{"as_of":"2026-08-09T08:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:df996e76c449d801f43a05588791864829525a1e40c2a39ea3515c5b213a27b7","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T07:34:30.802855Z","state":"measured"},{"denominator":25,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":25,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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":"2026-06-28T07:34:30.802855Z","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":"2026-07-02T06:06:41.570593Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"cited_work":{"arxiv_id":"2606.04583","doi":null,"metadata_source":"pith","pith_arxiv_id":"2606.04583","snapshot_observed_at":"2026-07-02T06:06:41.570593Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","venue":"cs.LG","work_id":"26c8f3e3-9586-4563-8c7d-08f8cefcb5f0","year":2026},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"cited_paper":"/paper/2606.04583","citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:48abc99b3bf5da8c7c4b89fbf4bf33d2e2305718f8fc770369f74c0b4cfea5a2","observation_id":"75b3c28b-0c97-4b99-aac7-af4ca3bc34b5","resolution":{"observed_at":"2026-07-02T06:06:41.571805Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2606.04583/citation-record","integrity":"/paper/2606.04583/integrity","json":"/paper/2606.04583/citation-record.json","paper":"/paper/2606.04583"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T07:34:30.802855Z","title":"This leads to a simpler model and a simpler optimization problem","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:28772b790e368357376eb31f3e92740380126f6899d6b86c767fca828782a7ea","observation_id":"a136a387-0387-4576-8d8b-525db3f82742","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:962881822241af680c6f6a42406cabfb6629179696b0c1715600ad984482179e","observation_id":"633fa8dd-3518-40a9-ba52-2526d741c680","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:fca8cdddac3be02e35486d13917a3ce6db57b73375de31dca4596a243107172c","observation_id":"728c8859-d37a-490c-971c-2ece4e1ddb05","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:3a765336404335b7d764e7806a6c7f11a8be806f4cc6f6754c80d4f6ddf4da29","observation_id":"84a25787-445b-44a9-9345-94291f6504ba","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"This paper is organized as follows: We present our model in Section 2 and our experimental results on MNIST in Sec- tion 3","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:d96267329892d2db3803057eee5955a11255eea2e73e559ead9bacaaf775fe88","observation_id":"280ad27f-b404-4fe3-a59a-36ea2b1228d7","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"cited_work":{"arxiv_id":"2606.04583","doi":null,"metadata_source":"pith","pith_arxiv_id":"2606.04583","snapshot_observed_at":"2026-07-02T06:06:41.570593Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","venue":"cs.LG","work_id":"26c8f3e3-9586-4563-8c7d-08f8cefcb5f0","year":2026},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"cited_paper":"/paper/2606.04583","citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:48abc99b3bf5da8c7c4b89fbf4bf33d2e2305718f8fc770369f74c0b4cfea5a2","observation_id":"75b3c28b-0c97-4b99-aac7-af4ca3bc34b5","resolution":{"observed_at":"2026-07-02T06:06:41.571805Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-28T07:34:30.802855Z","title":"We use ReLU as the activation function at the hidden units and softmax at the output; training is done to minimize the cross-entropy using Adam","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:bd8e66f35126ce0e18f3fb3dd01e12bb6650680124b46c56e1d0ebeb9dd02f57","observation_id":"b4824e2f-694a-4e9b-a146-ca0af319638b","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"We can generate binary hyperplanes by placing the sign function after Equation 3","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:99a12343c783e387d2fea1e1acc1d18e5eeb6f3b50bac8bd0cbc353602c4b50c","observation_id":"8c91ec14-36e2-4c16-945a-fd6c64d5988d","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"CIFAR-10 consists of 60,000 color images of size32×32belonging to ten classes, with 50,000 training and 10,000 test instances","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:444e2a4a98511a98aa90094a77dd166ee37feb4eafa75855c72a150c27463404","observation_id":"bd528f8f-cf18-4179-a8b6-26a302f8d082","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"Empirical and theoretical stud- ies have shown that deep networks often learn representa- tions that are effectively low-dimensional [7, 8]","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:d8ff0a1e8bff9ec41dd984e749a898764bd64fddb5313fccc08780149725e666","observation_id":"ba99c224-9194-4eca-8c9b-74a5b71ed41d","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"The rank of the co- variance factor provides a direct control over model capacity, yielding a smooth trade-off between fixed random features and fully trainable neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:8b007055071b908ffbfdf59cf41246941cf1888e0c3210e80bc9de82e7abde3f","observation_id":"733797aa-f788-4cff-b18f-1271773268e9","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"Random features for large- scale kernel machines,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:058443674fd44b9ffaa105fb8c06ba6fef74f440ddbaa99e8085bf0ecb245b8f","observation_id":"1949b9b6-1162-4629-b0f6-c632527dd4a2","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"Extreme learning machine for regression and multiclass classifi- cation,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:7bae95fab8d03998f3856b05156f3443bc6d0bbbe5e79be00497bac03dd0551b","observation_id":"08e4efd5-0a15-4546-95c7-c5ed4fb0f16d","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"A review on neural networks with random weights,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:6dd455dd15914c507200a7417ac63723a56ca6457df6feb5970f0da54e0735f3","observation_id":"cc7a7057-c686-4a34-bbfb-717113e05083","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"Randomness in neural net- works: An overview,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:3d02832caaf6b64ec252efdaf29d293dd7d8ca200f4b6a8db4b53066a0d2c285","observation_id":"f9039579-1295-4358-8302-067a98c6123b","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"Deep randomized neural networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:8143c76961a577633aee1fc20fe2c1ed048be05cdecf8cf84060b749b509091f","observation_id":"f5232e9d-c0cd-4146-bc40-ffa9debf7fe6","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.04352","last_updated":"2025-06-04T18:11:49Z","snapshot_observed_at":"2026-08-07T10:41:47.902134Z","submitted_at":"2025-06-04T18:11:49Z","title":"Half-Layered Neural Networks","version":1},"cited_work":{"arxiv_id":"2506.04352","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.04352","snapshot_observed_at":"2026-07-02T06:06:41.573069Z","title":"Half-layered neural networks,","venue":null,"work_id":"ab4ad547-f94a-4901-8b1d-19ebe822ebb2","year":2025},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"cited_paper":"/paper/2506.04352","citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:4658dcfe9bde4164437aa6db97b20712fe3f24ed8cb1036ebf7808daf20ffa96","observation_id":"91e46d0f-9fa6-46e8-951b-b358cfa4ceac","resolution":{"observed_at":"2026-07-02T06:06:41.574378Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-28T07:34:30.802855Z","title":"The low-rank simplicity bias in deep networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:0016f2ee9c845143b10af9316397e77c051aa913e0ba8a6ea9110cda97862013","observation_id":"c7e7a2be-6825-4280-b3b9-ca294e05303b","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"Toward moderate overparameterization: Global convergence guarantees for training shallow neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:0aaf7f76725d5f0be8912c6227a74c623a21c23bb0b4a4f9fa5cdc891f8258cb","observation_id":"8d1e2d33-e42e-47de-9e0f-e90a41962d0b","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"Pre- dicting parameters in deep learning,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:cd4bd636d504b7c20808f555302447983264ff389d085616a33ee8c20c47e9a8","observation_id":"7ff2e391-ef7a-48dc-930b-d5bf3cd57728","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"Speeding up convolutional neural networks with low rank expansions,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:12f08482cd0434519584b7c1076129f94d3b4b667057f8ac8e9ce0f9a8976623","observation_id":"9171a0a1-cf6b-469c-b9e9-e0140440cbe1","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"Sharp analysis of low-rank kernel ma- trix approximations,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:8ecb9991b3a90d0246fa21906cbae51e02915e16a0e120a6287cef413ff4df9a","observation_id":"928a648b-80a7-4873-af92-e6fd5fcece6d","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"Neal,Bayesian Learning for Neural Net- works, Springer, 1996","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:85412c6e6367f23b26525f641b736c2180172d696869b1594b264d70eed977aa","observation_id":"675e3114-3294-441b-92f8-06633fb0ae89","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","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":"2026-06-28T07:34:30.802855Z","title":"Deep neural networks as gaus- sian processes,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-28T07:34:30.802855Z"},"links":{"citing_paper":"/paper/2606.04583"},"observation_digest":"sha256:0623d67c4b212cb4d69133db5ab953861c9f00c5387dd4953dd7fdbe5cb56e3d","observation_id":"1c600211-9abb-4518-aff4-0a95bafbeb7c","resolution":{"observed_at":"2026-06-28T07:34:30.802855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.04583","last_updated":"2026-06-03T08:19:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T23:44:42.700120Z","submitted_at":"2026-06-03T08:19:00Z","title":"HalfNet: Randomized Neural Networks with Learned Subspace Geometry"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":24},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 1 inbound Pith citation observation for arXiv:2606.04583."}