{"as_of":"2026-08-08T07:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ae3cde70d8aa2d320fe1c0f850d774cdb4318d0d4c5585d2761015db7be9fc41","coverage":[{"denominator":8,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":8,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T06:00:15.484909Z","state":"measured"},{"denominator":8,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":8,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2602.00827/citation-record","integrity":"/paper/2602.00827/integrity","json":"/paper/2602.00827/citation-record.json","paper":"/paper/2602.00827"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T06:00:15.170988Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.00827","last_updated":"2026-05-26T05:46:26Z","snapshot_observed_at":"2026-08-07T15:40:46.008866Z","submitted_at":"2026-01-31T17:43:02Z","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T06:00:15.170988Z"},"links":{"citing_paper":"/paper/2602.00827"},"observation_digest":"sha256:ad1580333004fe3845a597cac6c4689f175f02e28c720381d0d67127ed7a2c9c","observation_id":"1eabee19-7a0e-400e-a354-3d2bfa6eeeaa","resolution":{"observed_at":"2026-08-03T06:00:15.170988Z","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":"2026-08-03T06:00:15.306784Z","title":"(2024, Appendix D.2), andβ:= (λx min)2/(32xmax)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.00827","last_updated":"2026-05-26T05:46:26Z","snapshot_observed_at":"2026-08-07T15:40:46.008866Z","submitted_at":"2026-01-31T17:43:02Z","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T06:00:15.306784Z"},"links":{"citing_paper":"/paper/2602.00827"},"observation_digest":"sha256:5b7802b193d679102cfc8b4e07c0dbb7bf0b725699449ed6a22c7ec2b96d9d6d","observation_id":"41830fe2-f680-421c-92e5-ccb2742dc407","resolution":{"observed_at":"2026-08-03T06:00:15.306784Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.01562","last_updated":"2025-06-02T11:38:10Z","snapshot_observed_at":"2026-08-07T11:36:03.615544Z","submitted_at":"2025-06-02T11:38:10Z","title":"Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.01562","snapshot_observed_at":"2026-08-03T06:00:14.874974Z","title":"S., Lucchi, A., Pascanu, R., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.00827","last_updated":"2026-05-26T05:46:26Z","snapshot_observed_at":"2026-08-07T15:40:46.008866Z","submitted_at":"2026-01-31T17:43:02Z","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T06:00:14.874974Z"},"links":{"cited_paper":"/paper/2506.01562","citing_paper":"/paper/2602.00827"},"observation_digest":"sha256:bac82d324a02527c5b57e06bdb415416864ae75fff194fb3feb233d22833772f","observation_id":"7eb00b84-6ccc-4e33-91f7-944b3fd7f28d","resolution":{"observed_at":"2026-08-03T06:00:14.874974Z","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":"2026-08-03T06:00:15.066357Z","title":"U-shape,","venue":null,"work_id":null,"year":2063},"citing_paper":{"arxiv_id":"2602.00827","last_updated":"2026-05-26T05:46:26Z","snapshot_observed_at":"2026-08-07T15:40:46.008866Z","submitted_at":"2026-01-31T17:43:02Z","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T06:00:15.066357Z"},"links":{"citing_paper":"/paper/2602.00827"},"observation_digest":"sha256:9ead463b342826442d625eac878f26b6f59498d62f8d2976756816f3afbf300b","observation_id":"60233ebf-fd6a-4d52-88b8-e0fb2b91695e","resolution":{"observed_at":"2026-08-03T06:00:15.066357Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-03T06:00:15.430895Z","title":"(2022).)sign(v j(t)) = sign(vj(0))","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.00827","last_updated":"2026-05-26T05:46:26Z","snapshot_observed_at":"2026-08-07T15:40:46.008866Z","submitted_at":"2026-01-31T17:43:02Z","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T06:00:15.430895Z"},"links":{"citing_paper":"/paper/2602.00827"},"observation_digest":"sha256:96e8ca5aaefb91e7354743e3012cc1b5184cec5f4417a7972b40cf2d483627c0","observation_id":"deeba83c-85ff-4928-a338-afd306d7099d","resolution":{"observed_at":"2026-08-03T06:00:15.430895Z","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":"2026-08-03T06:00:15.484909Z","title":"AUXILIARYLEMMATA Before start, we define Π∥ to be a orthogonal projection onto s and Π⊥ to be the orthogonal projection onto its complement","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2602.00827","last_updated":"2026-05-26T05:46:26Z","snapshot_observed_at":"2026-08-07T15:40:46.008866Z","submitted_at":"2026-01-31T17:43:02Z","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T06:00:15.484909Z"},"links":{"citing_paper":"/paper/2602.00827"},"observation_digest":"sha256:2306151cf65e65b469771e550a6a43f84345d9a5b4adacf5029bf60a7484e98a","observation_id":"c1886f39-d632-465e-b98b-08042dcdd6bd","resolution":{"observed_at":"2026-08-03T06:00:15.484909Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.15933","last_updated":"2022-01-31T12:58:39Z","snapshot_observed_at":"2026-08-07T15:39:56.731144Z","submitted_at":"2021-06-30T09:34:05Z","title":"Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.15933","snapshot_observed_at":"2026-08-03T06:00:14.652992Z","title":"Saddle-to-saddle dynamics in deep linear networks: Small initialization training, symmetry, and sparsity.arXiv preprint arXiv:2106.15933,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.00827","last_updated":"2026-05-26T05:46:26Z","snapshot_observed_at":"2026-08-07T15:40:46.008866Z","submitted_at":"2026-01-31T17:43:02Z","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-03T06:00:14.652992Z"},"links":{"cited_paper":"/paper/2106.15933","citing_paper":"/paper/2602.00827"},"observation_digest":"sha256:4c8aed3af56ff6a4953abbcf69fbdaed3747d81c13e732910ce3ffc3a88dd346","observation_id":"586fda19-a8a8-40da-b22c-a0822fc908b7","resolution":{"observed_at":"2026-08-03T06:00:14.652992Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.08367","last_updated":"2018-03-22T14:08:58Z","snapshot_observed_at":"2026-07-06T06:29:40.070023Z","submitted_at":"2018-03-22T14:08:58Z","title":"Gradient Descent Quantizes ReLU Network Features","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.08367","snapshot_observed_at":"2026-08-03T06:00:14.707112Z","title":"Gradient de- scent quantizes relu network features.arXiv preprint arXiv:1803.08367,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.00827","last_updated":"2026-05-26T05:46:26Z","snapshot_observed_at":"2026-08-07T15:40:46.008866Z","submitted_at":"2026-01-31T17:43:02Z","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-03T06:00:14.707112Z"},"links":{"cited_paper":"/paper/1803.08367","citing_paper":"/paper/2602.00827"},"observation_digest":"sha256:a15915a8c7c7f37986b8ac245708fdb4a600221365df26ae9ba7dbf95bc1d730","observation_id":"c268e8d9-313c-417a-bb82-179ea1854510","resolution":{"observed_at":"2026-08-03T06:00:14.707112Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2602.00827","last_updated":"2026-05-26T05:46:26Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T15:40:46.008866Z","submitted_at":"2026-01-31T17:43:02Z","title":"Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization"},"reference_resolution":{"displayed":8,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":8},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 8 of 8 outbound references and 0 inbound Pith citation observations for arXiv:2602.00827."}