{"as_of":"2026-08-20T12:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1f84c7534cd925b75ed3c6d914242ed1d718d4664062a88cf54f0169690bb6de","coverage":[{"denominator":67,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":67,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:51:08.024625Z","state":"measured"},{"denominator":68,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":68,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T05:48:55.160266Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T05:48:59.352106Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"cited_work":{"arxiv_id":"2505.20892","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.20892","snapshot_observed_at":"2026-08-06T05:48:59.352106Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","venue":"cs.LG","work_id":"133f3d92-707c-419b-bf04-a68473c93f94","year":2025},"citing_paper":{"arxiv_id":"2508.01219","last_updated":"2025-08-02T06:33:58Z","snapshot_observed_at":"2026-08-16T20:19:07.573738Z","submitted_at":"2025-08-02T06:33:58Z","title":"Eigen Neural Network: Unlocking Generalizable Vision with Eigenbasis","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T05:48:55.160266Z"},"links":{"cited_paper":"/paper/2505.20892","citing_paper":"/paper/2508.01219"},"observation_digest":"sha256:b330ca8f2cef730f1495a3832d74e66b05fa79a5ec24dd22b3dc08c28749cf8c","observation_id":"866f42b4-0982-48ab-8961-c99c88a10a0d","resolution":{"observed_at":"2026-08-06T05:48:59.445309Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.20892/citation-record","integrity":"/paper/2505.20892/integrity","json":"/paper/2505.20892/citation-record.json","paper":"/paper/2505.20892"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:51:16.821394Z","title":"Rumelhart, Geoffrey E","venue":null,"work_id":"7f1b3eb6-a6e5-416b-afcf-73c0fb08d2b3","year":1986},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:02.512350Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:fc9cd998201934a1d2462912ea361d32bcd62c89552df00d0db011f28854d3c0","observation_id":"4cdc23ff-0304-453d-8f37-32e5c0fcaeef","resolution":{"observed_at":"2026-08-07T13:51:16.898917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:02.592168Z","title":"Deep learning","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:02.592168Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:f50b0640f9823fad9813178f128bce823d3387c3b4a1a1cf4eb66839e359563c","observation_id":"1877ade1-7ce5-450f-b542-a9420e904aaf","resolution":{"observed_at":"2026-08-07T13:51:02.592168Z","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":"2026-08-07T13:51:02.708305Z","title":"Imagenet classification with deep convolutional neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:02.708305Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:fb826098d6ac16cc2df32d253540927a3192d70eaaf0883b4f9877c5aa799e2a","observation_id":"4731c814-070d-4f21-9bfe-2dcdf437552e","resolution":{"observed_at":"2026-08-07T13:51:02.708305Z","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":"2026-08-07T13:51:02.763680Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:02.763680Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:49957c1ff4708d9117f0e7e871607d1aa63aedbb4ba6d57af137b67fa5955aa5","observation_id":"2658b7ce-679d-4c34-afe7-153cd6dd92c3","resolution":{"observed_at":"2026-08-07T13:51:02.763680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T13:51:02.859262Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:02.859262Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:63babd0c568f742abcd555d46dfc392ad1c0c2c0bc6d96a1d79c8c9e2d07a209","observation_id":"31fb1bf4-5aea-4bbb-ad07-f18192942140","resolution":{"observed_at":"2026-08-07T13:51:02.859262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-07T13:51:02.954105Z","title":"Gemini: a family of highly capable multimodal models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:02.954105Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:14e7e3542a2caab49d825954f1d95040776c0c4a9070095d3981dc149f0d2c9a","observation_id":"9173ba47-d737-4774-b9ce-e92f09d5b71c","resolution":{"observed_at":"2026-08-07T13:51:02.954105Z","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":"2026-08-07T13:51:16.570349Z","title":"Energy and policy considerations for modern deep learning research","venue":null,"work_id":"905bd11b-de7f-4c6e-a560-ea9254d0b7e4","year":2020},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:03.074440Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:53913bdad9dcd43e2f9ae373426457e2ff90edbee5fe76df94d28b63f7b5eb3f","observation_id":"d653684b-516f-48a9-9fa6-a7a76a114206","resolution":{"observed_at":"2026-08-07T13:51:16.628094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:03.186425Z","title":"Efficient processing of deep neural networks: A tutorial and survey","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:03.186425Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:efe00be5ce970c48591affb4c868a685da0d8ace955f4e9d8378148a564efd8d","observation_id":"eb177090-d3ba-4c7b-9234-5f3254ea756a","resolution":{"observed_at":"2026-08-07T13:51:03.186425Z","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":"2026-08-07T13:51:03.298945Z","title":"Green ai","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:03.298945Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:7c97b079334206b9fd460b02ad3ca4b3f85b25ed0e2e03f68038dc60f843133d","observation_id":"37d62b99-bd52-4855-99f9-d647393a3b42","resolution":{"observed_at":"2026-08-07T13:51:03.298945Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.10350","last_updated":"2021-04-23T14:26:29Z","snapshot_observed_at":"2026-08-16T05:11:57.545339Z","submitted_at":"2021-04-21T04:44:25Z","title":"Carbon Emissions and Large Neural Network Training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.10350","snapshot_observed_at":"2026-08-07T13:51:03.367228Z","title":"Carbon emissions and large neural network training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:03.367228Z"},"links":{"cited_paper":"/paper/2104.10350","citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:fefcf27adf4677079e90f32f782a9c7ac20afd6b7de828f0623623cf4b5dedda","observation_id":"b9b1a589-94c4-474b-94a9-96095fce6d0f","resolution":{"observed_at":"2026-08-07T13:51:03.367228Z","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":"2026-08-07T13:51:16.378789Z","title":"Estimating the carbon footprint of bloom, a 176b parameter language model","venue":null,"work_id":"1f3abb33-d161-4c0b-b8d0-caa9896088d9","year":2023},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:03.444670Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:4e494614c4991382ccab5fcea436cd3965084cccb00f36dd8b283b1505b64cd2","observation_id":"9e68a750-7275-4bf6-b268-5569ed8d926c","resolution":{"observed_at":"2026-08-07T13:51:16.439201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:16.162166Z","title":"Computing’s energy problem (and what we can do about it)","venue":null,"work_id":"70185bbc-b6e0-46ec-8fc8-ff2bd663465e","year":2014},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:03.552521Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:2b14416e34befb24e06b9c3bdbe98cf8ec17ad931a171b4f45b72ae5317102ce","observation_id":"a3f8726e-e29e-411b-abeb-d1a503879685","resolution":{"observed_at":"2026-08-07T13:51:16.289034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:15.947261Z","title":"Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks","venue":null,"work_id":"8c17ea69-b9e9-4073-8ec8-41dca9aebef5","year":2016},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:03.632224Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:4e16946c5f839cd3f732235f549e98bf1d16945e8a9aaac195dcf88745a308a4","observation_id":"2e665849-79f0-4872-a447-d25a4e973ca8","resolution":{"observed_at":"2026-08-07T13:51:16.028206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:03.709006Z","title":"On computable numbers, with an application to the entscheidungsproblem","venue":null,"work_id":null,"year":1936},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:03.709006Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:2cf41ab822ca7e83d21f1a22cda1b2574b64549e0301befcef2a8c3a5037be82","observation_id":"c6eafa6a-776a-40a2-8d7e-3cc16bae5e50","resolution":{"observed_at":"2026-08-07T13:51:03.709006Z","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":"2026-08-07T13:51:15.703147Z","title":"First draft of a report on the edvac","venue":null,"work_id":"b57564f6-8647-476e-a07c-67a797fb1bcb","year":1945},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:03.809617Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:15612d07fdb67b3a8bf7ba164b40243282528dc66c481612b1c42d9b498b032c","observation_id":"fe79038d-ef52-46ed-975e-a09362b89880","resolution":{"observed_at":"2026-08-07T13:51:15.830427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:15.504437Z","title":"Reconstruction and simulation of neocortical microcircuitry","venue":null,"work_id":"63e51f9e-5b70-45b6-ae4d-4cdc1a0d8156","year":2015},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:03.910787Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:eb28e7928f561aa82ac27592aab582afd7bc558080b3c65459ecb0d5b6ee57c2","observation_id":"80e5789f-76fa-4913-b7f8-e2a005a49439","resolution":{"observed_at":"2026-08-07T13:51:15.588966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:03.974487Z","title":"Memory and information processing in neuromorphic systems","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:03.974487Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:035f195e6cd52b80b0160aaef4d318e347614f7a2c62feb139eb82da3b62830e","observation_id":"9ced11e7-7831-4ce5-9bb6-54bd9404fbe6","resolution":{"observed_at":"2026-08-07T13:51:03.974487Z","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":"2026-08-07T13:51:15.228619Z","title":"A million spiking-neuron integrated circuit with a scalable communication network and interface","venue":null,"work_id":"c449848b-727e-46d0-8baf-5a5f172fdfcf","year":2014},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:04.109660Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:1f41cd6cf58ff7220847ef1dd60f861e57960aad5123ff33fa542d3ff0a74b72","observation_id":"5c7e3efc-858d-485c-9484-fa2ab1561c72","resolution":{"observed_at":"2026-08-07T13:51:15.335247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:15.001624Z","title":"Distributed hierarchical processing in the primate cerebral cortex","venue":null,"work_id":"ae3781d6-fc64-4678-81da-212e8a696274","year":1991},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:04.178910Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:9cfe8a054cdc24b3a9b31c4b4cdf6a473cfa78e63a36e7bdc70f6c83415c1477","observation_id":"fc311a1a-3e1d-4b9d-a2f6-298cd0c00d2c","resolution":{"observed_at":"2026-08-07T13:51:15.103440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:14.711379Z","title":"Visual areas exert feedforward and feedback influences through distinct frequency channels","venue":null,"work_id":"d0ce5360-7a28-4a64-842d-19af5b362d90","year":2015},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:04.292255Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:d182bc48861b2f537a6992764e394d56171dd93d4b56c9e754ed8048100f9166","observation_id":"b5f35e97-4fbe-4719-aa84-ec5c27a7fc57","resolution":{"observed_at":"2026-08-07T13:51:14.832200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:14.540695Z","title":"Competitive learning: From interactive activation to adaptive resonance","venue":null,"work_id":"6a118e36-95b0-4213-a3c2-0bb67221b3c0","year":1987},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:04.360140Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:9fa426390f9a470d76c728dd68500f96d835273904c58a16da72918f0def9f67","observation_id":"157dbabf-31a2-452c-94d9-71fe2239ad53","resolution":{"observed_at":"2026-08-07T13:51:14.630503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:14.355035Z","title":"The recent excitement about neural networks","venue":null,"work_id":"b9fd4975-2133-4fbe-b89b-ce990adb6b85","year":1989},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:04.425188Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:204eddfb692d14fedf57b3ef7ee0614c6057319b4144c499ecd056fdc3b2b4ad","observation_id":"0bd270e1-f9cf-4a47-b0ec-02b18b2b3381","resolution":{"observed_at":"2026-08-07T13:51:14.436832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:04.544233Z","title":"Random synaptic feedback weights support error backpropagation for deep learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:04.544233Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:8dfce2c136d62dcc21fa2a9230720a99efcddf3f9fc30d7f617bf5c909d4a15e","observation_id":"02940621-7362-4414-a8a3-00941291eade","resolution":{"observed_at":"2026-08-07T13:51:04.544233Z","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":"2026-08-07T13:51:04.696354Z","title":"Backpropagation and the brain","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:04.696354Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:08ba1986acc48bfd48735c08efa975eb847ca50ad55a502f4d2831eba93a5662","observation_id":"ffa4f27a-d60a-4253-b119-78db5e5e5101","resolution":{"observed_at":"2026-08-07T13:51:04.696354Z","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":"2026-08-07T13:51:14.096593Z","title":"Dendritic solutions to the credit assignment problem","venue":null,"work_id":"d92be100-f42d-475e-8362-d9d0aa487ebd","year":2019},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:04.791566Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:9f85956ca504ef925ac62befc8421eab5496e2da4902db856400c905fd229b13","observation_id":"53049027-8bec-46dd-bf3c-14892a57880b","resolution":{"observed_at":"2026-08-07T13:51:14.226279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:13.958975Z","title":"Assessing the scalability of biologically-motivated deep learning algorithms and architectures","venue":null,"work_id":"caf705af-0084-424f-afae-7ace74b97729","year":2018},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:04.899940Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:214636ecb3f3025bc02bc66781e475d78d778dd9bd3273e51842b13317a379d3","observation_id":"4fd9bff4-0738-4df5-b258-1eb88d9855d4","resolution":{"observed_at":"2026-08-07T13:51:14.008064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:13.716551Z","title":"How important is weight symmetry in backpropagation? In Proceedings of the AAAI Conference on Artificial Intelligence, volume 30, 2016","venue":null,"work_id":"9078b576-6a77-41c1-b166-22a38674f8c2","year":2016},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:04.988441Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:1527968f89f907f6c6b2aa93bbe5dfacd63eac3d37a806eb6155d9156ed5d1d3","observation_id":"032e9104-1293-439c-bfe5-630a800dcc23","resolution":{"observed_at":"2026-08-07T13:51:13.828272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:13.540247Z","title":"Biologically-plausible learning algorithms can scale to large datasets","venue":null,"work_id":"5f7c02fd-9069-4832-b2ea-593be0455ee4","year":2019},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.057729Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:8752db1e9d1fbab4c74fb78922b8817a65f7c472bf58216f72474129b6aa084e","observation_id":"f33d0dd0-e7c2-46ef-9848-bbdf9b204659","resolution":{"observed_at":"2026-08-07T13:51:13.616060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:13.339396Z","title":"An approximation of the error backpropagation algorithm in a predictive coding network with local hebbian synaptic plasticity","venue":null,"work_id":"b36741bb-08db-44b8-b6f7-79d431169a37","year":2017},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.156486Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:0bdcd074950786f5ed06eb08a0c491e3db5eba389678922b76be5fcbe978687b","observation_id":"1d93818a-9dd1-4f5f-ac4a-6b8103602a9a","resolution":{"observed_at":"2026-08-07T13:51:13.418312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:13.232745Z","title":"Inferring neural activity before plasticity as a foundation for learning beyond backpropagation","venue":null,"work_id":"1874e80b-c4c3-4811-9e0f-ce524e8b48d9","year":2024},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.243861Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:79fc0799e43e984d53de6049a246d6e0c428f7ff5158e4364c7aa9cf8de9726e","observation_id":"2c76b77d-7415-4778-97f5-d128c7982046","resolution":{"observed_at":"2026-08-07T13:51:13.277544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:05.331857Z","title":"Equilibrium propagation: Bridging the gap between energy-based models and backpropagation","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.331857Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:ad74d518093b1ccc6a0db524488b0aa5562eb2397b6848c15720b99898d0428c","observation_id":"5ebd1206-5d19-4616-a121-282d6f246fba","resolution":{"observed_at":"2026-08-07T13:51:05.331857Z","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":"2026-08-07T13:51:13.004733Z","title":"Backpropagation without weight transport","venue":null,"work_id":"31a8e767-722d-4b7d-b4be-0dbfa158a71d","year":1994},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.398069Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:c661d3b9f67ef094dc92f8ec9f71f9b4b3d9c63cef7002baea95603f090f4ef6","observation_id":"adee6c2f-b1c0-4fa5-8cd8-259adb4c5fff","resolution":{"observed_at":"2026-08-07T13:51:13.138880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:12.840595Z","title":"Deep learning without weight transport","venue":null,"work_id":"ce9461a3-dd0d-4463-b480-ce637f7f08ee","year":2019},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.457077Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:0edaaa3c5281dc08f1f53a43d4ce4ef73e7818ce08fdf1377c1c581fd869e471","observation_id":"c2be1631-fee5-44ba-9ffb-45e1cb7d9665","resolution":{"observed_at":"2026-08-07T13:51:12.911166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:12.607507Z","title":"Spontaneous impulse activity of rat retinal ganglion cells in prenatal life","venue":null,"work_id":"f3bcf663-76ae-42d2-91cd-f394b5044395","year":1988},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.510459Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:78abf453fd4b732c77c9f4362df7ea418d362f24d3707339e1e5b219f302c6e9","observation_id":"3f472113-de7e-41f6-a547-744879b70743","resolution":{"observed_at":"2026-08-07T13:51:12.763206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:12.473925Z","title":"Retinal waves coordinate patterned activity throughout the developing visual system","venue":null,"work_id":"3cacca95-a333-4952-ab9a-d315a30d70d6","year":2012},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.587734Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:2d2fd3a6d7f3afa96c2ff9337a4afdca5388542fa63078264d76b9dd255ad4aa","observation_id":"59d28d15-4b1a-445d-9bf0-3bb17eccdb02","resolution":{"observed_at":"2026-08-07T13:51:12.528800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:12.263324Z","title":"Prenatal activity from thalamic neurons governs the emergence of functional cortical maps in mice","venue":null,"work_id":"af72a808-1b60-44bb-987c-c92b1f607564","year":2019},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.695899Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:3d0032f97369fb1fe32bcb039f7c4ce0cb0b231ea4a840ddb52f63820137f229","observation_id":"7890b136-7414-41b8-bfe1-31058d844cfa","resolution":{"observed_at":"2026-08-07T13:51:12.401318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:12.128497Z","title":"Spontaneous activity in developing thalamic and cortical sensory networks","venue":null,"work_id":"962aef0e-9d1d-4202-8477-faf64e9c4a3d","year":2021},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.782105Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:183bc650093e73899132f1ff65c1f8e80c552804db3538b4c4ad2831b255be1e","observation_id":"9d351661-0cbb-4c27-a73c-87e8e5c7ddf1","resolution":{"observed_at":"2026-08-07T13:51:12.194070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:11.882166Z","title":"Pretraining with random noise for fast and robust learning without weight transport","venue":null,"work_id":"9aa8d457-b3b9-48de-b20b-43cadbd901d6","year":2024},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.870755Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:e641cb5913ff8a5a431e1f77b32b8b14239034ba8bbff119eb5980924c0bb89f","observation_id":"a69d2e64-cc4a-43bc-8260-e20a7c7f3fa7","resolution":{"observed_at":"2026-08-07T13:51:12.029548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:11.717240Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":"3eaf1eef-b490-4a92-90b3-6e225b1c1861","year":2011},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.931604Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:50d4bd25d320fe173aa3387e3b1e41b39898cfcedcf3b9dddd7bd59bc8031da5","observation_id":"ad53f60c-6ef4-4d9b-9396-f946d2416437","resolution":{"observed_at":"2026-08-07T13:51:11.787747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:05.992626Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:05.992626Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:3983410280ae40ed4e73b887587681ef6d43f7095275ef2a9e08f2dd53ec3554","observation_id":"a940e100-e3c4-4110-9e68-de6f11cf83f8","resolution":{"observed_at":"2026-08-07T13:51:05.992626Z","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":"2026-08-07T13:51:06.052166Z","title":"An analysis of single-layer networks in unsupervised feature learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.052166Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:702f8a743d564c71c8e7e6db47dfcb84729e8ffdac150442b377cc6d9a605c97","observation_id":"adcd6fb7-9c97-48b8-93ba-3aecf5405915","resolution":{"observed_at":"2026-08-07T13:51:06.052166Z","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":"2026-08-07T13:51:06.102090Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.102090Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:d5f643ff0c1fa9c72d91513b7b68a5db37c0b1d1a22d28f6dfbc455237cf0b09","observation_id":"f7935e4d-837c-475f-bb39-dce65d37fe8d","resolution":{"observed_at":"2026-08-07T13:51:06.102090Z","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":"2026-08-07T13:51:06.171119Z","title":"Visualizing the loss landscape of neural nets","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.171119Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:8d79e3998670c42c57fce704d07cb82a33ede81f0efaaca31e783f27ad6acf36","observation_id":"ef8402bf-8333-42f9-b943-9b97e5d1fddc","resolution":{"observed_at":"2026-08-07T13:51:06.171119Z","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":"2026-08-07T13:51:11.456038Z","title":"Pyhessian: Neural networks through the lens of the hessian","venue":null,"work_id":"475f5196-976c-40fc-9d58-2abd5a9690fc","year":2020},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.246922Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:10add035f236c6187f1f30269d08cfdc415c3601f21aa73b17a9cb78da0d890b","observation_id":"eab75dfd-be09-4801-a868-eafa7aa7d342","resolution":{"observed_at":"2026-08-07T13:51:11.543059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:06.333422Z","title":"Flat minima","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.333422Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:a34ba12a8d2c381ae1bc12e7aa789b66785d4d77b4f776fa942586e9ed1e2d88","observation_id":"eb1c90a5-b42d-4653-9917-4a853a268d07","resolution":{"observed_at":"2026-08-07T13:51:06.333422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.04836","last_updated":"2017-02-09T20:38:16Z","snapshot_observed_at":"2026-08-15T20:45:29.277746Z","submitted_at":"2016-09-15T20:03:06Z","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.04836","snapshot_observed_at":"2026-08-07T13:51:06.395087Z","title":"On large-batch training for deep learning: Generalization gap and sharp minima","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.395087Z"},"links":{"cited_paper":"/paper/1609.04836","citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:6bab2922d727e46629f22124ab07a70a0933c03c4f8dbb621d41f350a91439a2","observation_id":"661d5ab0-f1f6-4e82-9ce0-06f9942587dc","resolution":{"observed_at":"2026-08-07T13:51:06.395087Z","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":"2026-08-07T13:51:11.200989Z","title":"Entropy-sgd: Biasing gradient descent into wide valleys","venue":null,"work_id":"c9ac2c6e-39cb-4ffa-9021-d26035801f02","year":2019},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.501534Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:4a81a9b2cdf0c5a7a1a616b47a061e05bfa4970b9904df989ceb0b23296745d8","observation_id":"01aea26e-3a91-4214-9a71-de5ddf58df43","resolution":{"observed_at":"2026-08-07T13:51:11.305286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05407","last_updated":"2019-02-25T14:18:11Z","snapshot_observed_at":"2026-08-14T19:36:09.254749Z","submitted_at":"2018-03-14T17:09:27Z","title":"Averaging Weights Leads to Wider Optima and Better Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05407","snapshot_observed_at":"2026-08-07T13:51:06.579511Z","title":"Averag- ing weights leads to wider optima and better generalization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.579511Z"},"links":{"cited_paper":"/paper/1803.05407","citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:c964323e5f3296bcdedb4d0a6a292effa676ef52d1ae21cc522e9852482cd666","observation_id":"99e2c61d-1e13-409f-8bc5-d902fe2370c2","resolution":{"observed_at":"2026-08-07T13:51:06.579511Z","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":"2026-08-07T13:51:06.649757Z","title":"Sharpness-aware minimization for efficiently improving generalization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.649757Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:15980cfe1cb637f7787130a8445578e8fe47e53fcbfe35b2ea8e26cf0c615c72","observation_id":"d1538452-f6ff-4207-8569-86f75b86d6e6","resolution":{"observed_at":"2026-08-07T13:51:06.649757Z","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":"2026-08-07T13:51:06.735432Z","title":"Benchmarking neural network robustness to common corruptions and perturbations","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.735432Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:5d433d3b122f027ca79b6986771cfedc4289843b3fb7d394be5b62ce979f961b","observation_id":"5be52539-c546-4458-8452-ab159e79db86","resolution":{"observed_at":"2026-08-07T13:51:06.735432Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-19T07:17:20.004918Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-07T13:51:06.806273Z","title":"Explaining and harnessing adversarial examples","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.806273Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:d2aa8893c5f0f53dd73a9c65f76360ecd9d8a0318fe31553870586cb9d52a34d","observation_id":"12525b35-44f8-4219-9982-5752bd9dad6d","resolution":{"observed_at":"2026-08-07T13:51:06.806273Z","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":"2026-08-07T13:51:06.886382Z","title":"Understanding the difficulty of training deep feedforward neural networks","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.886382Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:364a4681c5c957852b426bece6ce6056c7d472894ebb548acccb0df3ac8b1b10","observation_id":"2e1ef1e0-d73b-486d-bddb-212dc5c18209","resolution":{"observed_at":"2026-08-07T13:51:06.886382Z","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":"2026-08-07T13:51:10.915511Z","title":"On the importance of initialization and momentum in deep learning","venue":null,"work_id":"004d4b1f-cd99-4bff-9bfb-a70c264c74b8","year":2013},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:06.938337Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:5a8958758e3d9f7359212dd7994be44f0c95962f94407aee7803e62c88af9f94","observation_id":"4347f922-ffd1-487b-bcb4-6737bf16aeeb","resolution":{"observed_at":"2026-08-07T13:51:11.003019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:07.029435Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.029435Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:9787ddcd3da5e7cf2521b3cb9de85a5941525b6f694f84cd7141ebd80d159f2b","observation_id":"fd7779df-0725-48f2-b6e5-c04a4e5af671","resolution":{"observed_at":"2026-08-07T13:51:07.029435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6120","last_updated":"2014-02-19T17:26:57Z","snapshot_observed_at":"2026-08-14T23:50:45.351114Z","submitted_at":"2013-12-20T20:24:00Z","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6120","snapshot_observed_at":"2026-08-07T13:51:07.099327Z","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.099327Z"},"links":{"cited_paper":"/paper/1312.6120","citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:9d5e41100763037d3c58034d8dab7ad83cbff3443ea5dfe352aa005871693115","observation_id":"81fd28dd-ad42-442b-bd6b-45d56dc0a42e","resolution":{"observed_at":"2026-08-07T13:51:07.099327Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.17411","last_updated":"2025-03-27T12:34:23Z","snapshot_observed_at":"2026-08-15T09:48:07.655818Z","submitted_at":"2024-12-23T09:22:00Z","title":"Pretraining with random noise for uncertainty calibration","version":2},"cited_work":{"arxiv_id":"2412.17411","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.17411","snapshot_observed_at":"2026-08-07T13:51:08.151063Z","title":"Pretraining with random noise for uncertainty calibration","venue":"cs.LG","work_id":"66a89787-ee23-42ac-a0e7-7c51be529942","year":2024},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.172029Z"},"links":{"cited_paper":"/paper/2412.17411","citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:61131dd1b866731fe9d067e24a52c8e203ac2e7dca7e5981a5e47f782dd2f8a2","observation_id":"b07b38bc-549d-4e4f-b71d-b30844909e6d","resolution":{"observed_at":"2026-08-07T13:51:08.245892Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:10.561315Z","title":"Deep physical neural networks trained with backpropagation","venue":null,"work_id":"1cdf6d06-e2a9-41f1-8e9b-2e7f5eafdf42","year":2022},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.265793Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:7626ef8dfbdec702a8cb1202e953624781ce2f982d35f2654795564c5017a44d","observation_id":"84dd8943-faa0-401b-b5f4-19ece2a1b8b2","resolution":{"observed_at":"2026-08-07T13:51:10.748686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:10.184587Z","title":"Backpropagation-free training of deep physical neural networks","venue":null,"work_id":"17871a7f-0342-4046-9a80-f310f741569d","year":2023},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.334924Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:6dfe80df31d68ca97e1c8a70783893be0cb25355c8a667ed5fde01450c752e50","observation_id":"9a906413-fc03-4d16-b267-15cf402471fe","resolution":{"observed_at":"2026-08-07T13:51:10.339278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:07.411993Z","title":"Adversarial examples in the physical world","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.411993Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:ee0d7a9890f874d27169372ab9e44edd29d6d4763991b14c91b01bd5810cb233","observation_id":"8f92d423-87df-4e53-9bf4-cc117eb0bda0","resolution":{"observed_at":"2026-08-07T13:51:07.411993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-07T13:51:07.499050Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.499050Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:bcfe5541a27baf13c6d6fd38d4fb20f0181db9f1328c2c6b648d09e03aa00320","observation_id":"64d2cc96-602d-4971-993a-fdb791da1a9a","resolution":{"observed_at":"2026-08-07T13:51:07.499050Z","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":"2026-08-07T13:51:09.789431Z","title":"Hessian-based analysis of large batch training and robustness to adversaries","venue":null,"work_id":"1b4cb49a-22d7-453f-8bb8-92428dfdee8b","year":2018},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.567004Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:104e4b528a68929cdd59f784d4ca699f16e72417de94d5d6b1f41d886ec76c3b","observation_id":"41b2af7c-ac15-4e01-a4c4-b94090164ec1","resolution":{"observed_at":"2026-08-07T13:51:09.949471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:09.529056Z","title":"Randomized algorithms for estimating the trace of an implicit symmetric positive semi-definite matrix","venue":null,"work_id":"eb8c0988-4a9f-4552-b9d6-38f3f7f4f5a1","year":2011},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.638288Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:7420abdd73e07d832aff34a27c08420d5c594aa40f677cea30cf8beb49063d3b","observation_id":"203c72d8-2034-47e9-8557-d249b8a555be","resolution":{"observed_at":"2026-08-07T13:51:09.658803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:09.301329Z","title":"Calculation of gauss quadrature rules","venue":null,"work_id":"f7a154af-8d63-460e-a66e-558b67270997","year":1969},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.693650Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:7aa07002bcd2c37d98c624999748dc122954b320c8f8d3ee89c2da13e9c2f3d4","observation_id":"9e9d2473-1c7c-4952-ba2e-f3274ce401b0","resolution":{"observed_at":"2026-08-07T13:51:09.397433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:09.152259Z","title":"An investigation into neural net optimization via hessian eigenvalue density","venue":null,"work_id":"ce6fdebb-74b1-48e3-9379-a5f50f7ac8f7","year":2019},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.776509Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:92929796b5fce3d8788ba0f09f05b88d0b0de82b3991ce9e987f1a9ad92014fa","observation_id":"b9ac0437-2c1a-4cdb-8d67-16fe75b30513","resolution":{"observed_at":"2026-08-07T13:51:09.215284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:08.965225Z","title":"Additionally, we investigate several representative conditions to visualize learning curves: large forward weight variance at (24, √","venue":null,"work_id":"17657217-ba67-49fd-941a-fb7ee8a4dc15","year":null},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.852563Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:78af1b08bc640e3c065a71e0ae399b071205e0521ecaae32a7a67c12bd5ca065","observation_id":"2f1fce95-6dd9-427e-be48-305bf30f991a","resolution":{"observed_at":"2026-08-07T13:51:09.061492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:08.788079Z","title":"For each variance condition, learning curves of training accuracy, test accuracy, training loss, and test loss are presented from top to bottom","venue":null,"work_id":"fb3e812f-e57d-4031-a2cb-f84040361c34","year":null},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:07.928036Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:5f45f0c4f41b3828104ceabf24e9435ec01dc970886cbf26f25524c718afc19d","observation_id":"ccbe07e9-8221-4dfe-a12f-626610a66cdf","resolution":{"observed_at":"2026-08-07T13:51:08.893156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-07T13:51:08.527584Z","title":"We also explored a wide range of variances by varying a and b from 10−6 to 100 (smaller variances), and from 20 to 27 (larger variances), using exponential step sizes of 1","venue":null,"work_id":"d01c89e6-6521-4934-8dbb-d0c7cb8c3c61","year":null},"citing_paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:08.024625Z"},"links":{"citing_paper":"/paper/2505.20892"},"observation_digest":"sha256:e36d1db2bd21234b31df521df00f0726609cab62c39412a3ca2c3f6f5cf49f8d","observation_id":"5eb88e35-abe1-4684-a397-c2fca38f1cad","resolution":{"observed_at":"2026-08-07T13:51:08.640374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.20892","last_updated":"2025-05-27T08:34:12Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T20:25:41.906666Z","submitted_at":"2025-05-27T08:34:12Z","title":"One-Time Soft Alignment Enables Resilient Learning without Weight Transport"},"reference_resolution":{"displayed":67,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":28,"verified_exact":1,"verified_fuzzy":38},"total_outbound_references":67},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 1 inbound Pith citation observation for arXiv:2505.20892."}