{"as_of":"2026-08-08T09:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b8321ed3e696be768d6d6b6c29e74583df0f1bf2fb7abc52c1856d7e32762db3","coverage":[{"denominator":74,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":74,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T06:00:51.972799Z","state":"measured"},{"denominator":75,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":75,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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":"2026-08-05T18:12:34.296158Z","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":"2026-08-05T18:12:37.393299Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"cited_work":{"arxiv_id":"2506.06280","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.06280","snapshot_observed_at":"2026-08-05T18:12:37.393299Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","venue":"cs.LG","work_id":"3ff35488-c8f5-4a2d-9994-82722d3ea256","year":2025},"citing_paper":{"arxiv_id":"2508.15068","last_updated":"2025-08-20T21:08:29Z","snapshot_observed_at":"2026-08-07T05:02:51.529077Z","submitted_at":"2025-08-20T21:08:29Z","title":"S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-05T18:12:34.296158Z"},"links":{"cited_paper":"/paper/2506.06280","citing_paper":"/paper/2508.15068"},"observation_digest":"sha256:fc8777d435f27798945f5eadf45acc1807ce5c910151b837a34bcdae277c36d2","observation_id":"4f7a8ce7-cf02-445f-9d95-afe313e114ac","resolution":{"observed_at":"2026-08-05T18:12:37.398888Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.06280/citation-record","integrity":"/paper/2506.06280/integrity","json":"/paper/2506.06280/citation-record.json","paper":"/paper/2506.06280"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:53.017801Z","title":"The neural tangent kernel in high dimensions: Triple descent and a multi-scale theory of generalization","venue":null,"work_id":"e2eb7122-5ee5-4ec0-ab72-7e150caee985","year":2020},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.697796Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:ff244537afcaeab22beba7d172ef94c8fac1853e2a61dfc55178377808af5a19","observation_id":"732be365-4dff-4add-b42d-9882b4c2aa93","resolution":{"observed_at":"2026-08-07T06:00:53.022161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:53.004674Z","title":"powerlaw: a python package for analysis of heavy-tailed distributions","venue":null,"work_id":"448598ad-f3d8-401a-841f-674fce901229","year":2014},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.702376Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:7c9983cd12f02ad320a529f388cb89912c9a59c4780836c2353152b568c6ae6b","observation_id":"5b588b8a-d488-43f3-81ba-2ffe372a377b","resolution":{"observed_at":"2026-08-07T06:00:53.008834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.991638Z","title":"High-dimensional asymptotics of feature learning: How one gradient step improves the representation","venue":null,"work_id":"5f9ae7a4-421c-44b7-bf50-2d13225bbd1a","year":2022},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.706087Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:82242be30ad20b2cc060f5e17d96dd43fdcb8c0aab34c4a2c834df8ef3a50731","observation_id":"4233dee0-345f-4edf-b194-10c49200eb12","resolution":{"observed_at":"2026-08-07T06:00:52.995793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.979223Z","title":"Spectral analysis of large dimensional random matrices, volume 20","venue":null,"work_id":"b1226fde-5c4e-4c8c-9b6c-3d8f1a1a7a16","year":2010},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.709820Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:7cea32efe5c96d69ef8f2b1afed04c81b8a15d63c6eeac6bc4e22734a569f381","observation_id":"d2b71af2-15fa-4273-bf6a-c0b305124183","resolution":{"observed_at":"2026-08-07T06:00:52.983220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.11535","last_updated":"2021-03-16T00:59:19Z","snapshot_observed_at":"2026-07-06T10:43:49.435725Z","submitted_at":"2021-02-23T07:50:44Z","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.11535","snapshot_observed_at":"2026-08-07T06:00:51.713432Z","title":"Neural architecture search on imagenet in four gpu hours: A theoretically inspired perspective","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.713432Z"},"links":{"cited_paper":"/paper/2102.11535","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:ff808f7ad917db83933a6423da7d9ac4221e8cac4bea8948ea8091eba93f0b89","observation_id":"079aa85f-37d3-42bc-9805-d65cb46ea714","resolution":{"observed_at":"2026-08-07T06:00:51.713432Z","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":"2026-08-07T06:00:52.966551Z","title":"Policy learning from tutorial books via understanding, rehearsing and introspecting","venue":null,"work_id":"68236638-b58a-4743-9952-643da4a72cd9","year":2024},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.717469Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:dc238b6096212b8be316565625433b42f39e8904cda17ce1145a697763355a32","observation_id":"f8a57f33-5050-4002-a3cc-a5801f2450ed","resolution":{"observed_at":"2026-08-07T06:00:52.970709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.10044","last_updated":"2019-05-24T05:48:49Z","snapshot_observed_at":"2026-07-06T07:55:12.121264Z","submitted_at":"2019-05-24T05:48:49Z","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.10044","snapshot_observed_at":"2026-08-07T06:00:51.721613Z","title":"Boolq: Exploring the surprising difficulty of natural yes/no questions","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.721613Z"},"links":{"cited_paper":"/paper/1905.10044","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:9d62fa5b418e9f9c62b1e6171b3665cc9b2be7ae2658e6b268c62f8b50f45e8b","observation_id":"4c1a2e59-b3a3-4706-97d9-24f7df74bdcf","resolution":{"observed_at":"2026-08-07T06:00:51.721613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05457","last_updated":"2018-03-14T18:04:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2018-03-14T18:04:21Z","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05457","snapshot_observed_at":"2026-08-07T06:00:51.725336Z","title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.725336Z"},"links":{"cited_paper":"/paper/1803.05457","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:985279438a9c04a7b8db51d50f3d610abc98859dfa9ebb2add8780a5cd161ad7","observation_id":"cd9ffd53-d7fd-4819-b0e1-7d813db58903","resolution":{"observed_at":"2026-08-07T06:00:51.725336Z","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":"2026-08-07T06:00:51.729073Z","title":"Power-law distributions in empirical data","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.729073Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:ba98f774fcbd6ccf58aed8ea77a6a018d9c48a32a53f8755265e7e9d3714e71b","observation_id":"57227f9d-6a41-4752-b620-55096ec2bce5","resolution":{"observed_at":"2026-08-07T06:00:51.729073Z","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":"2026-08-07T06:00:52.945414Z","title":"Random Matrix Methods for Machine Learning","venue":null,"work_id":"2ae6f86f-5fac-4fc8-8692-286b567ccbe1","year":2022},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.732669Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:f58d08c98af64617efe93ae2b804b59e334fce5a001a5f389471d7199d70b3d6","observation_id":"36517b75-37e1-4bbd-925c-c0bad721a8d5","resolution":{"observed_at":"2026-08-07T06:00:52.949433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.932406Z","title":"Exact expressions for double descent and implicit regularization via surrogate random design","venue":null,"work_id":"d29ca794-b03b-4abd-84aa-7ae71b610472","year":2020},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.736091Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:a9d05d0bc3d1a33676f7fd7b5f494a82900370afd5ec7b008083443bdde6e4ba","observation_id":"139422d4-0e27-4663-9c77-066691da0a59","resolution":{"observed_at":"2026-08-07T06:00:52.936927Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.919721Z","title":"High-dimensional asymptotics of prediction: Ridge regression and classification","venue":null,"work_id":"52109ce1-23ec-4169-9ca1-33225b59c3bc","year":2018},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.739518Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:7f62249ef6a4aeee090fe38c4aad5c93d5555b186ace21a32cc1779f974d4666","observation_id":"b842158a-6bde-47b9-8cd3-2d033c7022a5","resolution":{"observed_at":"2026-08-07T06:00:52.923709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.07457","last_updated":"2018-11-19T02:06:09Z","snapshot_observed_at":"2026-07-06T07:15:30.564175Z","submitted_at":"2018-11-19T02:06:09Z","title":"Generalizable Adversarial Training via Spectral Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.07457","snapshot_observed_at":"2026-08-07T06:00:51.742816Z","title":"Generalizable adversarial training via spectral normalization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.742816Z"},"links":{"cited_paper":"/paper/1811.07457","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:b307c3b0244d434c6bd250fe96cd429898ed41ed5f7833e08a868fd9bd8c03ce","observation_id":"aaa82bb2-317c-4990-a6b0-dc45bc686ff6","resolution":{"observed_at":"2026-08-07T06:00:51.742816Z","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":"2026-08-07T06:00:52.907451Z","title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","venue":null,"work_id":"1b564e4b-d703-429a-a933-0c453a8bbf30","year":2023},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.746431Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:3ae4a5f3361ef1ba2fe0dc0de9e39e9f6ad9503a6fa8d2615cb849d00bf5afc3","observation_id":"c8a3653e-7d44-4211-835d-4868a2301122","resolution":{"observed_at":"2026-08-07T06:00:52.911350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:51.749774Z","title":"A framework for few-shot language model evaluation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.749774Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:77d499a827a2e276187cbca5d8d97c910395567f802de99566d39ae6e3fbe23a","observation_id":"516cb8c4-ef5f-40fa-a83d-dba3a8275186","resolution":{"observed_at":"2026-08-07T06:00:51.749774Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T06:00:51.753149Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.753149Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:bf41d59367c6dffb077056223496ef6464494ed12aa32b6cc79b834354b3c08b","observation_id":"5cc94017-8631-4d1d-810c-50bfb72c55d5","resolution":{"observed_at":"2026-08-07T06:00:51.753149Z","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":"2026-08-07T06:00:51.756863Z","title":"Weidenmüller","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.756863Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:2cdeb237b0b0273c46f6ee4c4de4ba052b7fde6b4640be1e3a281f6b91b8036f","observation_id":"be6a616a-fca2-4fbe-9141-285b976a2f4d","resolution":{"observed_at":"2026-08-07T06:00:51.756863Z","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":"2026-08-07T06:00:51.760473Z","title":"The heavy-tail phenomenon in sgd","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.760473Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:595ea8d907bde79f0c12a20c3643dcc5cd764d58e93e078da6fd66fc666e6c68","observation_id":"5f29d374-3906-4217-92b8-7cf47a2434b4","resolution":{"observed_at":"2026-08-07T06:00:51.760473Z","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":"2026-08-07T06:00:52.877688Z","title":"Learning both weights and connections for efficient neural network","venue":null,"work_id":"cedd97f5-3bda-42cc-a4fa-1fbdcd07b3fc","year":2015},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.763798Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:eac8e8508798f02c51ffaaa6637f10bcd764c9bc769c65373031f6676de447c6","observation_id":"b5f5e7f4-d5ae-4c49-900c-91b7367f2379","resolution":{"observed_at":"2026-08-07T06:00:52.882249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03542","last_updated":"2024-05-07T01:57:00Z","snapshot_observed_at":"2026-07-06T17:40:20.922598Z","submitted_at":"2024-03-06T08:38:34Z","title":"DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03542","snapshot_observed_at":"2026-08-07T06:00:51.767501Z","title":"Dpot: Auto-regressive denoising operator transformer for large-scale pde pre-training","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.767501Z"},"links":{"cited_paper":"/paper/2403.03542","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:d17747c9d4e24e0c275234bfe4473516df8c6e6e4e3223061e15dd0c78a50c6c","observation_id":"c793f809-80b1-4c22-8434-65beb61ac277","resolution":{"observed_at":"2026-08-07T06:00:51.767501Z","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":"2026-08-07T06:00:52.864751Z","title":"Surprises in high-dimensional ridgeless least squares interpolation","venue":null,"work_id":"552c7924-e374-4cfc-8d52-b0cf10840c11","year":2022},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.771183Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:c7eb7c13b7ec64f1db38539521ef4ac4bf98268ca77176c8515a078a1192175a","observation_id":"00bb0077-7dc3-4947-ae3b-6fa3c6953f3a","resolution":{"observed_at":"2026-08-07T06:00:52.868940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.851370Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","venue":null,"work_id":"bbd2ad3d-bac8-4bef-8536-6bffbdd1dbba","year":2015},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.774488Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:6b78a84c1fe0ba138db6219606de5354641a6b67bd59c55f6d67b1a841f33a2f","observation_id":"199ef913-5abb-4be3-a64a-ba70b326263b","resolution":{"observed_at":"2026-08-07T06:00:52.855730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:51.778001Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.778001Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:983dcf981c6e7b2fa318ed97c89a39fa51958e596a6db1ea905a2d7535a2c411","observation_id":"ff2bf95b-9f60-47c0-8bbe-4d55ad69f60a","resolution":{"observed_at":"2026-08-07T06:00:51.778001Z","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":"2026-08-07T06:00:52.829881Z","title":"A simple general approach to inference about the tail of a distribution","venue":null,"work_id":"83e8a040-2cdd-416d-9b14-06bbcf3c038d","year":1975},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.781338Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:1683098dc6fe0210f8c57595be2ebe44a446afd3cbe32456f0cdd652031b3a50","observation_id":"9beb227d-8103-442c-b5da-45de1b9d0955","resolution":{"observed_at":"2026-08-07T06:00:52.834148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.817301Z","title":"Multiplicative noise and heavy tails in stochastic optimization","venue":null,"work_id":"ad5d9f26-281a-42a7-9137-a5816048ea70","year":2021},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.784739Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:15778f685f210d109cd0a339c4f50a1e00e94e0d37e42b95d76bae2c7b34eda0","observation_id":"2a5f182c-16d6-4f17-9a83-ac3d183faab2","resolution":{"observed_at":"2026-08-07T06:00:52.821406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.804478Z","title":"Generalization bounds using lower tail exponents in stochastic optimizers","venue":null,"work_id":"757b9c75-45a9-4b85-b51f-df6c7b4a2b21","year":2022},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.788186Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:cf17925c4957ee3d550b79f7db8894788d3ad986bd528163bd8e67a28ceb69ec","observation_id":"9e18fbb4-472c-4c7b-a262-030bd38dfa49","resolution":{"observed_at":"2026-08-07T06:00:52.808590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.791771Z","title":"Universality laws for high-dimensional learning with random features","venue":null,"work_id":"e720bb1b-0b5a-4f94-9837-84a969dd4f76","year":1932},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.791721Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:326288827e4574f0082d28612f422332f249e4a3ea6232284c27dc622d0c795d","observation_id":"845f4b70-fd76-4090-847e-6c713ff9d976","resolution":{"observed_at":"2026-08-07T06:00:52.795909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04657","last_updated":"2025-08-10T23:57:10Z","snapshot_observed_at":"2026-07-06T18:26:58.940425Z","submitted_at":"2024-06-07T05:51:57Z","title":"From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04657","snapshot_observed_at":"2026-08-07T06:00:51.795047Z","title":"Crafting heavy-tails in weight matrix spectrum without gradient noise, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.795047Z"},"links":{"cited_paper":"/paper/2406.04657","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:19b108ca303277c8b74da5697e409917c7366dcf49a81c53f12c8e137c34f0d0","observation_id":"8dc60cf9-907f-4387-b44f-1c1320169106","resolution":{"observed_at":"2026-08-07T06:00:51.795047Z","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":"2026-08-07T06:00:51.798485Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.798485Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:d007fb27aefd27a5c050ca73f401bd95481b0dc0bd5f4cafa613bdbeff870101","observation_id":"68cb168f-7242-4399-ac8d-acbf1c5368c4","resolution":{"observed_at":"2026-08-07T06:00:51.798485Z","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":"2026-08-07T06:00:52.770849Z","title":"BaWA : Automatic optimizing pruning metric for large language models with balanced weight and activation","venue":null,"work_id":"a17917da-17b3-4e74-9d16-5571e6916f03","year":2025},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.801779Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:e7cb9291f5a9351f5a253ad466792d379aaf07f39f856903d7dab903ec4c0fa7","observation_id":"deeced84-2447-45c9-9695-85d85c712414","resolution":{"observed_at":"2026-08-07T06:00:52.775090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12178","last_updated":"2024-10-16T02:48:39Z","snapshot_observed_at":"2026-07-06T19:34:18.918585Z","submitted_at":"2024-10-16T02:48:39Z","title":"Model Balancing Helps Low-data Training and Fine-tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12178","snapshot_observed_at":"2026-08-07T06:00:51.805197Z","title":"Model balancing helps low-data training and fine-tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.805197Z"},"links":{"cited_paper":"/paper/2410.12178","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:e1682c375af5b5907f50c3b413d4d287e21869911974ef93ba57f7dacb46cd24","observation_id":"2aa71a65-f902-44b3-8afb-213cf0756125","resolution":{"observed_at":"2026-08-07T06:00:51.805197Z","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":"2026-08-07T06:00:52.757133Z","title":"Lift the veil for the truth: Principal weights emerge after rank reduction for reasoning-focused supervised fine-tuning","venue":null,"work_id":"92cf189c-0fe2-4bcf-8da5-9ed604afb814","year":2025},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.808746Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:a564394413eb5d24e91b49650d1dc87224c7307611e050999ea68f3cd1dd8976","observation_id":"d80cfb40-4173-4dc2-894f-dea92483912a","resolution":{"observed_at":"2026-08-07T06:00:52.761941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10912","last_updated":"2024-10-14T03:35:11Z","snapshot_observed_at":"2026-07-06T19:33:21.541657Z","submitted_at":"2024-10-14T03:35:11Z","title":"AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10912","snapshot_observed_at":"2026-08-07T06:00:51.812211Z","title":"Alphapruning: Using heavy-tailed self regularization theory for improved layer-wise pruning of large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.812211Z"},"links":{"cited_paper":"/paper/2410.10912","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:ddbd5238864ec21349ade265de60ce9ef1ebe4f52476f3f25ea2ae8756c20fb3","observation_id":"ea833ff8-10f9-4fb1-90b2-905f69a19ac9","resolution":{"observed_at":"2026-08-07T06:00:51.812211Z","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":"2026-08-07T06:00:52.743227Z","title":"Traditional and heavy tailed self regularization in neural network models","venue":null,"work_id":"e575a186-d717-4f81-86fb-2e3109e53796","year":2019},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.816243Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:dd5cf719518b30f1edb1c9d6762c815ac452e23c926c19d4ec382433df642243","observation_id":"62bfd72d-bddc-4a8c-8c7c-12af1970c10c","resolution":{"observed_at":"2026-08-07T06:00:52.747702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.08276","last_updated":"2019-01-24T08:20:42Z","snapshot_observed_at":"2026-07-06T07:28:43.161359Z","submitted_at":"2019-01-24T08:20:42Z","title":"Traditional and Heavy-Tailed Self Regularization in Neural Network Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.08276","snapshot_observed_at":"2026-08-07T06:00:51.819696Z","title":"Traditional and heavy-tailed self regularization in neural network models","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.819696Z"},"links":{"cited_paper":"/paper/1901.08276","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:4f6fececf287401b2ccb22f1cd6cf1403ebe1698f6d3e367d16b9f9a89603939","observation_id":"0d8389a0-9de5-4f32-9237-be8fd637dcb0","resolution":{"observed_at":"2026-08-07T06:00:51.819696Z","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":"2026-08-07T06:00:52.730276Z","title":"Implicit self-regularization in deep neural networks: Evidence from random matrix theory and implications for learning","venue":null,"work_id":"5fc61f07-cac4-4bbf-ad7f-d90ab2d9ac92","year":2021},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.823349Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:20f15b4921329b9a529ba898d98c7a159117c60c7fa72c403709908e8b3c38c7","observation_id":"626276c1-0762-4181-958d-aa4aefe79aec","resolution":{"observed_at":"2026-08-07T06:00:52.734471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:51.826610Z","title":"Martin, Tongsu Peng, and Michael W","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.826610Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:078787e76651a1932ee9982d424ac69c6d105700ee3ecf7418191f35c45cdd20","observation_id":"8d4de6ec-ac16-4ad6-b8fb-2e982a794a35","resolution":{"observed_at":"2026-08-07T06:00:51.826610Z","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":"2026-08-07T06:00:52.717675Z","title":"The generalization error of random features regression: Precise asymptotics and the double descent curve","venue":null,"work_id":"d4c92115-2bd4-4e00-be51-c9b55f192b01","year":2022},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.830605Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:c56a48605ad1ec80172b36ae8091ee6f62cf1590a4d156b5a21cebe928d75230","observation_id":"ee2ba575-99ff-4eb0-bb52-a6a9e8012a83","resolution":{"observed_at":"2026-08-07T06:00:52.721782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07843","last_updated":"2016-09-26T04:06:13Z","snapshot_observed_at":"2026-07-06T05:12:10.387914Z","submitted_at":"2016-09-26T04:06:13Z","title":"Pointer Sentinel Mixture Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.07843","snapshot_observed_at":"2026-08-07T06:00:51.834169Z","title":"Pointer sentinel mixture models","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.834169Z"},"links":{"cited_paper":"/paper/1609.07843","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:9e090dc23b305e3a6f40f97db8b57dbd9b7d609cb8f7d3afeeaf08ab94bfb276","observation_id":"e76c3c1a-d9ec-4ccd-b069-e83f7c537ecf","resolution":{"observed_at":"2026-08-07T06:00:51.834169Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.02789","last_updated":"2018-09-08T11:47:16Z","snapshot_observed_at":"2026-08-08T02:19:52.596062Z","submitted_at":"2018-09-08T11:47:16Z","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.02789","snapshot_observed_at":"2026-08-07T06:00:51.837865Z","title":"Can a suit of armor conduct electricity? a new dataset for open book question answering","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.837865Z"},"links":{"cited_paper":"/paper/1809.02789","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:4e8acbec2d78096381dde79e39cbe90a5820f9a672010d2d3f250618e84ffc54","observation_id":"e1bc72a5-4fc6-431f-b052-15ef7478c07d","resolution":{"observed_at":"2026-08-07T06:00:51.837865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.05957","last_updated":"2018-02-16T14:41:39Z","snapshot_observed_at":"2026-08-02T11:02:36.392878Z","submitted_at":"2018-02-16T14:41:39Z","title":"Spectral Normalization for Generative Adversarial Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.05957","snapshot_observed_at":"2026-08-07T06:00:51.841420Z","title":"Spectral normalization for generative adversarial networks, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.841420Z"},"links":{"cited_paper":"/paper/1802.05957","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:932ecf8429166c50044b43123720889a1b1f58062cff9df036bd00d3a5705f08","observation_id":"adf9ab93-26ef-4299-a41c-a761b1d1ec43","resolution":{"observed_at":"2026-08-07T06:00:51.841420Z","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":"2026-08-07T06:00:52.704757Z","title":"Graph spectra and the detectability of community structure in networks","venue":null,"work_id":"2ae64c34-3321-44a2-abe0-e4ce5b69fb07","year":2012},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.845913Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:aec95062ae3d96d71ea1b17b1867deb3a31174457d55004c1d9177a0a333442a","observation_id":"632d4784-38a3-402a-a7e8-1e30c44690f5","resolution":{"observed_at":"2026-08-07T06:00:52.708868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.692266Z","title":"Nonlinear random matrix theory for deep learning","venue":null,"work_id":"57796406-b50e-46bb-bb8a-e7cd79f6e3a6","year":2017},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.849549Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:c1c6cc68d9e24db5d7840e6920bf99a258592c960c723ed7cd718c0b1591e820","observation_id":"708f47bc-fe77-41ab-aa44-50896327ba50","resolution":{"observed_at":"2026-08-07T06:00:52.696398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10054","last_updated":"2024-10-14T00:43:02Z","snapshot_observed_at":"2026-07-06T19:32:42.378146Z","submitted_at":"2024-10-14T00:43:02Z","title":"AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10054","snapshot_observed_at":"2026-08-07T06:00:51.852982Z","title":"Alphalora: Assigning lora experts based on layer training quality","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.852982Z"},"links":{"cited_paper":"/paper/2410.10054","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:fc52da3757ac1e6cf0b7ba054c4629b8099b81efe0fee59c21020e1ff47c22f5","observation_id":"744d6b0b-ed8c-4240-ab1c-b2f5e709fced","resolution":{"observed_at":"2026-08-07T06:00:51.852982Z","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":"2026-08-07T06:00:51.856552Z","title":"Winogrande: An adversarial winograd schema challenge at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.856552Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:43c81c8fce77a7e37bd359d9519f935f7fc67a7747b13c7324dbec44c7783418","observation_id":"eb84b51b-2809-43a3-8810-e1849c8281b3","resolution":{"observed_at":"2026-08-07T06:00:51.856552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.04659","last_updated":"2020-02-20T11:24:34Z","snapshot_observed_at":"2026-08-07T19:20:38.365505Z","submitted_at":"2019-06-11T15:37:49Z","title":"Stable Rank Normalization for Improved Generalization in Neural Networks and GANs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.04659","snapshot_observed_at":"2026-08-07T06:00:51.860107Z","title":"Stable rank normalization for improved generalization in neural networks and gans","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.860107Z"},"links":{"cited_paper":"/paper/1906.04659","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:82c5dd8e95d1282604251bac7fe57f349fee6362174fa170c14c91831b697bb6","observation_id":"154b86d8-c19b-42e9-a583-5864e3a61a2a","resolution":{"observed_at":"2026-08-07T06:00:51.860107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-07-06T03:53:32.549552Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-07T06:00:51.863964Z","title":"Very deep convolutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.863964Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:f9f7e07c1e6f0df9bd8eb54b48c453b8e335e012fdfb88de0503ed32c84fbcec","observation_id":"bf5b3c2e-1c94-40b0-ab48-ae90404a3087","resolution":{"observed_at":"2026-08-07T06:00:51.863964Z","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":"2026-08-07T06:00:51.867767Z","title":"A tail-index analysis of stochastic gradient noise in deep neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.867767Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:b214c0d808697f82004f973a1611a2a563b2fe4ed9f33cbe62265ffdd9dbd16d","observation_id":"b53b2516-bd26-4c69-9e5a-016d0dc37f82","resolution":{"observed_at":"2026-08-07T06:00:51.867767Z","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":"2026-08-07T06:00:52.663469Z","title":"Hausdorff dimension, heavy tails, and generalization in neural networks","venue":null,"work_id":"0d5b67ae-caed-4734-8642-43c6f3482ec8","year":2020},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.871173Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:f0acb14f1fba173f9c6cf851e699f19305493fd06599b271c0fee06ea2d99c29","observation_id":"ea37a1a5-30e8-4607-aa0b-33fb9db059e5","resolution":{"observed_at":"2026-08-07T06:00:52.667546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11695","last_updated":"2024-05-06T17:47:01Z","snapshot_observed_at":"2026-07-06T15:44:42.776459Z","submitted_at":"2023-06-20T17:18:20Z","title":"A Simple and Effective Pruning Approach for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11695","snapshot_observed_at":"2026-08-07T06:00:51.874740Z","title":"A simple and effective pruning approach for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.874740Z"},"links":{"cited_paper":"/paper/2306.11695","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:f1cfb4a63eecf53edd5eecd29572d7aa4694b50e40d32d23c51dd7c2b45b4357","observation_id":"762e8aa0-feef-47a5-9815-7a3360b93b34","resolution":{"observed_at":"2026-08-07T06:00:51.874740Z","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":"2026-08-07T06:00:51.878664Z","title":"Pdebench: An extensive benchmark for scientific machine learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.878664Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:2b4d550ed9dce891e3403e7f31dd44f39d6ba27a081e8f8fa09e7f445a025b32","observation_id":"1d1f3918-3412-4211-b523-693144cf8601","resolution":{"observed_at":"2026-08-07T06:00:51.878664Z","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":"2026-08-07T06:00:51.882215Z","title":"Topics in random matrix theory, volume 132","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.882215Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:b26270fbcd104fc9434b59ce030a39f93802c7e1e8d75ba362e02c1fcc922619","observation_id":"d9d77f4e-3809-46ce-a750-5c70a0c0ced9","resolution":{"observed_at":"2026-08-07T06:00:51.882215Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-07T06:00:51.885978Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.885978Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:a54d030ea01743b3522f6af8e652e4d247dd0ecc8e86ce65ba33f38f4f22df3e","observation_id":"c96c9f74-da76-4aa9-bb53-120b22903b5d","resolution":{"observed_at":"2026-08-07T06:00:51.885978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-07T06:00:51.890034Z","title":"Llama 2: Open foundation and fine-tuned chat models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.890034Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:6764e3432f456fea542cbb26da0e6136d09632ba035355ecb6e9eaa664a65f2f","observation_id":"a26140bb-49b8-448c-929f-9b4f6fbf748d","resolution":{"observed_at":"2026-08-07T06:00:51.890034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1561/0100000001","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.006476Z","title":"Tulino and Sergio Verdú","venue":null,"work_id":"f6cfa9b8-2f08-4716-8edb-c29f19c231ff","year":2004},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.893958Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:d6174d497caab6a0a33b842c0fec9b422aea969c6b82aca4f53a574b6d6d89e1","observation_id":"b0cb3bab-38ca-4253-9122-3a4677239a24","resolution":{"observed_at":"2026-08-07T06:00:52.011695Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.07461","last_updated":"2019-02-22T23:53:34Z","snapshot_observed_at":"2026-07-06T06:34:26.609892Z","submitted_at":"2018-04-20T06:35:04Z","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.07461","snapshot_observed_at":"2026-08-07T06:00:51.897937Z","title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.897937Z"},"links":{"cited_paper":"/paper/1804.07461","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:a67b882a8ed37a307c9351df74525266860e99308f5f48c00c1ed26b4d8ab959","observation_id":"d3e1297c-6380-4b2c-bd80-8e5e7b7858c5","resolution":{"observed_at":"2026-08-07T06:00:51.897937Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.06506","last_updated":"2023-11-08T04:50:55Z","snapshot_observed_at":"2026-08-04T16:45:41.426786Z","submitted_at":"2022-11-11T23:00:30Z","title":"Spectral Evolution and Invariance in Linear-width Neural Networks","version":2},"cited_work":{"arxiv_id":"2211.06506","doi":null,"metadata_source":"pith","pith_arxiv_id":"2211.06506","snapshot_observed_at":"2026-08-07T06:00:52.291083Z","title":"Spectral Evolution and Invariance in Linear-width Neural Networks","venue":"cs.LG","work_id":"85a3ad9b-c68e-4a86-a5d4-671d13ca1c84","year":2022},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.901852Z"},"links":{"cited_paper":"/paper/2211.06506","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:d38ac773b5b62f0c95b90d41f84cb8652fd458214739d2669ccee3d9e50cda67","observation_id":"f74a8f92-4d78-4889-8e64-667299ae6b75","resolution":{"observed_at":"2026-08-07T06:00:52.295210Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.20018","last_updated":"2024-05-30T12:57:35Z","snapshot_observed_at":"2026-07-06T18:22:40.048076Z","submitted_at":"2024-05-30T12:57:35Z","title":"Safe Multi-agent Reinforcement Learning with Natural Language Constraints","version":1},"cited_work":{"arxiv_id":"2405.20018","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.20018","snapshot_observed_at":"2026-08-07T06:00:52.271015Z","title":"Safe Multi-agent Reinforcement Learning with Natural Language Constraints","venue":"cs.MA","work_id":"a73505c0-a0c1-4b58-8edb-2ecc274da234","year":2024},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.906214Z"},"links":{"cited_paper":"/paper/2405.20018","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:07a67475310349f2cfcd814055f2dfb2d132d745339ade305ed4a88ebff11a75","observation_id":"872597a2-1652-4265-933d-32899998335d","resolution":{"observed_at":"2026-08-07T06:00:52.276686Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.634392Z","title":"M3hf: Multi-agent reinforcement learning from multi-phase human feedback of mixed quality","venue":null,"work_id":"8ca24c82-fd8d-4712-b4e5-ac13dc540f54","year":2025},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.910500Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:acbe2d18860582f544eac5a4c2dcfc86afc18656bc18f49acc2e0789885141b3","observation_id":"091d8f56-5113-4809-a69e-27e4f77700fc","resolution":{"observed_at":"2026-08-07T06:00:52.638534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:51.914356Z","title":"Tensor programs iv: Feature learning in infinite-width neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.914356Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:185f5fce1e7bcc026f1df1fad946d3b604d14dd36cbf6d514fd0f40cba769755","observation_id":"080b48e7-3b2d-4bfb-88e9-31aae79215b6","resolution":{"observed_at":"2026-08-07T06:00:51.914356Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.03466","last_updated":"2022-03-28T08:12:14Z","snapshot_observed_at":"2026-08-07T09:04:57.100575Z","submitted_at":"2022-03-07T15:37:35Z","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.03466","snapshot_observed_at":"2026-08-07T06:00:51.918076Z","title":"Tensor programs v: Tuning large neural networks via zero-shot hyperparameter transfer","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.918076Z"},"links":{"cited_paper":"/paper/2203.03466","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:005635c588b09198b61af1e9fd47588ed0af6db9a697f0c3df4bda174189cf1b","observation_id":"697b68ac-94da-4602-88c9-c39d7c8cf124","resolution":{"observed_at":"2026-08-07T06:00:51.918076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.13910","last_updated":"2025-02-27T17:08:19Z","snapshot_observed_at":"2026-07-06T19:35:35.229351Z","submitted_at":"2024-10-17T00:13:31Z","title":"Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.13910","snapshot_observed_at":"2026-08-07T06:00:51.922284Z","title":"Mitigating the backdoor effect for multi-task model merging via safety-aware subspace","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.922284Z"},"links":{"cited_paper":"/paper/2410.13910","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:ed68a4bf705ca7aa6269645a0e1b1b52f32e9243ba34e322b0b6d5a7981bafef","observation_id":"f151b568-8217-4b12-8117-9873201dc6ca","resolution":{"observed_at":"2026-08-07T06:00:51.922284Z","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":"2026-08-07T06:00:52.613232Z","title":"Multimodal commonsense knowledge distillation for visual question answering (student abstract)","venue":null,"work_id":"a3845cc6-877b-439f-ae0e-6673b96aa5e3","year":2025},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.926420Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:c5a6242d3702070a2f0156409664dd4e2522f2bc6f02c031a924d483c3fc47ba","observation_id":"4db911bd-4f09-498a-92de-43940081b30c","resolution":{"observed_at":"2026-08-07T06:00:52.617248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.18491","last_updated":"2025-06-11T11:33:08Z","snapshot_observed_at":"2026-08-07T16:41:51.239181Z","submitted_at":"2025-03-24T09:45:26Z","title":"MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.18491","snapshot_observed_at":"2026-08-07T06:00:51.930988Z","title":"Magic-vqa: Multimodal and grounded inference with commonsense knowledge for visual question answering","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.930988Z"},"links":{"cited_paper":"/paper/2503.18491","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:8969547e8cefa1dd96b36f05c9f4afb4907f2ce8ba722c22560cb9619354af2c","observation_id":"14ceb5be-eff4-4fdb-a232-4850c8e0dbd9","resolution":{"observed_at":"2026-08-07T06:00:51.930988Z","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":"2026-08-07T06:00:51.935251Z","title":"Gonzalez, Kannan Ramchandran, Charles H","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.935251Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:f035cdc9ac70a00263472a34c80600669efac76884080c00eb6513f7aabd92c1","observation_id":"6c92a131-5f55-4467-8f83-2e87176298cb","resolution":{"observed_at":"2026-08-07T06:00:51.935251Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05175","last_updated":"2025-06-30T22:16:39Z","snapshot_observed_at":"2026-08-01T08:08:15.221032Z","submitted_at":"2023-10-08T14:22:58Z","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05175","snapshot_observed_at":"2026-08-07T06:00:51.939296Z","title":"Outlier weighed layerwise sparsity (owl): A missing secret sauce for pruning llms to high sparsity","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.939296Z"},"links":{"cited_paper":"/paper/2310.05175","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:f444de92ea7310d6f93f8e4d5146e90a2e24e200276bb7cec32ecb1cff29aba2","observation_id":"52659e9c-dcc0-4cf0-ae10-318c363af065","resolution":{"observed_at":"2026-08-07T06:00:51.939296Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.10941","last_updated":"2017-05-31T04:56:25Z","snapshot_observed_at":"2026-08-05T12:22:57.956907Z","submitted_at":"2017-05-31T04:56:25Z","title":"Spectral Norm Regularization for Improving the Generalizability of Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.10941","snapshot_observed_at":"2026-08-07T06:00:51.943686Z","title":"Spectral norm regularization for improving the generalizability of deep learning, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.943686Z"},"links":{"cited_paper":"/paper/1705.10941","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:4556202c1ef23ca57460838580fe0971b8a56acce3b8861853d265c6e55eeeb6","observation_id":"9fb287c6-7cc8-48ce-ab15-3f949fa6e9a2","resolution":{"observed_at":"2026-08-07T06:00:51.943686Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.07830","last_updated":"2019-05-19T23:57:23Z","snapshot_observed_at":"2026-07-31T00:09:56.948833Z","submitted_at":"2019-05-19T23:57:23Z","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.07830","snapshot_observed_at":"2026-08-07T06:00:51.947758Z","title":"Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:1905.07830, 2019","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.947758Z"},"links":{"cited_paper":"/paper/1905.07830","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:439447ec465e031e12a185000ac0621de2430ac545aa94d0207e4a321e142202","observation_id":"3ec66ec6-3ff3-4cd8-8906-5e6c9977da53","resolution":{"observed_at":"2026-08-07T06:00:51.947758Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.01068","last_updated":"2022-06-21T17:04:40Z","snapshot_observed_at":"2026-08-06T03:13:37.403059Z","submitted_at":"2022-05-02T17:49:50Z","title":"OPT: Open Pre-trained Transformer Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.01068","snapshot_observed_at":"2026-08-07T06:00:51.952130Z","title":"Opt: Open pre-trained transformer language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.952130Z"},"links":{"cited_paper":"/paper/2205.01068","citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:e92d6da0b1bd6d39ebb3f5299cbe1b33e2494111c724c63e19fc266e92858014","observation_id":"10a65845-56f2-4216-946d-cdc327725998","resolution":{"observed_at":"2026-08-07T06:00:51.952130Z","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":"2026-08-07T06:00:52.600723Z","title":"Temperature balancing, layer-wise weight analysis, and neural network training","venue":null,"work_id":"21a571fb-5071-482e-bc81-7a000bfdc9b1","year":2024},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.956252Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:9024faf6c334f5cafffa90ea27144ac172ad91e3c4fac1efebabf5e932718df4","observation_id":"1d3e3b2d-0071-41d3-b559-5f9c4f5870b9","resolution":{"observed_at":"2026-08-07T06:00:52.604603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:52.587605Z","title":"Remedy: Recipe merging dynamics in large vision-language models","venue":null,"work_id":"0a299a0d-94ce-4925-bead-33511a25f1fd","year":2025},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.960314Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:ac7a5b5e5328ca19f351cb261a6fc089cbdd0e74dcbe8aa1d5b1846b877ebb59","observation_id":"dbf735e7-d669-4466-9c83-cbdbe3856d02","resolution":{"observed_at":"2026-08-07T06:00:52.591848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:00:51.964187Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.964187Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:6a3b1c94aeb2b8f1c7e1a2c129424389d4dd2a0f03276c41a50f1ca8d92995e4","observation_id":"a06a3613-6153-410f-9c7b-4f180a284af3","resolution":{"observed_at":"2026-08-07T06:00:51.964187Z","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":"2026-08-07T06:00:51.968644Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.968644Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:e2dcd484e4d8538e935e4c3d2d5256d87a216dd9008b051fb195a9f3e67d3d29","observation_id":"ff7bb1ec-01dd-46c3-991f-c446b611261f","resolution":{"observed_at":"2026-08-07T06:00:51.968644Z","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":"2026-08-07T06:00:51.972799Z","title":"training quality","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","version":2},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-07T06:00:51.972799Z"},"links":{"citing_paper":"/paper/2506.06280"},"observation_digest":"sha256:ad21c50891d514c2545beb675bba3e3a0558b25aaff640fb61a5261a6cc0da48","observation_id":"45b6c17d-ec5a-4d0a-9971-cfd869263ad5","resolution":{"observed_at":"2026-08-07T06:00:51.972799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.06280","last_updated":"2025-08-18T03:36:09Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T06:32:53.646865Z","submitted_at":"2025-06-06T17:59:28Z","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias"},"reference_resolution":{"displayed":74,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":43,"verified_exact":3,"verified_fuzzy":28},"total_outbound_references":74},"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 74 of 74 outbound references and 1 inbound Pith citation observation for arXiv:2506.06280."}