08-04T07:54:43.450596Z","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":"2026-08-04T07:54:43.585623Z","title":"You only look once: Unified, real-time object detection","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:43.585623Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:2cb442cf9d9e3d0ccad34b6268ef31b27bb3e510e43dba50562dae8539629098","observation_id":"6ccb9a85-9dae-4f88-b8ef-bf9dccb3b9d7","resolution":{"observed_at":"2026-08-04T07:54:43.585623Z","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":"2026-08-04T07:54:43.754381Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:43.754381Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:0b17b615dd9a530573feb54ec9b2d933d7a2ca384b93887b6d1fdc7597175e69","observation_id":"be89b8f6-3711-4c4c-8256-60a0ae9334d1","resolution":{"observed_at":"2026-08-04T07:54:43.754381Z","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":"2026-08-04T07:54:43.893365Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:43.893365Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:047c7881ffd4d3ded58141c6cc9a4d10831f67fb5a626fae8fa335dc89d6d37a","observation_id":"ab4a6ca6-9984-4fff-aeb3-4e5ef89dd159","resolution":{"observed_at":"2026-08-04T07:54:43.893365Z","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":"2026-08-04T07:54:44.004652Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:44.004652Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:171dedea8cf30cca3f4d746e14befa2dd3c7878b962173a8e2ac9b169c10e313","observation_id":"07b29303-6cb5-4967-b892-bf5277f68885","resolution":{"observed_at":"2026-08-04T07:54:44.004652Z","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":"2026-08-04T07:54:44.162172Z","title":"Inference in artificial intelligence with deep optics and photonics.Nature, 588(7836):39–47, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:44.162172Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:dbfdc681c5af0d0e0392b2c31958dc7aba45ff6874dfa8980312265a6110f6c8","observation_id":"16357a0f-7aa1-4b49-97dc-d3dff635ffa0","resolution":{"observed_at":"2026-08-04T07:54:44.162172Z","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":"2026-08-04T07:54:44.338974Z","title":"Information processing using a single dynamical node as complex system","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:44.338974Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:780f1c52aba50504572b2dbbcfa73e1b6167f3b3cbb5bca73f229831a56a263b","observation_id":"54d76234-70b6-4e6e-9dbd-4b7755038272","resolution":{"observed_at":"2026-08-04T07:54:44.338974Z","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":"2026-08-04T07:54:44.485535Z","title":"Experimental demonstration of reservoir computing on a silicon photonics chip.Nature communications, 5(1):3541, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:44.485535Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:461277fc3ca8ed3e4e15e13a28101bd144d9e7c532e6b6b6812856689b846fd7","observation_id":"7d4a0d6e-195e-463f-9ac8-1b3e43029f35","resolution":{"observed_at":"2026-08-04T07:54:44.485535Z","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":"2026-08-04T07:54:44.619618Z","title":"Deep learning with coherent nanophotonic circuits.Nature photonics, 11(7):441– 446, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:44.619618Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:f41351a8847929dbe218e0704c662a88f086f513fe43b3383fc13394843186c0","observation_id":"34b3346b-e9fb-408d-bce2-f89965c05875","resolution":{"observed_at":"2026-08-04T07:54:44.619618Z","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":"2026-08-04T07:54:44.710248Z","title":"Neuromorphic photonic networks using silicon photonic weight banks.Scientific reports, 7(1):7430, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:44.710248Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:fc35ded5cd70936731d9b665ad739159ad61b3098c4d2f38d97960227d70696c","observation_id":"1fae683f-488e-4419-86c2-1be229d875f7","resolution":{"observed_at":"2026-08-04T07:54:44.710248Z","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":"2026-08-04T07:54:44.835843Z","title":"Reinforcement learning in a large-scale photonic recurrent neural network.Optica, 5(6):756–760, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:44.835843Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:36af5e08675a53d1bbb7106023c7dc58dc68d83e9a69508915be4db039de5614","observation_id":"3936268c-d197-41e2-8cd0-a3e72c8b6334","resolution":{"observed_at":"2026-08-04T07:54:44.835843Z","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":"2026-08-04T07:54:44.991755Z","title":"All-optical machine learning using diffractive deep neural networks.Science, 361(6406):1004–1008, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:44.991755Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:4d224c1fbabfbf144c18dd49bb741259df7258e29901237ff90034f824583df4","observation_id":"2080a32f-aae7-4339-9ddf-bccf4d58126c","resolution":{"observed_at":"2026-08-04T07:54:44.991755Z","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":"2026-08-04T07:54:45.140578Z","title":"Silicon photonics for artificial intelligence acceleration: Hotchips","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:45.140578Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:ca72b6eaa23aaa730452bf9f9478c6abea773757246887aaeebf4d2386645f84","observation_id":"73a5b925-2225-4211-b718-a6d66d97b43b","resolution":{"observed_at":"2026-08-04T07:54:45.140578Z","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":"2026-08-04T07:54:45.335135Z","title":"A crossbar array of magnetoresistive memory devices for in-memory computing","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:45.335135Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:ce5a2538d9b095f807cebb7e0116875818f4f902ba0772a85f8ac0e1b62f74fa","observation_id":"812d9110-1883-4fb6-a4ad-1b0de6834978","resolution":{"observed_at":"2026-08-04T07:54:45.335135Z","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":"2026-08-04T07:54:45.437929Z","title":"Wright, Tatsuhiro Onodera, Martin M","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:45.437929Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:2efdee16a16b569a38e3f47d26e912cbbbca2c902208fc14d8e34d5316069863","observation_id":"7a1bc86e-6ac4-4992-8636-09f5016def9d","resolution":{"observed_at":"2026-08-04T07:54:45.437929Z","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":"2026-08-04T07:54:45.558449Z","title":"Neuromorphic computing with nanoscale spintronic oscillators","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:45.558449Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:772beba7d24cc16e5f0be9d0e0fcf6d1319f2fe8548a95a40bcbc7705e740291","observation_id":"9c2b0f35-6fed-4f26-8030-9916d4ececf4","resolution":{"observed_at":"2026-08-04T07:54:45.558449Z","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":"2026-08-04T07:54:45.667844Z","title":"Training a multilayer dynamical spintronic network with stan- dard machine-learning tools to perform time-series classification.Physical Review Applied, 23(3):034051, mar 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:45.667844Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:395c0b710a3c09a9f470ce75a354d17d56c64a7289438cb3b0d74064f11fa990","observation_id":"e04df570-7f3c-4138-8aca-29273c5d635e","resolution":{"observed_at":"2026-08-04T07:54:45.667844Z","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":"2026-08-04T07:54:45.834831Z","title":"Vowel recognition with four coupled spin-torque nano- oscillators.Nature, 563(7730):230–234, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:45.834831Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:bcd7a1e579014fe24ab86a409859dc14d61db04b327960b4f30e3312935890e8","observation_id":"30017917-cf25-4a05-ba14-3010bf62028a","resolution":{"observed_at":"2026-08-04T07:54:45.834831Z","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":"2026-08-04T07:54:45.967529Z","title":"A pro- grammable chemical computer with memory and pattern recognition.Nature communications, 11(1):1442, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:45.967529Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:dada72514b52b4f866f23401bd25541a3457dcf7311a84ff41103f3c0ed6d286","observation_id":"0331e932-ba66-4318-a084-59c786e7571a","resolution":{"observed_at":"2026-08-04T07:54:45.967529Z","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":"2026-08-04T07:54:46.093445Z","title":"Phys- ical implementation of reservoir computing through electrochemical reaction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:46.093445Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:0382849d1a9594ca3eb7e26cbb72a6a584a6fb11c6db0700a1618a2b832a3129","observation_id":"a3744e0c-8fdb-4c10-b2e4-7b2bc72637a6","resolution":{"observed_at":"2026-08-04T07:54:46.093445Z","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":"2026-08-04T07:54:46.215336Z","title":"Imagenet classification with deep convolutional neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:46.215336Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:0b854269c309226f792447fbef99ca93316b6cca4660dffdca046818d01a775c","observation_id":"93cbd3ab-39de-4698-a897-c8c48d25204f","resolution":{"observed_at":"2026-08-04T07:54:46.215336Z","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":"2026-08-04T07:54:46.363244Z","title":"Improv- ing language understanding by generative pre-training","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:46.363244Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:6d67d636025fb8b92e4a5c1b41fc61da1154f714581e9b04a409da51a0b29d20","observation_id":"5d08240a-0b0b-4c4d-a12c-40351b856031","resolution":{"observed_at":"2026-08-04T07:54:46.363244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.08053","last_updated":"2020-03-13T23:45:18Z","snapshot_observed_at":"2026-08-12T10:50:46.357243Z","submitted_at":"2019-09-17T19:42:54Z","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.08053","snapshot_observed_at":"2026-08-04T07:54:46.532017Z","title":"Megatron-lm: Training multi-billion parameter 17 language models using model parallelism.arXiv preprint arXiv:1909.08053, 2019","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:46.532017Z"},"links":{"cited_paper":"/paper/1909.08053","citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:38b140a846e5aabcbd19479b19d7a5721f221d9060f2e5f7a8e2e13962f2af66","observation_id":"ed87a060-a4e6-4ca0-aa74-c402f93cc3e6","resolution":{"observed_at":"2026-08-04T07:54:46.532017Z","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":"2026-08-04T07:54:46.644610Z","title":"Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:46.644610Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:24c64ae7862cb5c8f70431bc62ab2f40d2ce308d0b3e364dff8c03b0a3f3afb7","observation_id":"8dd39e45-3a98-4ba9-9fd6-e31447d08b90","resolution":{"observed_at":"2026-08-04T07:54:46.644610Z","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":"2026-08-04T07:54:46.757884Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:46.757884Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:d5a479fe565eec77b292384738758a4894a6360de0a0c490b199c0e71f198e27","observation_id":"f8cedfd1-ccde-4ebd-ac37-de539e4f6136","resolution":{"observed_at":"2026-08-04T07:54:46.757884Z","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":"2026-08-04T07:54:46.943125Z","title":"Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:46.943125Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:1ca2f0942f0604559f36b04c56ebb168519b394c0edeef677ceb221d10dc6f79","observation_id":"d3fc233f-12a8-4cda-8f14-c32160e321c9","resolution":{"observed_at":"2026-08-04T07:54:46.943125Z","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":"2026-08-04T07:54:47.107275Z","title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.Journal of Machine Learning Research, 23(120):1–39, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:47.107275Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:d6126499e806ad4e9a04c2e76f1239b4d5a6dd20d8c6b2529d65938cc16f3069","observation_id":"3ad84620-e500-4b95-89fa-6fb943fa104a","resolution":{"observed_at":"2026-08-04T07:54:47.107275Z","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":"2026-08-04T07:54:47.273775Z","title":"Palm: Scaling language modeling with pathways.Journal of Machine Learning Research, 24(240):1–113, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:47.273775Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:be87eb57ef9395dc00690c70da76c8e4d37767dcef596cc1b6d4d0704585ac5f","observation_id":"f46ec540-c160-47e9-87b2-4096730f75cc","resolution":{"observed_at":"2026-08-04T07:54:47.273775Z","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":"2026-08-04T07:54:47.414422Z","title":"All-optical spiking neurosynaptic networks with self- learning capabilities.Nature, 569(7755):208–214, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:47.414422Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:79fd4c14099662b9fd0646c53c600e8eef9eafc59c9bf7da2496928289b6564c","observation_id":"3e0b6ec1-8f81-4dca-a51a-cd7895494d0f","resolution":{"observed_at":"2026-08-04T07:54:47.414422Z","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":"2026-08-04T07:54:47.490635Z","title":"Fully hardware-implemented memristor convolutional neural network.Nature, 577(7792):641–646, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:47.490635Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:8ba299a36bbde68d2367afcfb3cffbab48536a6259f6c949585e3176feb51dc9","observation_id":"b5ad96a7-7239-487d-8a3a-a6839f7619e9","resolution":{"observed_at":"2026-08-04T07:54:47.490635Z","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":"2026-08-04T07:54:45.245145Z","title":"IEEE Computer Society, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:45.245145Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:2f8db9927f5e13afc3df13a10039aa78f7999bc36d99ee399c71b1c20cf370c0","observation_id":"98e0c7ee-2c0b-49c9-babb-1181e0a5abc0","resolution":{"observed_at":"2026-08-04T07:54:45.245145Z","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":"2026-08-04T07:54:47.569102Z","title":"Novel nondelay-based reservoir computing with a single micromechanical nonlinear resonator for high-efficiency information processing.Microsystems & Nanoengineering, 7(1):83, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:47.569102Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:981f8a139293b7c7d4e88156da2b47dbaa5287c0088dead3161fc07a988564c8","observation_id":"9b158157-7fab-45cc-8fa8-57a6bb56b899","resolution":{"observed_at":"2026-08-04T07:54:47.569102Z","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":"2026-08-04T07:54:47.663717Z","title":"Collective and synchronous dynamics of photonic spiking neurons.Nature communications, 12(1):2325, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:47.663717Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:424cac686928b58063e89eef6b395c1b69cb627863b873b8d17f5132bbd9bc4c","observation_id":"e1696d42-7456-4804-9a8a-22acde454e0a","resolution":{"observed_at":"2026-08-04T07:54:47.663717Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-07-06T08:52:12.656082Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-04T07:54:47.735789Z","title":"Scaling laws for neural language models.arXiv preprint arXiv:2001.08361, 2020","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:47.735789Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:b76c496ae060692f4a3ca383f629a14529fbfa54a0305ae6bba57df55f70bea8","observation_id":"1750c9c0-70b4-4368-bd58-5f7fe3e79b56","resolution":{"observed_at":"2026-08-04T07:54:47.735789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.02852","last_updated":"2022-07-05T20:55:38Z","snapshot_observed_at":"2026-08-12T22:04:04.773760Z","submitted_at":"2022-07-05T20:55:38Z","title":"Machine Learning Model Sizes and the Parameter Gap","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.02852","snapshot_observed_at":"2026-08-04T07:54:47.790951Z","title":"Machine learning model sizes and the parameter gap.arXiv preprint arXiv:2207.02852, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:47.790951Z"},"links":{"cited_paper":"/paper/2207.02852","citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:ecf4d8d435a5b8836d4896aadb57022b330c9f3053bd5aa9030f0e31dc349256","observation_id":"8b3907bc-3c5a-47a9-a401-931da6594fc4","resolution":{"observed_at":"2026-08-04T07:54:47.790951Z","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":"2026-08-04T07:54:47.855274Z","title":"Diffractive optical computing in free space.Nature Communications, 15(1):1525, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:47.855274Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:ac9f0ee768ea0653682f7b3d04309b04cf0a90fa32b685ecd17635754cc20fc6","observation_id":"66b012b3-14f5-4e28-ac38-7b7052b2da49","resolution":{"observed_at":"2026-08-04T07:54:47.855274Z","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":"2026-08-04T07:54:47.908087Z","title":"Scaling up silicon photonic-based accelerators: Challenges and opportunities.APL Photonics, 7(2), 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:47.908087Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:7cb363ab13841bf2322fef635327cdc44d2982e5f73c0a8b55b359810c4a69f2","observation_id":"21a5886e-181c-41d8-90a6-ea6e74cf1324","resolution":{"observed_at":"2026-08-04T07:54:47.908087Z","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":"2026-08-04T07:54:47.975574Z","title":"On the effect of the thermal cross-talk in a photonic feed-forward neural network based on silicon microresonators.Frontiers in Physics, 10:1093191, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:47.975574Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:0d537cca8d7637dfd7b46e4eb11ed72bb9665cc95daa2db5bc21c16cba7de42e","observation_id":"28805f0f-e10a-42b1-90e5-713e9ebe0e92","resolution":{"observed_at":"2026-08-04T07:54:47.975574Z","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":"2026-08-04T07:54:48.032175Z","title":"Neuromorphic spintronics.Nature electronics, 3(7):360–370, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.032175Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:790bf9275f26edd2c9b559e3a860689798cad4d6f7386cbb0bbcac42576bbf5b","observation_id":"7d242e64-e41f-47ab-b6d1-2a1cdf9afe2c","resolution":{"observed_at":"2026-08-04T07:54:48.032175Z","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":"2026-08-04T07:54:48.100826Z","title":"The physics of optical computing.Nature Reviews Physics, 5(12):717–734, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.100826Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:29e9b30a356bd89c8c77f1606d8c46630e5f2ef8b903c98d81febd58dccd0d50","observation_id":"c643d013-ed2e-4cc8-9cc0-3ba3f8ee57c7","resolution":{"observed_at":"2026-08-04T07:54:48.100826Z","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":"2026-08-04T07:54:48.148194Z","title":"Handwritten digit recognition with a back-propagation network.Advances in neural information processing systems, 2, 1989","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.148194Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:d4e58b2bab5c72f29457468c02296b2a287b4075b9c7da3cf27b76a119f393c1","observation_id":"0adb5666-87f8-4cd7-a84d-fefe8d55fccf","resolution":{"observed_at":"2026-08-04T07:54:48.148194Z","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":"2026-08-04T07:54:48.242847Z","title":"Neural networks and principal component analysis: Learning from examples without local minima.Neural Networks, 2(1):53–58, 1989","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.242847Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:90d70575b10c9c1d3e60c269d71e073808d0de79186b2c45a5d3b8146da8b653","observation_id":"a139d5c3-cedd-4c80-b177-de1191a78811","resolution":{"observed_at":"2026-08-04T07:54:48.242847Z","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":"2026-08-04T07:54:48.354011Z","title":"Balanced and deterministic weight-sharing helps network performance","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.354011Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:ecbe320c10a2d0adce6cfeddc5dc3e2c0fbb06c38e403768848fbf9137e96cb6","observation_id":"82e63099-2e47-4669-b277-573c3e80578d","resolution":{"observed_at":"2026-08-04T07:54:48.354011Z","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":"2026-08-04T07:54:48.412773Z","title":"Quantum computing in the nisq era and beyond.Quantum, 2:79, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.412773Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:5e4d54e36aadcd6a2ccbfb4e2db9936d17d174301010ad0e03a580db13b318a1","observation_id":"523e69af-ba00-4374-9d0e-c3ffa20032e7","resolution":{"observed_at":"2026-08-04T07:54:48.412773Z","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":"2026-08-04T07:54:48.459618Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.459618Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:be994bf39e05656ccaff03c9c4168a999841be7aa926efa226ef31e11f3f7856","observation_id":"0d18f984-7f50-458d-9096-0d96c14f7adc","resolution":{"observed_at":"2026-08-04T07:54:48.459618Z","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":"2026-08-04T07:54:48.523497Z","title":"Behavioral classification of sequential neural activity using time varying recurrent neural networks.IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.523497Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:5965418ff3fe553c70e60261c054e005a94b826c4838e7330410cd18a7cd1814","observation_id":"c5ea6450-9c44-4677-a44c-28b17f309be2","resolution":{"observed_at":"2026-08-04T07:54:48.523497Z","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":"2026-08-04T07:54:48.599765Z","title":"Deep neural networks using a single neuron: folded-in-time architecture using feedback-modulated delay loops.Nature communications, 12(1):5164, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.599765Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:e9945fa855ae27926c186b30fc42439775953c22d930ae4b98b4e8f317f57026","observation_id":"93563621-fee6-40c6-a771-286471236552","resolution":{"observed_at":"2026-08-04T07:54:48.599765Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.09106","last_updated":"2016-12-01T10:08:15Z","snapshot_observed_at":"2026-08-13T11:42:24.563958Z","submitted_at":"2016-09-27T05:57:00Z","title":"HyperNetworks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.09106","snapshot_observed_at":"2026-08-04T07:54:48.686059Z","title":"Hypernetworks.arXiv preprint arXiv:1609.09106, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.686059Z"},"links":{"cited_paper":"/paper/1609.09106","citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:92a13e1a2af6a765cf03dd3d7ab7e5df9674ceac55b0f447686686b7ca44adaa","observation_id":"67d021fc-f8af-4ea6-8def-51b83959b43a","resolution":{"observed_at":"2026-08-04T07:54:48.686059Z","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":"2026-08-04T07:54:48.758293Z","title":"Wave physics as an analog recurrent neural network.Science advances, 5(12):eaay6946, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.758293Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:27cb84e57f350a67c491af0faf4aa76c39ff284c0544f031e710399ea60a381f","observation_id":"863a4ff1-f1f6-4aa4-af49-b31fce23afa3","resolution":{"observed_at":"2026-08-04T07:54:48.758293Z","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":"2026-08-04T07:54:48.845719Z","title":"Dynamic filter networks.Advances in neural information processing systems, 29, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.845719Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:e66b5bcb983b84189e0b95f0e1901cdcc3bd9106739b89e24ecd8a1b421744c3","observation_id":"2670fdd9-12a1-47f3-93bb-2c343acaadc7","resolution":{"observed_at":"2026-08-04T07:54:48.845719Z","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":"2026-08-04T07:54:48.916807Z","title":"Using fast weights to attend to the recent past.Advances in neural information processing systems, 29, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.916807Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:ad2ff12abc9d71dbad586b86caeb7f3bea9e8fb61e4d3932e3cfa76eb2f3a460","observation_id":"8e54053a-ef3f-4eea-8e83-03fc8f1d4a4c","resolution":{"observed_at":"2026-08-04T07:54:48.916807Z","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":"2026-08-04T07:54:48.963908Z","title":"Feedback control for microring weight banks.Optics express, 26(20):26422–26443, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:48.963908Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:e42668e4dbf562fe36d1213b33ab0ddc406cd07929081f47d52d049c1a662d31","observation_id":"2bfcaab6-de47-4bc0-bdc2-5369a93754ab","resolution":{"observed_at":"2026-08-04T07:54:48.963908Z","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":"2026-08-04T07:54:49.065204Z","title":"Large-scale photonic processors 19 and their applications.npj Nanophotonics, 2(1):32, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.065204Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:d83df1405a53dca1468aece81e5baf3d0e69f28fcafc89452adc664cfa55bf87","observation_id":"dba48d0a-fd2f-4fd7-9d86-bca6f86ca563","resolution":{"observed_at":"2026-08-04T07:54:49.065204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1308.0850","last_updated":"2014-06-05T16:04:02Z","snapshot_observed_at":"2026-08-05T10:16:44.137827Z","submitted_at":"2013-08-04T21:04:36Z","title":"Generating Sequences With Recurrent Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1308.0850","snapshot_observed_at":"2026-08-04T07:54:49.159483Z","title":"Generating sequences with recurrent neural networks.arXiv preprint arXiv:1308.0850, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.159483Z"},"links":{"cited_paper":"/paper/1308.0850","citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:8c0f22636d6f29fd1ab50b82b09c63093e3abffb350ae5d3e91ef518fc10d1b0","observation_id":"bb5f07ab-d82d-41c3-a65e-0c79c97aeff9","resolution":{"observed_at":"2026-08-04T07:54:49.159483Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06570","last_updated":"2017-10-18T03:05:47Z","snapshot_observed_at":"2026-08-10T09:23:42.946138Z","submitted_at":"2017-10-18T03:05:47Z","title":"A Correspondence Between Random Neural Networks and Statistical Field Theory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06570","snapshot_observed_at":"2026-08-04T07:54:49.270126Z","title":"A corre- spondence between random neural networks and statistical field theory.arXiv preprint arXiv:1710.06570, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.270126Z"},"links":{"cited_paper":"/paper/1710.06570","citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:16330a5f9eb8355cc502a2ef84afdbedfe62865bf27556f861e8f53030d2ca36","observation_id":"1d4f5acf-3306-4faa-a548-fc358ae759d0","resolution":{"observed_at":"2026-08-04T07:54:49.270126Z","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":"2026-08-04T07:54:49.298459Z","title":"Digital light processing and mems: timely convergence for a bright future.Proceedings of SPIE, 2639:2–14, 1997","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.298459Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:9bebf5cea7566a048bca7d65e1ef4adf5736a22b91c221c0c957f2341972e51d","observation_id":"8c055431-4df9-4ac1-92bc-cdc86f64fc04","resolution":{"observed_at":"2026-08-04T07:54:49.298459Z","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":"2026-08-04T07:54:49.347874Z","title":"Femotosecond switching in a dual-core-fiber nonlinear coupler.Optics Letters, 13(10):904–906, 1988","venue":null,"work_id":null,"year":1988},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.347874Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:bd97d9f6d28cb2dfa0ad1759bbbf02ace2107dd9a66dfabe09d8000f39e88176","observation_id":"f4e1cb41-7583-4270-8211-e4c7255faf14","resolution":{"observed_at":"2026-08-04T07:54:49.347874Z","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":"2026-08-04T07:54:49.418216Z","title":"Silicon microring resonators.Laser & photonics reviews, 6(1):47–73, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.418216Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:c893c2bb659b81d52a03d5631a8b6f4f864dddf7020b9c3d72a5e5acb837fa32","observation_id":"e673a9e5-9750-41e6-844e-4413fef81d92","resolution":{"observed_at":"2026-08-04T07:54:49.418216Z","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":"2026-08-04T07:54:49.503763Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.503763Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:3016369b4c4c127fe7128a8c90441063d6b4dc0862d6986a1aab6f610237d366","observation_id":"6d64b75f-40cb-4fd1-b035-063179bffff5","resolution":{"observed_at":"2026-08-04T07:54:49.503763Z","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":"2026-08-04T07:54:49.565621Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.565621Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:4dcbfb35398e7a9175f1db6bd935c2b6694e5547c052482196155e5090ad4960","observation_id":"038dea4c-2bc3-463f-88d3-822795b2b3df","resolution":{"observed_at":"2026-08-04T07:54:49.565621Z","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":"2026-08-04T07:54:49.622674Z","title":"A theoretically grounded application of dropout in recurrent neural networks.Advances in neural information processing systems, 29, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.622674Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:5f4381b74cc4851ff6cb134826ea566e7a10cbebc19dea2afb2fdab384692778","observation_id":"df1d967a-d024-4115-82f3-6962b4fc27d4","resolution":{"observed_at":"2026-08-04T07:54:49.622674Z","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":"2026-08-04T07:54:49.695307Z","title":"Shakespeare’s plays, sonnets and poems from the fol- ger shakespeare","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.695307Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:6c671988c929c5d781097f0ab2034653d257400b050d13f5370465a39a9fa9f3","observation_id":"ebef0d5a-614d-4e73-a87e-f2996e60e711","resolution":{"observed_at":"2026-08-04T07:54:49.695307Z","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":"2026-08-04T07:54:49.771392Z","title":"On the difficulty of training recurrent neural networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.771392Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:8e047979768538293c54adf8f779f8bf965abddf09f0883abfd55400f25d395b","observation_id":"94ed04f4-1758-4ea7-99e0-9f3e88fe915e","resolution":{"observed_at":"2026-08-04T07:54:49.771392Z","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":"2026-08-04T07:54:49.838910Z","title":"Learning long-term depen- dencies with gradient descent is difficult.IEEE transactions on neural networks, 5(2):157–166, 1994","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.838910Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:f5c9098de6cbd91d24f794f7f15b445761ff889431a8b0a228d2200577c93b0f","observation_id":"9c5d189b-5f0a-4862-9df5-0851b251bf93","resolution":{"observed_at":"2026-08-04T07:54:49.838910Z","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":"2026-08-04T07:54:49.907538Z","title":"van der Wiel","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.907538Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:8a783e51d3d65dfc8c7fc6cdcea8407816bd44c59b7b6f3503046fd17ba0b12f","observation_id":"995933fb-b282-4a8e-8dd2-0ce1eecdd18f","resolution":{"observed_at":"2026-08-04T07:54:49.907538Z","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":"2026-08-04T07:54:49.975442Z","title":"Infor- mation processing capacity of dynamical systems.Scientific reports, 2(1):514, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:49.975442Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:f85895d05b2a807c8786d87855f1ec6227514b9b5a3e8c8bb018bd8c6d831e26","observation_id":"de956ec2-805d-4d6d-93a5-923d0ddc7e03","resolution":{"observed_at":"2026-08-04T07:54:49.975442Z","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":"2026-08-04T07:54:50.030045Z","title":"On the number of linear regions of deep neural networks","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:50.030045Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:46a34f2a8493e50f81045146f13dc932bf5817a44f716b27061415cd3a684601","observation_id":"e44f3f1a-fffc-4fc9-a383-554860cd3fa8","resolution":{"observed_at":"2026-08-04T07:54:50.030045Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-04T07:54:50.116241Z","title":"Adam: A method for stochastic optimization.arXiv preprint 20 arXiv:1412.6980, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:50.116241Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:b23ab9dd05c794f69d33036e4164c043ecd1537578bfd72f6ec1a04fc94a2531","observation_id":"259a67c0-3023-4a5c-8cdf-77ad369ded81","resolution":{"observed_at":"2026-08-04T07:54:50.116241Z","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":"2026-08-04T07:54:50.178371Z","title":"Physical deep learning with biologically inspired training method: gradient-free approach for physical hardware.Nature Communications, 13(1):7847, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:50.178371Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:b49d6ad454e9e51167704d277beaebd62c0db777b6692c1cdcc782dee678ae87","observation_id":"b83d81b4-29cb-43a0-9816-924c0df739e7","resolution":{"observed_at":"2026-08-04T07:54:50.178371Z","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":"2026-08-04T07:54:50.232046Z","title":"Blending optimal control and biologically plausible learning for noise-robust physical neural networks.Phys","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:50.232046Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:d4ba32c7fc5197c5484d852829a8b870d1c1134a60284ffa28ffe42dc84ceba0","observation_id":"039ab522-2445-4651-b986-efe39f9a8114","resolution":{"observed_at":"2026-08-04T07:54:50.232046Z","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":"2026-08-04T07:54:50.310270Z","title":null,"venue":null,"work_id":null,"year":1964},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:50.310270Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:4fc6acf02d8e0ed025b5e60c36bf8352d73a8a51d988fc00061238df2c274391","observation_id":"72d412b6-3e43-4e30-945f-8cd20ea2bb4b","resolution":{"observed_at":"2026-08-04T07:54:50.310270Z","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":"2026-08-04T07:54:50.368922Z","title":"Lecture 6e: Rmsprop — divide the gradient by a running average of its recent magnitude","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:50.368922Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:50e4521ddbc92e466183d63b64538680201923adfdef7a739def4b0c82eecedf","observation_id":"7e24284f-a174-41cb-a08a-c0774d3dd77e","resolution":{"observed_at":"2026-08-04T07:54:50.368922Z","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":"2026-08-04T07:54:50.450142Z","title":"Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278– 2324, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:50.450142Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:694d613ce10981b4431be6834c27e5c239ba04976b932c690ff43d91c9cdda45","observation_id":"23dea27e-fe45-4af6-a79c-01492a401dcf","resolution":{"observed_at":"2026-08-04T07:54:50.450142Z","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":"2026-08-04T07:54:50.503515Z","title":"Input (Hidden, Output)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-04T07:54:50.503515Z"},"links":{"citing_paper":"/paper/2511.00044"},"observation_digest":"sha256:76b3491785763966fa244863c2ec822de51ef2bac2f5a0fb8a6af717a479cc50","observation_id":"f15e2f59-f013-4ed4-b47f-41055cc1cb5d","resolution":{"observed_at":"2026-08-04T07:54:50.503515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2511.00044","last_updated":"2026-06-10T09:24:32Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T13:51:55.677141Z","submitted_at":"2025-10-28T07:25:41Z","title":"Time-multiplexed layer reuse for physical neural networks"},"reference_resolution":{"displayed":75,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":75,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":75},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 75 of 75 outbound references and 0 inbound Pith citation observations for arXiv:2511.00044."}