{"as_of":"2026-08-14T01:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0928d1a880883ea297156df5b3aecf09742ab4e6e14ddf1b4da877fc5b1b5300","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T15:38:34.441081Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T13:48:20.879054Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.05271","last_updated":"2024-11-17T22:18:40Z","snapshot_observed_at":"2026-08-13T04:23:52.399591Z","submitted_at":"2024-02-07T21:31:53Z","title":"Feature learning as alignment: a structural property of gradient descent in non-linear neural networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.05271","snapshot_observed_at":"2026-08-12T15:38:34.441081Z","title":"Gradient descent induces alignment between weights and the empirical NTK for deep non -linear networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.14079","last_updated":"2024-11-21T12:43:49Z","snapshot_observed_at":"2026-08-13T16:52:05.494762Z","submitted_at":"2024-11-21T12:43:49Z","title":"Interpretable QSPR Modeling using Recursive Feature Machines and Multi-scale Fingerprints","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T15:38:34.441081Z"},"links":{"cited_paper":"/paper/2402.05271","citing_paper":"/paper/2411.14079"},"observation_digest":"sha256:80459fdd267960d516c2cad670ac7f32c588d17d84204a2d866175500644ed3c","observation_id":"e4fa0e72-4b6f-4b37-a507-625a11d27374","resolution":{"observed_at":"2026-08-12T15:38:34.441081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.05271","last_updated":"2024-11-17T22:18:40Z","snapshot_observed_at":"2026-08-13T04:23:52.399591Z","submitted_at":"2024-02-07T21:31:53Z","title":"Feature learning as alignment: a structural property of gradient descent in non-linear neural networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.05271","snapshot_observed_at":"2026-08-05T20:29:37.635294Z","title":"Feature learning as alignment: a structural prop- erty of gradient descent in non-linear neural networks, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.10490","last_updated":"2025-08-14T09:49:07Z","snapshot_observed_at":"2026-08-08T15:31:03.421956Z","submitted_at":"2025-08-14T09:49:07Z","title":"On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T20:29:37.635294Z"},"links":{"cited_paper":"/paper/2402.05271","citing_paper":"/paper/2508.10490"},"observation_digest":"sha256:4072115b295150706943e46cdd750457c1fb5bad69e0bbfad06cf0e2c3c59411","observation_id":"e52ca1e5-c03b-4f84-b573-d5c1b4b75ee1","resolution":{"observed_at":"2026-08-05T20:29:37.635294Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.05271","last_updated":"2024-11-17T22:18:40Z","snapshot_observed_at":"2026-08-13T04:23:52.399591Z","submitted_at":"2024-02-07T21:31:53Z","title":"Feature learning as alignment: a structural property of gradient descent in non-linear neural networks","version":4},"cited_work":{"arxiv_id":"2402.05271","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.05271","snapshot_observed_at":"2026-07-03T13:48:20.879054Z","title":"Feature learning as align- ment: a structural property of gradient descent in non-linear neural networks","venue":null,"work_id":"82809ee2-2b21-4e99-9fd4-112126138c09","year":2024},"citing_paper":{"arxiv_id":"2605.04971","last_updated":"2026-05-06T14:27:18Z","snapshot_observed_at":"2026-08-11T15:46:43.995483Z","submitted_at":"2026-05-06T14:27:18Z","title":"Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-08T17:21:23.468992Z"},"links":{"cited_paper":"/paper/2402.05271","citing_paper":"/paper/2605.04971"},"observation_digest":"sha256:238772cc4d60e9d4ef80b380e52d482fa439330b088d768a2625558e868dd172","observation_id":"95ae1458-79f2-43d5-8129-c599dddfea0c","resolution":{"observed_at":"2026-05-11T17:41:06.404804Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.05271","last_updated":"2024-11-17T22:18:40Z","snapshot_observed_at":"2026-08-13T04:23:52.399591Z","submitted_at":"2024-02-07T21:31:53Z","title":"Feature learning as alignment: a structural property of gradient descent in non-linear neural networks","version":4},"cited_work":{"arxiv_id":"2402.05271","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.05271","snapshot_observed_at":"2026-07-03T13:48:20.879054Z","title":"Feature learning as align- ment: a structural property of gradient descent in non-linear neural networks","venue":null,"work_id":"82809ee2-2b21-4e99-9fd4-112126138c09","year":2024},"citing_paper":{"arxiv_id":"2606.19367","last_updated":"2026-06-11T03:50:14Z","snapshot_observed_at":"2026-08-11T02:59:37.659416Z","submitted_at":"2026-06-11T03:50:14Z","title":"Weibull Weight-Scale Parameter Evolution under AdamW Training Dynamics","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-06-27T07:34:04.456453Z"},"links":{"cited_paper":"/paper/2402.05271","citing_paper":"/paper/2606.19367"},"observation_digest":"sha256:0d13e415dbd163f0647c11e5f5afbf9602888fb4f86e662e0c6a6785d91a09ae","observation_id":"f48a2322-9c67-480a-9bd6-cc115d890e1a","resolution":{"observed_at":"2026-07-03T13:48:20.880534Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.05271/citation-record","integrity":"/paper/2402.05271/integrity","json":"/paper/2402.05271/citation-record.json","paper":"/paper/2402.05271"},"outbound":[],"paper":{"arxiv_id":"2402.05271","last_updated":"2024-11-17T22:18:40Z","latest_version":4,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-13T04:23:52.399591Z","submitted_at":"2024-02-07T21:31:53Z","title":"Feature learning as alignment: a structural property of gradient descent in non-linear neural networks"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2402.05271."}