{"as_of":"2026-08-18T12:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f59324e500f69a3a79ed693a9da1c32ecf8391f0b83723f2acfbc9dc11fc66af","coverage":[{"denominator":109,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T00:46:06.117939Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.11585/citation-record","integrity":"/paper/2608.11585/integrity","json":"/paper/2608.11585/citation-record.json","paper":"/paper/2608.11585"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:46:05.668781Z","title":"Toward a formal theory for computing machines made out of whatever physics offers.Nature Communications, 14(1):4911, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.668781Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:f44293d466e67b937350943c7a1acb17181b4f68e53fddffaba973c5c2fa14ae","observation_id":"9e1388fa-67d4-4edc-a5f5-8c9cb1c2342f","resolution":{"observed_at":"2026-08-16T00:46:05.668781Z","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":"2026-08-16T00:46:05.674358Z","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":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.674358Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:36f508291f5504762c5c8b78d2ac4be3c9a3573520b25ee8345a5b85913a38b6","observation_id":"390890aa-ece4-4859-b520-6346e33c4789","resolution":{"observed_at":"2026-08-16T00:46:05.674358Z","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":"2026-08-16T00:46:05.679450Z","title":"Analogue computing with metamaterials.Nature Reviews Materials, 6(3):207–225, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.679450Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:a836de52d2357d43009c06ff74fe242a90c8ccaa8ccfc6304c6685f816d08bf6","observation_id":"76a352bc-44f6-4f8c-9703-0c9b8a940f4b","resolution":{"observed_at":"2026-08-16T00:46:05.679450Z","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":"2026-08-16T00:46:05.684462Z","title":"In- sensor passive speech classification with phononic metamaterials.Advanced Functional Materials, 34(17):2311877, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.684462Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:2fb2ddafe5e10704d5bf835ac70d1c42cbd739244f01f3e154e2fec6efe7ecd8","observation_id":"d42fc0af-98a4-4243-8c68-a37e65c213c2","resolution":{"observed_at":"2026-08-16T00:46:05.684462Z","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":"2026-08-16T00:46:05.689360Z","title":"Demonstration of decentralized physics-driven learning.Physical Review Applied, 18(1):014040, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.689360Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:f4c572cd0ed54bc50a1a93d2684c12685d61884c14210356f2f1c544a3852b26","observation_id":"53d7cb4f-ea7c-4074-991a-40d292e37af4","resolution":{"observed_at":"2026-08-16T00:46:05.689360Z","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":"2026-08-16T00:46:05.694295Z","title":"Memory devices and applications for in-memory computing.Nature Nanotechnology, 15(7):529–544, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.694295Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:ac43bf84e8ee8bccb487f3451f6c1154c7fc9b36ff2ae3ea37f6d369982b18f3","observation_id":"ae9680dc-0321-415c-9b73-fed30cc69f37","resolution":{"observed_at":"2026-08-16T00:46:05.694295Z","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":"2026-08-16T00:46:05.699902Z","title":"Physics for neuromorphic computing.Nature Reviews Physics, 2(9):499–510, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.699902Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:8c6303ee41649d7a2b91221a8ff8436c2d4987c236a432b7d7d100ff16e38309","observation_id":"30a9bd48-367d-4d05-875c-fe0cc682f8c6","resolution":{"observed_at":"2026-08-16T00:46:05.699902Z","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":"2026-08-16T00:46:05.704410Z","title":"Photonics for artificial intelligence and neuro- morphic computing.Nature Photonics, 15(2):102–114, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.704410Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:414eb34106b406a817384edbdb5aa37143484fc5ec313ebb879a7f43869174f3","observation_id":"f8723c8b-ad74-4e56-bf23-bd0303be1a5a","resolution":{"observed_at":"2026-08-16T00:46:05.704410Z","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":"2026-08-16T00:46:05.709025Z","title":"Scalable optical learning operator.Nature Computational Science, 1(8):542–549, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.709025Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:664025f0825894a5a25801b481be6109156e68d057aeb0db9b2747d845c1b4f1","observation_id":"81ac24da-a5e1-453e-9a86-7999d1f34a84","resolution":{"observed_at":"2026-08-16T00:46:05.709025Z","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":"2026-08-16T00:46:05.713783Z","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":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.713783Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:506909a28031af194c494566b2564792c4120b1829a583002361ce08cc2c6db2","observation_id":"01d23a7a-dab5-4eab-beb5-32bd07c940a2","resolution":{"observed_at":"2026-08-16T00:46:05.713783Z","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":"2026-08-16T00:46:05.718359Z","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":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.718359Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:ecb94346c5426803fa024602ecd01450cf0ea472a0bf1e8d3a9e9ff5048b2fbb","observation_id":"20ed9a9b-c7e5-425c-bbb9-a26f305baa71","resolution":{"observed_at":"2026-08-16T00:46:05.718359Z","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":"2026-08-16T00:46:05.722972Z","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":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.722972Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:21bdd7e44f9b94e2b5418e62dc98e4a9fdae1a8338f59698e66171783d0b310b","observation_id":"39d062a5-2d47-4776-a7d5-2619d4a2efed","resolution":{"observed_at":"2026-08-16T00:46:05.722972Z","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":"2026-08-16T00:46:05.727183Z","title":"Arbitrary control over multimode wave propagation for machine learning.Nature Physics, 22:164–171, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.727183Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:d55c0a653819cdfb0b3492b1fe8b33c442d3db1c64e0e56684ec8158b7f7cb7c","observation_id":"4f097ac2-8f69-4f96-b5f0-f6ac8c32ea45","resolution":{"observed_at":"2026-08-16T00:46:05.727183Z","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":"2026-08-16T00:46:05.731258Z","title":"Programmable on-chip nonlinear photonics.Nature, 649(8096):330–337, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.731258Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:fba4e5d4d664f469733d63bb2ede6abf1e377cc1f6df03382aea333148ea21e4","observation_id":"0bbb5d47-3c1a-4687-9ecc-970768ce654e","resolution":{"observed_at":"2026-08-16T00:46:05.731258Z","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":"2026-08-16T00:46:05.735169Z","title":"Recent advances in physical reservoir computing: A review.Neural Networks, 115:100–123, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.735169Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:b6b1f84b6d0f171b0a8403b27a9787e9dc0099e34f45be3e04ae35d559becfaf","observation_id":"60280dce-5d22-4071-a4f9-5d7087ec8e31","resolution":{"observed_at":"2026-08-16T00:46:05.735169Z","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":"2026-08-16T00:46:05.739200Z","title":"Training of physical neural networks.Nature, 645(8079):53–61, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.739200Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:a272fffd155f9b053624d53e3c6d66567356d7fc407dacd15a2bab93008ed420","observation_id":"439dbfdd-4382-4765-8723-7a84c3149a8a","resolution":{"observed_at":"2026-08-16T00:46:05.739200Z","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":"2026-08-16T00:46:05.743289Z","title":"Inverse-designed low-index-contrast structures on a silicon photonics platform for vector– matrix multiplication.Nature Photonics, 18(5):501–508, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.743289Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:a6e1a75b4ccf60403de6ad0d86c7d4327ec402422ffdd00fd0a24569688c5531","observation_id":"ce7500e7-f875-4566-bf02-6b98bef6bf76","resolution":{"observed_at":"2026-08-16T00:46:05.743289Z","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":"2026-08-16T00:46:05.747818Z","title":"Deep physical neural networks trained with backpropagation.Nature, 601(7894):549–555, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.747818Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:25bc60b9fa6858dce28e528a018e2c3d1b671b8a2cb926b652a81d2bcd198397","observation_id":"5763e534-48e2-44e1-8541-dc7c6930c79c","resolution":{"observed_at":"2026-08-16T00:46:05.747818Z","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":"2026-08-16T00:46:05.752125Z","title":"Optical diffusion models for image generation.Advances in Neural Information Processing Systems, 37:59150–59173, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.752125Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:4921ab5d99d47d9c4f1a217d238e139d414e8e3172be81daabbe78a37812bb99","observation_id":"05f81b04-ffc5-418e-a426-4e58ff843b74","resolution":{"observed_at":"2026-08-16T00:46:05.752125Z","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":"2026-08-16T00:46:05.756170Z","title":"Trainable hardware for dynamical computing using error backpropagation through physical media","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.756170Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:aadcbb5f6c089abca7e438e8e13b114abb76c5d4a7d37bad997429b85cd429fa","observation_id":"50a66671-2cca-4823-baa0-fdd1c9d4b0a6","resolution":{"observed_at":"2026-08-16T00:46:05.756170Z","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":"2026-08-16T00:46:05.760173Z","title":"In situ optical backpropagation training of diffractive optical neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.760173Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:9ae25cf183d86bfa889427a3df24253abb07a1392ff7f0d7778e517a5600aa16","observation_id":"692a3931-d99e-4ebf-adaa-f2f0f9edb98b","resolution":{"observed_at":"2026-08-16T00:46:05.760173Z","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":"2026-08-16T00:46:05.764139Z","title":"Threading light through dynamic complex media.Nature Photonics, 19(4):434–440, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.764139Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:b1f489e3528e926d661b39c081092191d371997fcd940af02b6fab75644043cf","observation_id":"c188d944-052f-4061-b6a1-25d5f118be7a","resolution":{"observed_at":"2026-08-16T00:46:05.764139Z","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":"2026-08-16T00:46:05.768746Z","title":"Experimentally realized in situ backpropagation for deep learning in photonic neural networks.Science, 380(6643):398–404, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.768746Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:1997ffeb017c943b1590fa2452f91db8ca74c6b0de68c4829066fcb135988739","observation_id":"4e9fd759-bc2c-46bd-944e-59acdf15e33f","resolution":{"observed_at":"2026-08-16T00:46:05.768746Z","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":"2026-08-16T00:46:05.773332Z","title":"Training all-mechanical neural networks for task learning through in situ backpropagation.Nature Communications, 15(1):10528, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.773332Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:eff3e9f048e8fe35574da5e7ca7d220dfa55b42bb63bee05eddfe8fdaef9e822","observation_id":"505b96cf-33c7-4f70-b02a-973eaa9cc50b","resolution":{"observed_at":"2026-08-16T00:46:05.773332Z","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":"2602.03546","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:46:06.812418Z","title":"How to train your resistive net- work: Generalized equilibrium propagation and analytical learning.arXiv preprint arXiv:2602.03546, 2026","venue":null,"work_id":"d93ed329-deb2-4123-b268-ce74a408145b","year":2026},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.777764Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:a7bf98a5298470bb78513987350ebbf194ada7e136a3474feff66f52ef5985cd","observation_id":"ee0f850b-7327-4018-8b4f-b0835e093bb7","resolution":{"observed_at":"2026-08-16T00:46:06.820789Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:46:05.782236Z","title":"Self-learning machines based on Hamiltonian echo backpropagation.Physical Review X, 13(3):031020, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.782236Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:210be1e23b055f3b52fe090d2c6483ff073e281bbeb963aa215b87619377336a","observation_id":"a004e595-e3a2-4f9c-94c1-d8270fdbea4e","resolution":{"observed_at":"2026-08-16T00:46:05.782236Z","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":"2026-08-16T00:46:05.787186Z","title":"Routledge, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.787186Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:edd45df44ea69972873a84a7e34a7a3c31fca2935ecdafa44a6ad1032f6ae8e3","observation_id":"50ebd2a2-6be2-49d9-813e-6f9bddc7bcd8","resolution":{"observed_at":"2026-08-16T00:46:05.787186Z","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":"2026-08-16T00:46:05.792039Z","title":"Springer Science & Business Media, 2010","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.792039Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:8ee230957d6a51cb0d656ff5b45b96c8a89c28384c7839a065a8d2897282d419","observation_id":"1fcc1974-647f-4d27-8fba-c9a035532395","resolution":{"observed_at":"2026-08-16T00:46:05.792039Z","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":"2026-08-16T00:46:05.796502Z","title":"In-situ physical adjoint comput- ing in multiple-scattering electromagnetic environments for wave control.Nature Communications, 16(1):11466, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.796502Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:33a7092e312888fd628410f3294f273b767deb9411a668779b4968c3bbc2b413","observation_id":"1f4ff490-52f3-40ea-8231-dc111bd61ee7","resolution":{"observed_at":"2026-08-16T00:46:05.796502Z","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":"2026-08-16T00:46:05.800788Z","title":"Equilibrium propagation: Bridging the gap between energy- based models and backpropagation.Frontiers in Computational Neuroscience, 11:24, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.800788Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:aabfd25563ff0276961aa81d34c255ef9c5f6ccdec18146786e880aee784d540","observation_id":"57d860a0-289e-4ff4-a45d-3303ff35947a","resolution":{"observed_at":"2026-08-16T00:46:05.800788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.05259","last_updated":"2025-06-05T17:20:39Z","snapshot_observed_at":"2026-08-18T03:32:03.352493Z","submitted_at":"2025-06-05T17:20:39Z","title":"Learning long range dependencies through time reversal symmetry breaking","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.05259","snapshot_observed_at":"2026-08-16T00:46:05.805154Z","title":"Learning long range dependencies through time reversal symmetry breaking.arXiv preprint arXiv:2506.05259, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.805154Z"},"links":{"cited_paper":"/paper/2506.05259","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:8e9b4d10adc5c1e55af425ea5df6df5da48c0e6ab8c3b6b8c4fff448f7199c63","observation_id":"78ee6357-725f-41ab-bc4c-cd2af153e0d7","resolution":{"observed_at":"2026-08-16T00:46:05.805154Z","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":"2026-08-16T00:46:07.769115Z","title":"Fully forward mode training for optical neural networks.Nature, 632(8024):280–286, 2024","venue":null,"work_id":"9afbe2d0-2a65-41a2-b6e1-9dff4517e004","year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.809993Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:76ed48e6454dc5536fe4fb047019fc88d92882ea0d47656353110c180307291b","observation_id":"3192cc96-5d43-4e37-906b-9fa929a9037a","resolution":{"observed_at":"2026-08-16T00:46:07.774226Z","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":"2026-08-16T00:46:07.754042Z","title":"Training of photonic neural networks through in situ backpropagation and gradient measurement.Optica, 5(7):864–871, 2018","venue":null,"work_id":"0ad5d0e8-36b8-447d-9b55-004db2f768a6","year":2018},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.814375Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:b6619420ec3083e3d34cb83d598c9b0ea8760af16e6f9f7bd51c57256e32ec75","observation_id":"a947b660-a766-42f8-93bb-5360f341d709","resolution":{"observed_at":"2026-08-16T00:46:07.759135Z","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":"2026-08-16T00:46:07.738804Z","title":"Multilayer optical learning networks.Applied Optics, 26(23):5061–5076, 1987","venue":null,"work_id":"804c34b9-948f-4e99-accd-1795acf3988d","year":1987},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.818879Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:29408b092538dc10f57b5f37c73570c58b43d1fa06522215e5215da247ccc462","observation_id":"a3619e2b-4beb-42fa-aab9-0cd7d48f2988","resolution":{"observed_at":"2026-08-16T00:46:07.743830Z","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":"2026-08-16T00:46:07.723851Z","title":"Backpropagation through nonlinear units for the all-optical training of neural networks.Photonics Research, 9(3):B71– B80, 2021","venue":null,"work_id":"e5562749-3bb7-4255-9355-ab608a66fc7c","year":2021},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.823634Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:514e82a79be213f2b44b0ee50799409bb9919702cda3c747177793290ac2cfda","observation_id":"749bbef2-626a-4dc9-98b0-e9be04d04501","resolution":{"observed_at":"2026-08-16T00:46:07.728618Z","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":"2026-08-16T00:46:07.708972Z","title":"Training neural networks with end-to-end optical backpropagation.Advanced Photonics, 7(1):016004, 2025","venue":null,"work_id":"3fb86387-33ec-4260-9fc5-bf2459bdc5cf","year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.827946Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:7a6bcde6dae099d6e068013685fa0cbee106b6da7b41c5204e27ebd35321395e","observation_id":"0850a9da-0271-45f1-a2eb-0bb449a11797","resolution":{"observed_at":"2026-08-16T00:46:07.713689Z","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":"2026-08-16T00:46:07.693517Z","title":"Fully nonlinear neuromorphic computing with linear wave scattering.Nature Physics, 20(9):1434–1440, 2024","venue":null,"work_id":"fe04f475-2d2d-42f2-9414-a3bc371aa7a4","year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.832389Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:6fa4b9f0619ccedd9d4296f78027ff83d8beb295d257ff5cdea7c5bc1c60e111","observation_id":"f75b57b1-16a6-4743-b60a-354b9c18daac","resolution":{"observed_at":"2026-08-16T00:46:07.698781Z","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":"2503.07796","last_updated":"2025-03-10T19:25:29Z","snapshot_observed_at":"2026-08-16T12:51:22.279640Z","submitted_at":"2025-03-10T19:25:29Z","title":"Topological mechanical neural networks as classifiers through in situ backpropagation learning","version":1},"cited_work":{"arxiv_id":"2503.07796","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.07796","snapshot_observed_at":"2026-08-16T00:46:06.720325Z","title":"Topological mechanical neural networks as classifiers through in situ backpropagation learning","venue":"cond-mat.dis-nn","work_id":"585f6c30-cf71-485a-af2d-250a2417a661","year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.836754Z"},"links":{"cited_paper":"/paper/2503.07796","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:7c191f9e0afc46069735e5e2fbdbd4dd00e25261cc97f786dcd45f272e775864","observation_id":"3b303f06-fb83-4e97-a48a-02407dec855e","resolution":{"observed_at":"2026-08-16T00:46:06.725556Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:46:07.679048Z","title":"Localization transitions in non-Hermitian quantum mechan- ics.Physical Review Letters, 77(3):570–573, 1996","venue":null,"work_id":"6bb0e9cf-a5a1-40af-877c-9b08201007b6","year":1996},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.841572Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:0cb34501693a7ec263ab286293ed6dd336df5bf3c0a46a2538d8a0a2e95b7136","observation_id":"a8bae4a4-c628-4ab9-87fe-5f017e560918","resolution":{"observed_at":"2026-08-16T00:46:07.683863Z","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":"2026-08-16T00:46:07.664162Z","title":"Supervised learning in physical networks: From machine learning to learning machines.Physical Review X, 11(2):021045, 2021","venue":null,"work_id":"d387ba10-6d8f-4758-a254-1aa6d11f2874","year":2021},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.846312Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:fce007ba0dbfd25c9971df7ac03e5cf7761d1b9588820262e498773652dd4ede","observation_id":"554567a5-4fa4-4aab-8b73-aef886c7e86c","resolution":{"observed_at":"2026-08-16T00:46:07.668938Z","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":"2026-08-16T00:46:07.648670Z","title":"Learning without neurons in physical systems.Annual Review of Condensed Matter Physics, 14(1):417–441, 2023","venue":null,"work_id":"8a9f438f-5b60-49bf-89b5-d1bd79b68fe9","year":2023},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.850950Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:a54924fd121aadfad53dbae9e83d0c04029533bf28317f99b308f02139544ed9","observation_id":"ef9aaac2-3884-4719-a08b-dd31537eb2c8","resolution":{"observed_at":"2026-08-16T00:46:07.653877Z","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":"2026-08-16T00:46:07.634110Z","title":"Machine learning without a processor: Emergent learning in a nonlinear analog network","venue":null,"work_id":"91c37ec4-95ff-44d2-9bad-2d7abb8370be","year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.855456Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:1ed87ff4064f0dcb32e661d6f29176cfcaac2f878c8060e35e620f4dc66037f2","observation_id":"1eaadaea-5699-431b-87d5-0afdac308e17","resolution":{"observed_at":"2026-08-16T00:46:07.639176Z","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":"2026-08-16T00:46:07.618505Z","title":"Training self-learning circuits for power-efficient solutions.APL Machine Learning, 2(1):016114, 2024","venue":null,"work_id":"25ddb42f-599c-48dc-95e6-7078765a9411","year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.860305Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:3bdcc8833535d64629ba5ce51c9d0ea1cf70875ccb52efa817c16e5e82785025","observation_id":"f12580a3-b3fc-4531-aa40-838b9dac20a2","resolution":{"observed_at":"2026-08-16T00:46:07.624068Z","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":"2606.15443","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:46:06.693346Z","title":"Coercivity and local convergence of physical learning in linear circuits.arXiv preprint arXiv:2606.15443, 2026","venue":null,"work_id":"4b540601-e10c-4e8b-b39b-942568269180","year":2026},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.864538Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:f9597c29d3f8beb7513ac9b3b43b1ab970547ade588ff7c681880abe7cc077ac","observation_id":"2b987779-abb5-48d4-86b8-e5ea50fd7cd7","resolution":{"observed_at":"2026-08-16T00:46:06.700817Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:46:07.603017Z","title":"Multimodal deep learning using on-chip diffractive optics with in situ training capability.Nature Communications, 15(1):6189, 2024","venue":null,"work_id":"9f14f184-e8af-4ac4-8771-8db32291f532","year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.868953Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:a63271a70fa0ece6276c75d941cda8573c6bd63779ee9dc724555d9f026ba704","observation_id":"238edb60-a8c8-484c-9346-861d962f5aee","resolution":{"observed_at":"2026-08-16T00:46:07.608323Z","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":"2026-08-16T00:46:07.588138Z","title":"Multimodal oscillator networks learn to solve a classification problem.npj Metamaterials, 2(1):3, 2026","venue":null,"work_id":"70daaed9-e6c8-485d-ac20-e22a3c451857","year":2026},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.873525Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:ef74794937f7844e33e38b1e9eb851e03d38fac142f9c13dc88ddc89d4d21878","observation_id":"5cc3973c-b700-4343-b5d1-29954cf711b6","resolution":{"observed_at":"2026-08-16T00:46:07.592977Z","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":"2026-08-16T00:46:07.573360Z","title":"Forward–forward training of an optical neural network","venue":null,"work_id":"463f4823-d130-4bfb-a343-0bcd513a9537","year":2023},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.878428Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:8a94866bced7c30ed71c6dde2968794fc802ac80ade64eaa7e4dcb5b8594a812","observation_id":"88177e8b-b945-4c39-ae01-df9d4deaa277","resolution":{"observed_at":"2026-08-16T00:46:07.578223Z","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":"2026-08-16T00:46:07.558638Z","title":"Backpropagation-free training of deep physical neural networks.Science, 382(6676):1297–1303, 2023","venue":null,"work_id":"bafd2bcb-bcad-403e-b006-012ebe94e61a","year":2023},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.882587Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:e9649d41676432b4409e95b93fd0d23781d6795632eb6a9687d35a3059344046","observation_id":"c301d3ae-72b7-4e7d-9d13-6c2d1875b071","resolution":{"observed_at":"2026-08-16T00:46:07.563475Z","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":"2602.09569","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:46:06.598292Z","title":"Training deep physical neural networks with local physical information bottleneck.arXiv preprint arXiv:2602.09569, 2026","venue":null,"work_id":"e536256f-9d4d-46de-ac4f-563d7ada1371","year":2026},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.887082Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:5eb5dcf3da31ad9a5258d59e6eb0f19935b2dd1a0f99af860df449ef2ade38d5","observation_id":"32326224-c03d-430b-a550-6a844bb390cb","resolution":{"observed_at":"2026-08-16T00:46:06.606189Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:46:07.544194Z","title":"Using memristors for robust local learning of hardware restricted Boltzmann machines.Scientific Reports, 9(1):1851, 2019","venue":null,"work_id":"085b0f5e-043c-417f-909d-5fc052989d89","year":2019},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.891088Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:c7f30fb64e231bb3e1db9a106b64caaff84f137e733f3b9d91f0529b3ea18c3b","observation_id":"8328d740-a91b-4fa4-8379-a6292a4e101a","resolution":{"observed_at":"2026-08-16T00:46:07.549099Z","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":"2026-08-16T00:46:07.529552Z","title":null,"venue":null,"work_id":"d56b17c1-90f4-4adc-ae68-6ada2ec42737","year":2026},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.895409Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:e7b8fa60c3553332c3af27c5da763910fe28b6a4be34bc7948b28f27945f45f5","observation_id":"0d0e9a17-65b4-45e8-abc6-a1e631ecf16e","resolution":{"observed_at":"2026-08-16T00:46:07.534127Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2506.19136","last_updated":"2026-07-03T15:09:41Z","snapshot_observed_at":"2026-08-17T08:23:51.722795Z","submitted_at":"2025-06-23T21:11:40Z","title":"Local Learning Rules for Out-of-Equilibrium Physical Generative Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.19136","snapshot_observed_at":"2026-08-16T00:46:05.899468Z","title":"Local learning rules for out-of-equilibrium physical generative models.arXiv preprint arXiv:2506.19136, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.899468Z"},"links":{"cited_paper":"/paper/2506.19136","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:750d93925414c119c856c6961ddb1dd9defd0af2f404d5d115d0a25958dc7971","observation_id":"bde93477-ce26-4af7-85a3-b7bcfff8c27f","resolution":{"observed_at":"2026-08-16T00:46:05.899468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.20401","last_updated":"2025-08-01T15:35:41Z","snapshot_observed_at":"2026-08-18T11:56:55.645663Z","submitted_at":"2025-04-29T03:55:05Z","title":"Nonlinear Computation with Linear Optics via Source-Position Encoding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.20401","snapshot_observed_at":"2026-08-16T00:46:05.904066Z","title":"Nonlinear computation with linear optics via source-position encoding.arXiv preprint arXiv:2504.20401, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.904066Z"},"links":{"cited_paper":"/paper/2504.20401","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:a676a6174d579f07223e007d5ed84a128ebe88a57790b92d0d617dc44323c17d","observation_id":"94665e02-f2c7-4478-841f-2cdeaa291c87","resolution":{"observed_at":"2026-08-16T00:46:05.904066Z","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":"2026-08-16T00:46:07.514300Z","title":"Nonlinear optical encoding enabled by recurrent linear scattering.Nature Photonics, 18(10):1067–1075, 2024","venue":null,"work_id":"6a01b86c-c2da-4cff-a345-c9e18ab422ac","year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.908418Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:c750367244ddcf775a7ad50738caa7f854f3ef92a691f56e0cc23e0e2c6f3ecf","observation_id":"8995debe-bb78-4997-b40d-a4910fc1e758","resolution":{"observed_at":"2026-08-16T00:46:07.519296Z","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":"2026-08-16T00:46:07.498929Z","title":"Nonlinear processing with linear optics.Nature Photonics, 18(10):1076–1082, 2024","venue":null,"work_id":"8ad6c24c-b5d0-45e6-80cf-ae68cc7d8380","year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.912296Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:9b39e2642c0aa640e55c39347ad486f11fadb2520c3f29718450858cd1aafdcf","observation_id":"195a060a-4933-4e83-92a9-9d31b527349d","resolution":{"observed_at":"2026-08-16T00:46:07.503984Z","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":"2026-08-16T00:46:07.483736Z","title":"Giles and Niles A","venue":null,"work_id":"70bbcc43-b95d-45ff-9508-9e0cecc674c9","year":2000},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.916872Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:904ca189a6ad609ebb8ad895481422dadab82ca4d5307adc9a405a55cdf70036","observation_id":"edeab902-72ae-42b2-abb7-bcd209690470","resolution":{"observed_at":"2026-08-16T00:46:07.489024Z","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":"2026-08-16T00:46:07.468700Z","title":null,"venue":null,"work_id":"36cb83ab-23c1-40b8-b18e-40c7239a52b4","year":2006},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.921441Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:f841a0a929e246388e1d891d05393bee6227de4ce2ce1eb24c8cc57d8683949a","observation_id":"821fb53f-9b43-4696-898e-774607be9530","resolution":{"observed_at":"2026-08-16T00:46:07.473800Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-16T00:46:07.453470Z","title":"Dutton, and Shanhui Fan","venue":null,"work_id":"ce81baa5-5551-436a-8694-90ace3ba609a","year":2004},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.926116Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:d960528ceccdffd165a10cef2df8d2c38879089cb51e03616e91b0e7f9dcf9de","observation_id":"3ebc2fd8-2071-4698-a0db-85e575f6fedf","resolution":{"observed_at":"2026-08-16T00:46:07.458801Z","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":"2026-08-16T00:46:07.439670Z","title":null,"venue":null,"work_id":"813adf64-cbcf-43e6-96cf-de314ef18804","year":2007},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.930783Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:e7d41bd4e6195f2e15d65e40a719562dcd0b8068e64812e9863a36ee0149e05e","observation_id":"af87eca3-4d14-414d-98eb-81634cde922b","resolution":{"observed_at":"2026-08-16T00:46:07.444135Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-16T00:46:07.425887Z","title":"Optimal control of PDEs in a complex space setting: Application to the Schr¨ odinger equation.SIAM Journal on Control and Optimization, 57(2):1390–1412, 2019","venue":null,"work_id":"2fed841b-68e3-4185-9c5e-35c94aa719e8","year":2019},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.935322Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:e2044782ea0507757b5055c6dd181463acf32bde337b0128e6ca63d1a61fd41d","observation_id":"79b9c01d-f373-48c9-acc1-08c5f2d4db9c","resolution":{"observed_at":"2026-08-16T00:46:07.430331Z","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":"2026-08-16T00:46:07.410748Z","title":null,"venue":null,"work_id":"e3c41f13-419a-4d73-a08c-829934ec4449","year":1983},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.939731Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:c2d003f2df82f69191963c6c31189b67107c6b730ef77870328fe89206378852","observation_id":"16c8f897-3230-4c95-89fc-14c4d23fbd51","resolution":{"observed_at":"2026-08-16T00:46:07.415728Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-16T00:46:07.395148Z","title":"Complex-valued matrix differentiation: Techniques and key results.IEEE Transactions on Signal Processing, 55(6):2740–2746, 2007","venue":null,"work_id":"6cff6b16-622e-4ff3-a10b-8d3222fa35fb","year":2007},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.944453Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:a2ba1760e1d11e3690fa81467151870d9beb1e087fbc9a1a53c2be68671bb502","observation_id":"4bd3ec84-a8fc-4737-82ab-ce013e93e14f","resolution":{"observed_at":"2026-08-16T00:46:07.400856Z","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":"2026-08-16T00:46:07.380888Z","title":"Unconstrained optimization of real functions in complex variables.SIAM Journal on Optimization, 22(3):879–898, 2012","venue":null,"work_id":"4e9702e8-5601-41b2-9def-7f7ce55fd7e3","year":2012},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.949079Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:a114dab02a42517f527ca3008459f25acf7f81934b0564681341102406044f83","observation_id":"7f1c2edd-c7d8-448d-b799-f3c2ef3c7579","resolution":{"observed_at":"2026-08-16T00:46:07.385593Z","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":"2026-08-16T00:46:07.366467Z","title":"Springer Netherlands, 2009","venue":null,"work_id":"0050ce0f-4987-46e2-970b-e83218522176","year":2009},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.953746Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:5ef901078096e212c83bf386b1693d398652850a7bbf90f7cbf24642d2879b60","observation_id":"8435d6bb-f50e-48e0-829b-ff865826fdb2","resolution":{"observed_at":"2026-08-16T00:46:07.371041Z","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":"2602.19122","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:46:06.486938Z","title":"Training overdamped dynamics.arXiv preprint arXiv:2602.19122, 2026","venue":null,"work_id":"c2755aa3-e117-49dc-ab4f-c44b9f79a168","year":2026},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.958437Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:a1ec25df55b6b7003bd849baef49afc838961ed4b253289e196b2318f00db577","observation_id":"8c9b545d-c999-4b8a-9365-5b69453dbc43","resolution":{"observed_at":"2026-08-16T00:46:06.496495Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.20402","last_updated":"2025-08-08T04:52:40Z","snapshot_observed_at":"2026-08-14T18:27:46.991911Z","submitted_at":"2025-06-25T13:16:52Z","title":"Equilibrium Propagation for Dissipative Dynamics","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.20402","snapshot_observed_at":"2026-08-16T00:46:05.963030Z","title":"Equilibrium propagation for dissipative dynamics.arXiv preprint arXiv:2506.20402, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.963030Z"},"links":{"cited_paper":"/paper/2506.20402","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:8ebdeaaa23b18b03dd89f1934da7953c7d9f54a8ed5ca9a5925041568851a613","observation_id":"447a349e-3302-4b4c-a838-e3377c9a5be1","resolution":{"observed_at":"2026-08-16T00:46:05.963030Z","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":"2026-08-16T00:46:07.352428Z","title":"Holomorphic equilibrium propagation computes exact gradi- ents through finite size oscillations.Advances in Neural Information Processing Systems, 35:12950– 12963, 2022","venue":null,"work_id":"ad320fa9-e325-4b7e-890b-b4d31a35b4e7","year":2022},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.968550Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:7f3e3b2daf48f10f8060b4eadde4cd0691ae92ba1ebd117ef406e097e291f25c","observation_id":"ca56bbf5-6df2-4f4e-9131-db17485e4117","resolution":{"observed_at":"2026-08-16T00:46:07.357149Z","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":"2508.11750","last_updated":"2025-08-15T18:00:05Z","snapshot_observed_at":"2026-08-14T07:10:05.934970Z","submitted_at":"2025-08-15T18:00:05Z","title":"Training nonlinear optical neural networks with Scattering Backpropagation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.11750","snapshot_observed_at":"2026-08-16T00:46:05.973046Z","title":"Training nonlinear optical neural networks with scattering backpropagation.arXiv preprint arXiv:2508.11750, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.973046Z"},"links":{"cited_paper":"/paper/2508.11750","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:5d98c31890428fcc325aeb119cbfd35747243480e502197c127740bad5372b97","observation_id":"f81da60f-1d69-4808-ac96-16ea337ff137","resolution":{"observed_at":"2026-08-16T00:46:05.973046Z","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":"2026-08-16T00:46:05.977788Z","title":"Near-equilibrium propagation training in nonlinear wave systems.arXiv preprint arXiv:2510.16084, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.977788Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:b3407d196a3fee5a3dbea41d3d7df513d5ff78e50b6f6a45b1524a1bbe444bed","observation_id":"56ab3b59-ff39-4601-9649-f93a9dfc20b0","resolution":{"observed_at":"2026-08-16T00:46:05.977788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.04873","last_updated":"2018-08-14T19:41:12Z","snapshot_observed_at":"2026-08-17T10:31:24.297521Z","submitted_at":"2018-08-14T19:41:12Z","title":"Generalization of Equilibrium Propagation to Vector Field Dynamics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.04873","snapshot_observed_at":"2026-08-16T00:46:05.982267Z","title":"Gen- eralization of equilibrium propagation to vector field dynamics.arXiv preprint arXiv:1808.04873, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.982267Z"},"links":{"cited_paper":"/paper/1808.04873","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:e079ea38092413ed4dcd37a1be4c36f205f340ebc44dacb941cc7b7af1073fc4","observation_id":"3a5ff6f6-3e8e-4944-9273-6da0ab2db595","resolution":{"observed_at":"2026-08-16T00:46:05.982267Z","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":"2026-08-16T00:46:07.336545Z","title":"Improving equilibrium propagation without weight symmetry through Jacobian homeostasis","venue":null,"work_id":"3caa2da1-9370-4efc-9b92-13d66d52f5d3","year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.987035Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:8938ad18523131d8a01d89ae36deda5f58b6f63bd5372fc7086c20ddac47cddd","observation_id":"13440c67-405e-4b43-af1f-29db97d3d10b","resolution":{"observed_at":"2026-08-16T00:46:07.341615Z","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":"2602.03670","last_updated":"2026-06-01T15:49:57Z","snapshot_observed_at":"2026-08-17T07:07:24.052976Z","submitted_at":"2026-02-03T15:52:23Z","title":"Equilibrium Propagation for Non-Conservative Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.03670","snapshot_observed_at":"2026-08-16T00:46:05.991596Z","title":"Equilibrium propagation for non-conservative systems.arXiv preprint arXiv:2602.03670, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.991596Z"},"links":{"cited_paper":"/paper/2602.03670","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:074178729a00ed5564c450dd6e2a1f4d64702f9b80bccacac6e8483275ad9dd2","observation_id":"a6514f2c-e84e-4b45-8d02-cbab3d0a0de5","resolution":{"observed_at":"2026-08-16T00:46:05.991596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.15021","last_updated":"2022-05-30T12:02:53Z","snapshot_observed_at":"2026-08-16T16:56:42.081415Z","submitted_at":"2022-05-30T12:02:53Z","title":"Agnostic Physics-Driven Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.15021","snapshot_observed_at":"2026-08-16T00:46:05.996422Z","title":"Agnostic physics-driven deep learning.arXiv preprint arXiv:2205.15021, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:05.996422Z"},"links":{"cited_paper":"/paper/2205.15021","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:16bfe5b9a6182d82b191f469520a66f02f02fcffb98dac19a0b60140ae828469","observation_id":"0702e99d-78ff-4a76-8c31-7735c30d45dd","resolution":{"observed_at":"2026-08-16T00:46:05.996422Z","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":"2026-08-16T00:46:07.321779Z","title":"Reciprocal relations in irreversible processes","venue":null,"work_id":"bb01a82e-06b9-451d-96fc-a6d5b656ccf0","year":1931},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.001356Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:4ae4e1683dde92629f27aa2f1b21b730ccf520a0da6c0cb188e35a72bb42f5be","observation_id":"233e277a-b10e-4463-818b-7472e4faeb7f","resolution":{"observed_at":"2026-08-16T00:46:07.326899Z","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":"2026-08-16T00:46:07.306701Z","title":"Fluctuations and irreversible processes.Physical Review, 91(6):1505–1512, 1953","venue":null,"work_id":"fbec5499-6051-4bc8-af36-cf1dfcc02668","year":1953},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.006772Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:e739276155e7adacb681c3dab0537b76a63782e8e01a9748834f7b9870e196f5","observation_id":"dd5878f1-c8f3-4399-8e08-0bed7b2923d3","resolution":{"observed_at":"2026-08-16T00:46:07.311481Z","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":"2026-08-16T00:46:07.292590Z","title":"Topological mechanics of gyroscopic metamaterials.Proceedings of the National Academy of Sciences, 112(47):14495–14500, 2015","venue":null,"work_id":"cfe3ea1d-cb09-4c8c-a452-6e526094a543","year":2015},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.011635Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:de145f7138375a0dfc00db77c681bc2ab3bc1da882c033a539ac0a2f0b8021c9","observation_id":"339ca949-da9e-4b12-8cfa-8eb07698b381","resolution":{"observed_at":"2026-08-16T00:46:07.296883Z","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":"2026-08-16T00:46:07.278838Z","title":"Observation of PT phase transition in a simple mechanical system.American Journal of Physics, 81(3):173–179, 2013","venue":null,"work_id":"adac56fc-9e6c-4177-8100-4d5d8277904a","year":2013},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.016356Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:6139e42f3f189b1d63193085a1a35da1cf76ad0e7876a5634f4f1b5d65f4b2e3","observation_id":"cbaa2982-725e-44e8-9964-2bef625484a1","resolution":{"observed_at":"2026-08-16T00:46:07.283561Z","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":"2026-08-16T00:46:07.263208Z","title":"Time reversal of ultrasonic fields","venue":null,"work_id":"63e45012-13c2-4574-8698-10311f984e41","year":1992},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.020788Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:39fedfb3bec43e018f8df6e602cf9958da07a086f7073fb9842fdc468f5b13ad","observation_id":"b17f11b2-c0ce-47d8-be06-fed64e592b3a","resolution":{"observed_at":"2026-08-16T00:46:07.267883Z","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":"2506.06248","last_updated":"2026-04-13T10:47:48Z","snapshot_observed_at":"2026-08-15T15:14:57.250998Z","submitted_at":"2025-06-06T17:17:40Z","title":"Lagrangian-based Equilibrium Propagation: generalisation to arbitrary boundary conditions & equivalence with Hamiltonian Echo Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.06248","snapshot_observed_at":"2026-08-16T00:46:06.025279Z","title":"Lagrangian-based equilib- rium propagation: generalisation to arbitrary boundary conditions & equivalence with Hamiltonian echo learning.arXiv preprint arXiv:2506.06248, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.025279Z"},"links":{"cited_paper":"/paper/2506.06248","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:97e1434c9a4c189cc27557e75c18479d3b408e052f8272c78428162f050624b7","observation_id":"e49d490e-1376-42df-855c-4bbeb5b6cc30","resolution":{"observed_at":"2026-08-16T00:46:06.025279Z","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":"2026-08-16T00:46:07.248975Z","title":null,"venue":null,"work_id":"5159044e-39f3-46a3-b9be-1de30c0d996d","year":1965},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.030076Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:6e9bd4c5f258c530aa86601a0ff6a6893d0705b8c578a1635d253e6c0be0b72c","observation_id":"4ed3ec33-de91-475f-b1a9-6743b52de51f","resolution":{"observed_at":"2026-08-16T00:46:07.253047Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-16T00:46:07.233993Z","title":"Scaling equilibrium propagation to deep convnets by drastically reducing its gradient estimator bias.Frontiers in Neuroscience, 15:633674, 2021","venue":null,"work_id":"0204b6ce-f719-4a27-a334-890f38845abf","year":2021},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.034069Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:c7deac4ac6eb88928b8e838adb7fef795214b3c1b7986541e285df9606bcbc4c","observation_id":"150c1501-62ce-4abb-aac0-e92d6a32a0f8","resolution":{"observed_at":"2026-08-16T00:46:07.238766Z","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":"2026-08-16T00:46:07.218916Z","title":"Equilibrium propagation for learning in Lagrangian dynamical systems.Physical Review E, 112(3):035304, 2025","venue":null,"work_id":"8d3d5fe1-5499-4a63-8a25-4f7ae27aed8f","year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.038029Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:1de321d65d62ed8774b9dd0b4f19288f6211f0285107cc058db0ceb8b9b0bbd9","observation_id":"d28915eb-8e5f-4934-b1e0-12381ae629f7","resolution":{"observed_at":"2026-08-16T00:46:07.224163Z","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":"2026-08-16T00:46:07.204133Z","title":"Springer Science & Business Media, 1991","venue":null,"work_id":"99778f81-696b-4520-98ed-8fbeb224369e","year":1991},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.042357Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:037c1f962a45a6f5c584c5f3659541fbf7cd4fa8cdba4faffaed0354fb62687c","observation_id":"8f707fd7-c1bb-479d-af54-7e64e05c0883","resolution":{"observed_at":"2026-08-16T00:46:07.208800Z","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":"2312.04858","last_updated":"2023-12-08T06:26:04Z","snapshot_observed_at":"2026-08-16T14:36:36.332569Z","submitted_at":"2023-12-08T06:26:04Z","title":"A short tutorial on Wirtinger Calculus with applications in quantum information","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.04858","snapshot_observed_at":"2026-08-16T00:46:06.046428Z","title":"A short tutorial on Wirtinger calculus with applications in quantum information.arXiv preprint arXiv:2312.04858, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.046428Z"},"links":{"cited_paper":"/paper/2312.04858","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:fb4fb6b85574aaefed8992cbeab37f158448fba8047133f83363ee7f772d2de5","observation_id":"93d14549-4456-4522-9b98-94cb7800308b","resolution":{"observed_at":"2026-08-16T00:46:06.046428Z","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":"2026-08-16T00:46:07.188999Z","title":"Integrated photonic neural network with on-chip backpropagation training.Nature, 651(8107):927–932, 2026","venue":null,"work_id":"6980ca31-f54b-4f36-bee9-10ef4bb92e1b","year":2026},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.050664Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:2175a5c1069029e16b15a47ea002041170334b9ef0d499fdc2d1359fd3e356ea","observation_id":"ca8384b6-1708-4544-b1fa-8f2c26c38205","resolution":{"observed_at":"2026-08-16T00:46:07.194144Z","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":"2006.01981","last_updated":"2020-06-09T22:26:05Z","snapshot_observed_at":"2026-08-10T18:05:12.198187Z","submitted_at":"2020-06-02T23:38:35Z","title":"Training End-to-End Analog Neural Networks with Equilibrium Propagation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.01981","snapshot_observed_at":"2026-08-16T00:46:06.054589Z","title":"Training end-to-end analog neural networks with equilibrium propagation.arXiv preprint arXiv:2006.01981, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.054589Z"},"links":{"cited_paper":"/paper/2006.01981","citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:e102b1fded770f235f01cdba565641d6c5b89948e869400cacc1e85a4e72bc87","observation_id":"90ae2b03-5a70-47c2-a8d8-d2feffeb4f42","resolution":{"observed_at":"2026-08-16T00:46:06.054589Z","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":"2026-08-16T00:46:07.174182Z","title":"Training an Ising machine with equilibrium propagation.Nature Communications, 15(1):3671, 2024","venue":null,"work_id":"8d2b3a89-f058-4f20-97a7-1ea8c104d439","year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.058717Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:9ee21d6f9a620eb879e7c3e0aacdba09a6026195566b679911bcdd1d4fd7bceb","observation_id":"76a1151c-2b73-4eb4-aea3-8081200b7ddb","resolution":{"observed_at":"2026-08-16T00:46:07.178878Z","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":"2026-08-16T00:46:07.158969Z","title":"Equivalence of equilibrium propagation and recurrent back- propagation.Neural Computation, 31(2):312–329, 2019","venue":null,"work_id":"4c9058d0-8d47-41d1-839a-afcef3dec194","year":2019},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.062633Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:eb995cb0ede5c65a80059d098b6ee547fe3b5ea63d96ec09b37b7c9ad0edaa41","observation_id":"3fc0bcfd-8e07-4fc0-839e-6679f0e9065b","resolution":{"observed_at":"2026-08-16T00:46:07.164079Z","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":"2026-08-16T00:46:07.144071Z","title":"Updates of equilibrium prop match gradients of backprop through time in an RNN with static input.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"efaf712e-8058-46a4-9b25-1c45e2273786","year":2019},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.067153Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:a84d85253fa35834e409e44beef509463cb92c434a598ed0cba60e85fb2308d3","observation_id":"ce00a984-62df-4183-a3f5-9ac44af1ae4d","resolution":{"observed_at":"2026-08-16T00:46:07.148938Z","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":"2026-08-16T00:46:07.128827Z","title":"Frequency propagation: Multimechanism learning in nonlinear physical networks.Neural Computation, 36(4):596–620, 2024","venue":null,"work_id":"50d5fcd2-dd7f-49a9-9674-7307f2d0025c","year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.071873Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:97abf3b776c6d85227dcac9f18ed0a40e6ef5163108cd6a66800f3042440988f","observation_id":"5e98f556-17f6-4f7c-96b3-83801e1cb2b6","resolution":{"observed_at":"2026-08-16T00:46:07.133741Z","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":"2026-08-16T00:46:07.114479Z","title":"Training coupled phase oscillators as a neuromorphic platform using equilibrium propagation.Neuromorphic Computing and Engineering, 4(3):034014, 2024","venue":null,"work_id":"29fb7549-616e-410e-8e64-836b9ef0c89f","year":2024},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.076518Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:8dbcacee3124d6d453029cbc76ac1f3204732a5cdd7327fab428041911f76851","observation_id":"a8ab75d8-791f-4c7d-a45f-7b18a7075f7d","resolution":{"observed_at":"2026-08-16T00:46:07.119150Z","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":"2026-08-16T00:46:07.099921Z","title":"Generalized bulk–boundary correspondence in non-Hermitian topolectrical circuits.Nature Physics, 16(7):747– 750, 2020","venue":null,"work_id":"40054fe4-83db-498a-ac7e-2ed8faa7ed74","year":2020},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.081204Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:17ac459721ce172a95141b2d0a5c565da4c88e148436c6e410de3773ac69fd43","observation_id":"157d1eeb-ac3b-405a-84ae-f380bffddc68","resolution":{"observed_at":"2026-08-16T00:46:07.104681Z","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":"2026-08-16T00:46:07.085154Z","title":"Topological funneling of light.Science, 368(6488):311–314, 2020","venue":null,"work_id":"e6637aa5-3a21-4884-a162-333479dae184","year":2020},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.085506Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:cbdbe40ef2024cd50e4835f280619371e765484ffe1e6566c6931bcb17936aae","observation_id":"e3c54856-4d7d-4d6a-893f-b7e88ed60b30","resolution":{"observed_at":"2026-08-16T00:46:07.089730Z","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":"2026-08-16T00:46:07.069097Z","title":"Sound isolation and giant linear nonreciprocity in a compact acoustic circulator.Science, 343(6170):516–519, 2014","venue":null,"work_id":"09499bd2-3919-4755-aeb8-1bc4ea1fb2cd","year":2014},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.090155Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:3b12e1779439ff3d3f6ffb67c9f6f17f4491cd44893650d053ae78128aff3591","observation_id":"5dc0e373-235d-4765-a390-6f51c8993368","resolution":{"observed_at":"2026-08-16T00:46:07.074399Z","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":"2026-08-16T00:46:07.053388Z","title":"Odd elasticity.Nature Physics, 16(4):475–480, 2020","venue":null,"work_id":"23226814-7c05-40d1-81af-8a0325b29035","year":2020},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.094767Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:be4f5e582ac21cd8082f7833708849f43c3512485f1918052e41a7ca7dc5f8aa","observation_id":"b2e53d59-41de-4251-a6bd-2f17d5371455","resolution":{"observed_at":"2026-08-16T00:46:07.058277Z","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":"2026-08-16T00:46:07.038257Z","title":"On Onsager’s principle of microscopic reversibility.Reviews of Modern Physics, 17(2-3):343–350, 1945","venue":null,"work_id":"ca0ba044-6c67-4ad1-972e-a487502650ad","year":1945},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.099445Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:3147833458faaef16729d7f853bde2c5e3b35da3e98f0f5a7d5bb31f58d977c1","observation_id":"b0bafa6d-7c27-4745-abab-54af78674ba8","resolution":{"observed_at":"2026-08-16T00:46:07.043100Z","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":"2026-08-16T00:46:07.022909Z","title":"Symmetry and topology in non-Hermitian physics.Physical Review X, 9(4):041015, 2019","venue":null,"work_id":"459725e5-3c8f-4a0a-9f0a-8a7850b33c97","year":2019},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.104192Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:150411e660f818cba2225d05215fb9699f677449821bb26e63371fd8b68e0887","observation_id":"df0bd6df-2fe8-4d49-932b-7b7d01837bb0","resolution":{"observed_at":"2026-08-16T00:46:07.028033Z","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":"2026-08-16T00:46:07.007179Z","title":"Non-reciprocal robotic metamaterials.Nature Communications, 10(1):4608, 2019","venue":null,"work_id":"f92a7804-bfe7-4d21-a602-26567f3baaa8","year":2019},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.108772Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:ecd30bf283c414bafc365f5f90b4ee7e1ac3a2cbd478329d269cce9bc0719fe6","observation_id":"602965f6-e642-4273-bfe7-45bbf84eb7cd","resolution":{"observed_at":"2026-08-16T00:46:07.012305Z","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":"2026-08-16T00:46:06.991386Z","title":"Observation of non-Hermitian topology and its bulk–edge correspondence in an active mechanical metamaterial","venue":null,"work_id":"61114c6e-e842-45a2-b43e-8d93f534492a","year":2020},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.113279Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:454e80b188def0fd7a6bdb197961dbd2d2cb0e16c1ef0663e4c21238b18868b1","observation_id":"ff8fbc27-cff2-49a5-b823-1b6077a0024f","resolution":{"observed_at":"2026-08-16T00:46:06.996375Z","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":"2026-08-16T00:46:06.975783Z","title":"Adjoint computation of Berry phase gradients.Journal of Sound and Vibration, 619:119357, 2025","venue":null,"work_id":"faa33609-586b-405f-baa9-94347b2140aa","year":2025},"citing_paper":{"arxiv_id":"2608.11585","last_updated":"2026-08-12T02:53:39Z","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-16T00:46:06.117939Z"},"links":{"citing_paper":"/paper/2608.11585"},"observation_digest":"sha256:7d54549aa88a14e43e521116488b4d1be30b1d0d3b4d3274311ac9259b27d4bf","observation_id":"50cc25b8-d88c-42a5-9623-44c932676803","resolution":{"observed_at":"2026-08-16T00:46:06.981345Z","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":"2608.11585","last_updated":"2026-08-12T02:53:39Z","latest_version":1,"primary_category":"cond-mat.dis-nn","snapshot_observed_at":"2026-08-18T02:50:06.955938Z","submitted_at":"2026-08-12T02:53:39Z","title":"Unifying Physical Backpropagation"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":46,"verified_exact":5,"verified_fuzzy":49},"total_outbound_references":109},"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 100 of 109 outbound references and 0 inbound Pith citation observations for arXiv:2608.11585."}