{"as_of":"2026-08-09T00:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e2a1b9c5f3a38bcdba76fd80a3972ccbc6edf4b5ea72dd6846924778f22158b7","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:43:57.049767Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2506.04523/citation-record","integrity":"/paper/2506.04523/integrity","json":"/paper/2506.04523/citation-record.json","paper":"/paper/2506.04523"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:44:01.906543Z","title":"Sustainable ai: Environmental implications, challenges and opportunities,","venue":null,"work_id":"2b61bd3d-5754-43c8-ba10-733b9e22be18","year":2022},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:53.381961Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:efce1418e06fe3892785354c4f17ee047ca8fa6cb61abed27452584eac74ce21","observation_id":"160f4c76-8534-4f7f-97f4-1a3789523361","resolution":{"observed_at":"2026-08-07T10:44:01.961145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:44:01.754931Z","title":"OpenAI’s CEO Says the Age of Giant AI Models Is Already Over — wired.com,","venue":null,"work_id":"5288b060-4870-4b22-bde2-60d5680f06f6","year":2025},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:53.482828Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:3a89cc0e7333db0e57558e2b402a58100278c6a898c9eec8e4236d59b7e175e5","observation_id":"3c04183f-be06-48a9-83ad-89e53c52d14a","resolution":{"observed_at":"2026-08-07T10:44:01.830800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2775.36628","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:44:00.317025Z","title":"Hybrid heterogeneous clusters can lower the energy consumption of llm inference workloads,","venue":null,"work_id":"da81e40c-804f-46a0-a4e6-c90e4a969bc8","year":2024},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:53.586833Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:13f5654fa122c78057393747bda44c9745400e3e82f2aba25882a798d360c40b","observation_id":"440795a6-6e0e-4f50-810f-dd6744deebe6","resolution":{"observed_at":"2026-08-07T10:44:00.460608Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:43:53.688230Z","title":"From words to watts: Benchmarking the energy costs of large language model inference,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:53.688230Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:83db3fd2e8e392924793103fd4e774fe0bc95f19e383bad6cce92834c8940922","observation_id":"dcd3e779-e1e2-4c9d-9756-bfa91a9bd433","resolution":{"observed_at":"2026-08-07T10:43:53.688230Z","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":"record/7855594","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:43:59.932975Z","title":"The environmental impact of ai: A case study of water consumption by chat gpt,","venue":null,"work_id":"8c41ee64-07fc-4aa1-a1d3-3e19a6258401","year":2023},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:53.776620Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:d334ed66949b0e83e85c829488ad54ce064ce2d4a65c53a9c3579d60281f1182","observation_id":"ffd4536f-486d-4978-8318-443a03c6d202","resolution":{"observed_at":"2026-08-07T10:44:00.026748Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:44:01.648375Z","title":"Q&A: UW researcher discusses just how much energy ChatGPT uses — washington.edu,","venue":null,"work_id":"fdadc69b-b8e4-4063-932b-836edfb30c97","year":2023},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:53.837816Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:3e791d3e9ecf879027421a8e600b2d14608bdddcbaeed89937c674c61e320c9a","observation_id":"0ad21955-9fcb-488c-8b07-63792715783e","resolution":{"observed_at":"2026-08-07T10:44:01.699725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:43:53.939335Z","title":"Reservoir computing approaches to recurrent neural network training,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:53.939335Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:ff7972b61347babb9db14b633e359d7abc77b347649bacf5fe423b9e6c8b9134","observation_id":"87540934-0347-4c0b-9985-76d1d69d98b1","resolution":{"observed_at":"2026-08-07T10:43:53.939335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.15045","last_updated":"2021-06-01T19:32:18Z","snapshot_observed_at":"2026-08-06T03:30:01.746175Z","submitted_at":"2020-12-30T05:20:16Z","title":"Reservoir Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.15045","snapshot_observed_at":"2026-08-07T10:43:54.047640Z","title":"Reservoir transformers,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:54.047640Z"},"links":{"cited_paper":"/paper/2012.15045","citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:d589edfe21be18edef6020c92d1701e54e21bcd886b08a7c780f7d0ddb44d3a0","observation_id":"af86c34b-e1cd-4652-9cd4-a4182fdf9f46","resolution":{"observed_at":"2026-08-07T10:43:54.047640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.3390/en16145366","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:43:58.913211Z","title":"Analogue and physical reservoir computing using water waves: Applications in power engineering and beyond,","venue":null,"work_id":"a2a8f75e-9e13-41dc-9fdd-01cf359abac5","year":2023},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:54.148487Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:9cca809ce5f8d05222bd03eaf38084edb9245455e74808088306ddb7b7a4b8f5","observation_id":"623f9a57-dbc1-4b9e-89e7-ae61dd4dd824","resolution":{"observed_at":"2026-08-07T10:43:59.065743Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:43:54.276501Z","title":"Advances in coherent magnonics,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:54.276501Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:9a1cf16fb1f23697ed39a477f91464f69d13b9952aeca614341df6a0e01316d6","observation_id":"3b6d5ad7-1a80-4506-b48d-d3b914a34705","resolution":{"observed_at":"2026-08-07T10:43:54.276501Z","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":"2026-08-07T10:43:54.388716Z","title":"Hybrid quantum systems based on magnonics,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:54.388716Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:fcfcdd54beacb500d43f5e324503b4633d6175063fecad4068347702d5703d50","observation_id":"9b0f8813-67ae-403e-bbc5-601feaa96fb4","resolution":{"observed_at":"2026-08-07T10:43:54.388716Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/s42005-019-","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:43:58.663240Z","title":"Towards magnonic devices based on voltage- controlled magnetic anisotropy,","venue":null,"work_id":"af92532c-06fe-4bb7-b43c-7c77f084a438","year":2019},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:54.513439Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:3da57bad4c79463dcbee0a9fcfeb923c96855975c9f92891103371b999418500","observation_id":"28a24975-f82c-41e0-9d05-32b827a7b23b","resolution":{"observed_at":"2026-08-07T10:43:58.762207Z","resolver_source":"doi_truncated","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1088/1361-6463/aa6a65","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:43:58.398981Z","title":"Magnonic crystals for data processing,","venue":null,"work_id":"717ceba2-ce7e-4458-8c48-a20d873b07f1","year":2017},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:54.624302Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:a231be4560b9708cfb85311abba467d8581a15b93780737e0e50161b503c29f3","observation_id":"71c2814f-e560-4f4f-81ee-27547266b843","resolution":{"observed_at":"2026-08-07T10:43:58.506805Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1201/9780429423079-6","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:43:58.177463Z","title":null,"venue":null,"work_id":"264dce23-d5fa-443b-92db-e91b3fc14274","year":2019},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:54.709678Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:10f441a4d69743c0ab1220a0be8702ccf5f426b01fb2e7f1ee9c66c423a15eed","observation_id":"ea59ad2f-9a28-48c7-9647-918cc6d7c77c","resolution":{"observed_at":"2026-08-07T10:43:58.277458Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1063/1.4960195","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:43:57.993819Z","title":"Nonlinear spin wave coupling in adjacent magnonic crystals,","venue":null,"work_id":"ef446890-45c7-4b23-939a-5156a571f230","year":2016},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:54.781853Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:4b2e928485d633f0b1c2fa2e5c59335729ae16ed598602f007daf0bf0381796d","observation_id":"47c3f674-e67c-41a6-ae6d-a8a353b87f87","resolution":{"observed_at":"2026-08-07T10:43:58.076500Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:43:54.873990Z","title":"Nanoscale spin-wave circuits based on engineered reconfigurable spin-textures,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:54.873990Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:1492bee0360d8734d39c82cd729d60f677a05b62dc4f683e1abb5908b0df4ba0","observation_id":"63eeed53-1988-465b-ac2d-53f2e78a5c11","resolution":{"observed_at":"2026-08-07T10:43:54.873990Z","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":"2020.30280","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:43:59.588582Z","title":"Spin wave normalization toward all magnonic circuits,","venue":null,"work_id":"ac55983f-93b6-4211-9bc3-2fbdc9517804","year":2021},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:54.979095Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:bbb481549ba74c1c686954f3cc5ee214ef6f9a0877cdbd07affc04c9eb68c89a","observation_id":"f2ba6c89-f214-42de-80c5-825595654766","resolution":{"observed_at":"2026-08-07T10:43:59.715439Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1063/1.4987007","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:43:57.725354Z","title":"A switchable spin-wave signal splitter for magnonic networks,","venue":null,"work_id":"154f8371-00eb-40a0-ab33-c591bf51cda6","year":2017},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:55.086062Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:b94dd7e15d67a8b559dc726f15c69d7ef11a7adf889246c8b8d023e506ad2d7e","observation_id":"52e07262-08e3-44c9-9085-3bc368453ed8","resolution":{"observed_at":"2026-08-07T10:43:57.843424Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.09542","last_updated":"2024-04-25T18:21:43Z","snapshot_observed_at":"2026-07-06T18:14:54.506051Z","submitted_at":"2024-04-25T18:21:43Z","title":"Hybrid Magnonic Reservoir Computing","version":1},"cited_work":{"arxiv_id":"2405.09542","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.09542","snapshot_observed_at":"2026-08-07T10:43:59.223214Z","title":"Hybrid Magnonic Reservoir Computing","venue":"cs.ET","work_id":"8acda64f-9dc1-4aa8-982e-5a81501f1b3e","year":2024},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:55.198430Z"},"links":{"cited_paper":"/paper/2405.09542","citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:ef227609c6d6288cf2e552d8acc1dcea0790727d93c2eafce86b47d5d53fd433","observation_id":"bf60e2d3-bae1-4be1-a049-3540df2dab91","resolution":{"observed_at":"2026-08-07T10:43:59.326059Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:43:55.326799Z","title":"Iono–magnonic reservoir computing with chaotic spin wave interference manipulated by ion-gating,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:55.326799Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:31010abb566dde1b75914f4612a0a12ee80bc6cf7ba52c2bc6060d68462c111a","observation_id":"44ad6dc9-98a5-4ea1-89ad-82fda4586e21","resolution":{"observed_at":"2026-08-07T10:43:55.326799Z","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":"2026-08-07T10:44:01.537131Z","title":"On the importance of initialization and momentum in deep learning,","venue":null,"work_id":"1b231926-5742-427f-af1a-19b003cb46fa","year":2013},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:55.444620Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:eab8d75771d1ad1cf0fbca1ff84fcafe7687743ae3db94703e38c1c641ec42b5","observation_id":"e7998950-3ebd-4a3b-bf62-3552591c0574","resolution":{"observed_at":"2026-08-07T10:44:01.581568Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:43:55.585112Z","title":"Understand- ing deep learning requires rethinking generalization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:55.585112Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:92d1491a1a5938843ae8390ac367d26370467c44a56df46f357b6332e80a7c16","observation_id":"1c22c617-97a1-4cee-8a8d-37be86772a61","resolution":{"observed_at":"2026-08-07T10:43:55.585112Z","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":"2026-08-07T10:43:55.691904Z","title":"Variational quantum algorithms,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:55.691904Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:9e642c4703fb0b52cb726c8c55ecb9e43da5fdaf054b89b2aaa4c22fcc1fae9a","observation_id":"1f5b9815-b9e5-457e-b1ef-65dcbbcec49c","resolution":{"observed_at":"2026-08-07T10:43:55.691904Z","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":"2026-08-07T10:44:01.409121Z","title":"Breast cancer wisconsin (diagnostic),","venue":null,"work_id":"52c1d779-94a9-4a94-a257-f8e6a01d8025","year":1993},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:55.775322Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:0ffa123f6ceb5c6809b08956012e4d0d500906d6b99f60e5a72844e7dfc20f04","observation_id":"0b396dff-153e-483c-8cb8-028aed7a7d6d","resolution":{"observed_at":"2026-08-07T10:44:01.472920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:43:55.849661Z","title":"Bottou,Large-Scale Machine Learning with Stochastic Gradient Descent","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:55.849661Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:4906ba85b8371ec6b8d463a40370be8cffbe3ae5bfe17d25737e5343c70338e1","observation_id":"d379919f-51ec-467a-99d5-041e19eb1762","resolution":{"observed_at":"2026-08-07T10:43:55.849661Z","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":"2026-08-07T10:43:55.921838Z","title":"Adam: A method for stochastic optimization,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:55.921838Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:c0300b2d9e5923ea70578db28321222f8fbd669820ce8e6627ce33f6e4c355c6","observation_id":"ff765cc8-a6f0-4853-b75f-2baf2ec54fa4","resolution":{"observed_at":"2026-08-07T10:43:55.921838Z","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":"2026-08-07T10:44:01.203883Z","title":"Multi30k: Multilingual english-german image descriptions,","venue":null,"work_id":"c8aec359-eaae-4e19-82e5-37e900923135","year":null},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.178311Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:b49d3caf7296be9739f2213f6746f07abb21966ead312d98feb3d499ede65528","observation_id":"e5aed5cd-ae4a-432a-b1da-c8ac75a0f692","resolution":{"observed_at":"2026-08-07T10:44:01.320823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:44:00.883616Z","title":"Numerical simulations of a magnonic reservoir computer,","venue":null,"work_id":"bca04452-311f-4e1b-a7db-4eb194cc436b","year":null},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.448699Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:fdc2b0e690280560d99feeda6ec67bc57aa7e66a36e2be01b8664e6987ba47e3","observation_id":"ba6d8aaa-4f31-4bc9-9dbd-9481bda843cd","resolution":{"observed_at":"2026-08-07T10:44:01.040995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:43:56.658737Z","title":"Implementing a magnonic reservoir computer model based on time-delay multiplex- ing,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.658737Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:c81eef8795c0fcf70d839ef22920684b94ef8cad68383dd0e2e9df1499e06827","observation_id":"dcc4f427-6ded-49ee-92df-89b4bdb959fb","resolution":{"observed_at":"2026-08-07T10:43:56.658737Z","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":"2026-08-07T10:43:56.793550Z","title":"A current- controlled magnonic reservoir for physical reservoir computing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.793550Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:2a80d857f0df90d2def58adc96aa6c454f5c432bf7864dad2ac14b726f761b85","observation_id":"644409b2-52a7-4d68-90c5-e5625236e643","resolution":{"observed_at":"2026-08-07T10:43:56.793550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1103/physrevapplied.10.034063","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:43:57.186446Z","title":"Macromagnetic simulation for reservoir computing utilizing spin dynamics in magnetic tunnel junctions,","venue":null,"work_id":"48eb8195-91b0-4a1b-8dcf-1b09d0562aff","year":2018},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.934454Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:92fddd867be82a3592f969639b4b604460138f7ddb7ee34fb34627706fc10d62","observation_id":"148b1c02-c720-42b7-86f9-4f6cf155e5c5","resolution":{"observed_at":"2026-08-07T10:43:57.298549Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:44:00.537781Z","title":"At the edge of chaos: Real-time computations and self-organized criticality in recurrent neural networks,","venue":null,"work_id":"dad90e37-7b54-419e-acd5-212140f63acb","year":2004},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:57.049767Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:1f258019c17b31ebccff68bdc495f2eea81ff68d2bfd06650a6d7681027edc94","observation_id":"94ba6eeb-409f-489f-a044-2e738344fe97","resolution":{"observed_at":"2026-08-07T10:44:00.646152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-07T10:43:56.038494Z","title":"Available: https://arxiv.org/abs/1412.6980","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.038494Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:cff824d9538d6df5ba1acae15ae3e39dfb8cef919604f289647dc8232b9a76bd","observation_id":"f2ec0d62-4049-4d33-bf31-f7e37037de5f","resolution":{"observed_at":"2026-08-07T10:43:56.038494Z","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":"2026-08-07T10:43:56.320215Z","title":"Available: http://dx.doi.org/10.18653/v1/W16-3210","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.320215Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:702d870ade6cd7d5965c43c9768f8dd5611241a8a72f66ad6499d00cf7bc891d","observation_id":"a2d8f4c7-f13b-42d2-b587-51dc56281e1e","resolution":{"observed_at":"2026-08-07T10:43:56.320215Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1063/5.0184848","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:43:57.427673Z","title":"Available: http://dx.doi.org/10.1063/5.0184848","venue":null,"work_id":"c41367fa-b1b6-41a1-944f-bc73c8273e10","year":null},"citing_paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T10:43:56.554921Z"},"links":{"citing_paper":"/paper/2506.04523"},"observation_digest":"sha256:5b036a738530313f876affd8b5fbd8b3b7d7f28f4485f0675723612c7ce02946","observation_id":"f0133127-354d-4abd-adcb-775c61855a0d","resolution":{"observed_at":"2026-08-07T10:43:57.551067Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.04523","last_updated":"2025-06-05T00:06:30Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T16:30:14.089397Z","submitted_at":"2025-06-05T00:06:30Z","title":"Perturbative Gradient Training: A novel training paradigm for bridging the gap between deep neural networks and physical reservoir computing"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":1,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":15,"verified_exact":9,"verified_fuzzy":8},"total_outbound_references":35},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2506.04523."}