{"as_of":"2026-08-09T05:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4f0e17b70b0ac16fdeb31755ce90dae8986ed21775ba0ecaf160dffab5b69d91","coverage":[{"denominator":53,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":53,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T15:34:16.775757Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T18:26:05.728364Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-12T05:31:24.127049Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"cited_work":{"arxiv_id":"2502.06443","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.06443","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2502.06443 , year=","venue":null,"work_id":"01749daf-b1e4-48c0-903c-78d500e2bbc4","year":2025},"citing_paper":{"arxiv_id":"2604.22951","last_updated":"2026-07-08T19:29:03Z","snapshot_observed_at":"2026-07-12T23:17:30.297545Z","submitted_at":"2026-04-24T18:49:08Z","title":"The Power of Power Law: Asymmetry Enables Compositional Reasoning","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-05-08T11:49:49.787123Z"},"links":{"cited_paper":"/paper/2502.06443","citing_paper":"/paper/2604.22951"},"observation_digest":"sha256:beedbfcc61d7bf5da2f58644704580e197cfe54c09d222839b78b2f7c451362f","observation_id":"b29a5ca7-1e84-4455-b407-a4eee819984c","resolution":{"observed_at":"2026-05-11T19:31:08.363842Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.06443","snapshot_observed_at":"2026-07-12T18:26:05.728364Z","title":"Low-dimensional functions are efficiently learnable under randomly biased distributions","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.22951","last_updated":"2026-07-08T19:29:03Z","snapshot_observed_at":"2026-07-12T23:17:30.297545Z","submitted_at":"2026-04-24T18:49:08Z","title":"The Power of Power Law: Asymmetry Enables Compositional Reasoning","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-07-12T18:26:05.728364Z"},"links":{"cited_paper":"/paper/2502.06443","citing_paper":"/paper/2604.22951"},"observation_digest":"sha256:c5a19246c310ab600e43ba6cccfabecf6f93ecaa9abac247c0a443854f273f46","observation_id":"8ce4de0f-6d99-4261-b741-38c20ec46912","resolution":{"observed_at":"2026-07-12T18:26:05.728364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"cited_work":{"arxiv_id":"2502.06443","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.06443","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2502.06443 , year=","venue":null,"work_id":"01749daf-b1e4-48c0-903c-78d500e2bbc4","year":2025},"citing_paper":{"arxiv_id":"2605.10237","last_updated":"2026-05-11T09:11:20Z","snapshot_observed_at":"2026-07-06T23:22:13.774652Z","submitted_at":"2026-05-11T09:11:20Z","title":"The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently","version":1},"reference_index":158,"source":"arxiv_source","source_observed_at":"2026-05-12T05:27:11.761971Z"},"links":{"cited_paper":"/paper/2502.06443","citing_paper":"/paper/2605.10237"},"observation_digest":"sha256:2d09a3c280524813cb5291affa83dc374f85707912144ba370e48263aff5c729","observation_id":"9d37d22a-bbd6-45a1-ab99-91479acc4f0b","resolution":{"observed_at":"2026-05-12T05:31:24.131423Z","resolver_source":"arxiv_id","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/2502.06443/citation-record","integrity":"/paper/2502.06443/integrity","json":"/paper/2502.06443/citation-record.json","paper":"/paper/2502.06443"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:34:17.636360Z","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","venue":null,"work_id":"c09f2b79-6d67-465d-a9f2-61990d84fbd5","year":2023},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.556772Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:5ab70fd562fab21a32b9ac9722173080b6813afa61d28b3bc2392c8325b91889","observation_id":"3413796e-a243-4d74-b9db-a1c7de98cf60","resolution":{"observed_at":"2026-08-08T15:34:17.640124Z","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":"2026-08-08T15:34:17.623901Z","title":"The merged-staircase property: a necessary and nearly sufficient condition for sgd learning of sparse functions on two-layer neural networks","venue":null,"work_id":"aaca9c83-65e8-4b2b-9e34-13df5edd97d5","year":2022},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.561381Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:115e892207d9afd2b2b36ec964fc2c5533a2cc6557b67812be8bfb44752e9962","observation_id":"54a40a25-9e73-4387-8654-8b7482ae7cf0","resolution":{"observed_at":"2026-08-08T15:34:17.627812Z","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":"2026-08-08T15:34:17.611573Z","title":"Provable advantage of curriculum learning on parity targets with mixed inputs","venue":null,"work_id":"5dd4474c-7543-4aab-bca9-6a0fff662b98","year":2023},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.565411Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:7a0ffb88624e7da2ac34a4abd75d6b9bf4223ca8ea1b5dd97e83cfa365f17438","observation_id":"10d60919-e706-4f38-8963-1717eef1ba7f","resolution":{"observed_at":"2026-08-08T15:34:17.615542Z","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":"2405.15459","last_updated":"2025-02-10T09:33:48Z","snapshot_observed_at":"2026-08-05T15:27:10.774229Z","submitted_at":"2024-05-24T11:34:31Z","title":"Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15459","snapshot_observed_at":"2026-08-08T15:34:16.569798Z","title":"Repetita iuvant: Data repetition allows SGD to learn high-dimensional multi-index functions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.569798Z"},"links":{"cited_paper":"/paper/2405.15459","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:1e883697230e4bc81a735d3b5f93f4b3e26382548e89c066768735a412c024ec","observation_id":"d891adcf-4063-4d6b-beea-bcf753a75f3a","resolution":{"observed_at":"2026-08-08T15:34:16.569798Z","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":"2026-08-08T15:34:17.597771Z","title":"On the universality of deep learning","venue":null,"work_id":"336b27c9-d534-4c49-abcf-5d26ef66a6cd","year":2020},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.574076Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:5d12a96b6b29af875e156c062119f3b9750448f965fe33668e1713d25c5fa86f","observation_id":"6ea80aca-4b31-4ebc-99c1-ef9201ecda8d","resolution":{"observed_at":"2026-08-08T15:34:17.601804Z","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":"2026-08-08T15:34:17.583352Z","title":"Online stochastic gradient descent on non-convex losses from high-dimensional inference","venue":null,"work_id":"10181eb1-05e2-41f9-8318-bfdd5e908b18","year":2021},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.578158Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:61703bb84811d820bfdd74b542012a649ba29547edd408ee400311f58d9db685","observation_id":"16c83e81-ae2c-43c9-b4cb-f97ff89df101","resolution":{"observed_at":"2026-08-08T15:34:17.588213Z","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":"2026-08-08T15:34:17.568499Z","title":"High-dimensional limit theorems for SGD : Effective dynamics and critical scaling","venue":null,"work_id":"0cf5dfcf-d03f-481f-a0a9-46786e47af75","year":2022},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.582610Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:8490c91f0e384cb6f5b937789788157af8799548f7759be29ea8f21138159b42","observation_id":"df28bd48-c375-4ffe-97f9-7276990a1693","resolution":{"observed_at":"2026-08-08T15:34:17.573284Z","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":"2310.19793","last_updated":"2023-11-02T17:33:13Z","snapshot_observed_at":"2026-08-04T08:51:40.592790Z","submitted_at":"2023-10-30T17:55:28Z","title":"On Learning Gaussian Multi-index Models with Gradient Flow","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.19793","snapshot_observed_at":"2026-08-08T15:34:16.586354Z","title":"On learning G aussian multi-index models with gradient flow","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.586354Z"},"links":{"cited_paper":"/paper/2310.19793","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:e8d91188204245a522cdf2ac772feec1ba46e1a813bf6ebce8d9014cc4bfaefb","observation_id":"2230fce1-742b-4d12-a5c6-8ffb0cd67864","resolution":{"observed_at":"2026-08-08T15:34:16.586354Z","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":"2026-08-08T15:34:17.554985Z","title":"Learning single-index models with shallow neural networks","venue":null,"work_id":"4e3a8f13-b90b-4f8f-b79e-eca9d02f16bf","year":2022},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.590954Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:5f8dc7fb47b87dace559fe4cae64f77133e662250e19597de9220d7f6c78f46e","observation_id":"d73e4deb-6fee-4ae9-b951-fc8f14de59b1","resolution":{"observed_at":"2026-08-08T15:34:17.559422Z","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":"2026-08-08T15:34:17.541448Z","title":"Id3 learns juntas for smoothed product distributions","venue":null,"work_id":"2728a5df-790a-42c7-be4d-9e8a1058865e","year":2020},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.595252Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:3cbf143fb849eff04f5c43abaca1655a578a5292752c6163467b7c2ef822dcbe","observation_id":"c68a95ba-b8f1-4912-96e8-abfb8f342c59","resolution":{"observed_at":"2026-08-08T15:34:17.545776Z","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":"2207.08799","last_updated":"2023-01-15T21:53:00Z","snapshot_observed_at":"2026-08-06T09:14:09.933368Z","submitted_at":"2022-07-18T17:55:05Z","title":"Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.08799","snapshot_observed_at":"2026-08-08T15:34:16.599535Z","title":"Hidden progress in deep learning: Sgd learns parities near the computational limit","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.599535Z"},"links":{"cited_paper":"/paper/2207.08799","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:4eb3406820e718b287d5ba7f19e7d73e2460dd437dcc0ece78c4a1301b0cb1f3","observation_id":"7f726ba0-ece0-4ead-a770-3acad5f9d011","resolution":{"observed_at":"2026-08-08T15:34:16.599535Z","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":"2026-08-08T15:34:17.527795Z","title":"High-dimensional asymptotics of feature learning: How one gradient step improves the representation","venue":null,"work_id":"6d43102e-49e6-4628-9814-2a729703cd08","year":2022},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.604240Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:3e065a5becd65de44255a9be57773a22db1f729cf085c5a0e7e5e6202485e0db","observation_id":"75582ffb-1a54-4324-8d40-191e5adc18cd","resolution":{"observed_at":"2026-08-08T15:34:17.532171Z","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":"2026-08-08T15:34:17.514004Z","title":"Learning in the presence of low-dimensional structure: a spiked random matrix perspective","venue":null,"work_id":"5db83ae5-ad18-47f0-b337-c1d254b211c0","year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.608434Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:08ff0af744f2e6c0fb7990a6c9f0d4cc9188b3e9ac88d76d61e4745eaf5a6b4a","observation_id":"5a9d4ad8-a5c0-4aa3-a899-4a2fae77dc92","resolution":{"observed_at":"2026-08-08T15:34:17.518573Z","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":"2026-08-08T15:34:16.612659Z","title":"Learning time-scales in two-layers neural networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.612659Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:0eb88581ef364562c4c7dd798e5abf63eb4a64fb4cd5e99c6c28421ed23e2360","observation_id":"d4f5879d-e842-4356-a0b7-77b7ec874038","resolution":{"observed_at":"2026-08-08T15:34:16.612659Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"math/0104271","last_updated":"2001-04-27T18:16:11Z","snapshot_observed_at":"2026-08-09T04:48:53.805297Z","submitted_at":"2001-04-27T18:16:11Z","title":"The Distribution of Values of Analytic Functions on Convex Bodies","version":1},"cited_work":{"arxiv_id":"math/0104271","doi":null,"metadata_source":"pith","pith_arxiv_id":"math/0104271","snapshot_observed_at":"2026-08-08T15:34:17.076093Z","title":"The Distribution of Values of Analytic Functions on Convex Bodies","venue":"math.CV","work_id":"8febf0fc-0cb1-4e07-bf92-c3c6a249a83f","year":2001},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.616687Z"},"links":{"cited_paper":"/paper/math/0104271","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:9364485a30100af822e51f3a4bee65052575cff663e3932a3da71ddb0e132396","observation_id":"00ff46dd-da5f-4bc0-aa77-8f746c0d313e","resolution":{"observed_at":"2026-08-08T15:34:17.080764Z","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":"2026-08-08T15:34:17.491374Z","title":"Learning narrow one-hidden-layer ReLU networks","venue":null,"work_id":"7ffdcb06-48ab-44df-98b5-ac8221d360a3","year":2023},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.621292Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:a81a381dfc9ad221d7a57f4debeae67a665edd11b2e1e7e1ca88684dee4cb641","observation_id":"07956966-6f13-4bef-9684-209f0064e743","resolution":{"observed_at":"2026-08-08T15:34:17.495703Z","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":"2506.00764","last_updated":"2025-06-01T00:43:46Z","snapshot_observed_at":"2026-08-07T11:56:21.335564Z","submitted_at":"2025-06-01T00:43:46Z","title":"Learning Juntas under Markov Random Fields","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.00764","snapshot_observed_at":"2026-08-08T15:34:16.625479Z","title":"Learning juntas under markov random fields","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.625479Z"},"links":{"cited_paper":"/paper/2506.00764","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:8c5b33dd9e5e19f41e0cc0f855c79a4c233eb490efa686a627270b56af0bdd6c","observation_id":"f37d323b-f737-477b-b7fb-6fbc2621d801","resolution":{"observed_at":"2026-08-08T15:34:16.625479Z","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":"2026-08-08T15:34:17.477932Z","title":"A mathematical model for curriculum learning for parities","venue":null,"work_id":"bf6d5b16-7222-47cb-bdf2-e838d6595165","year":2023},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.629831Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:11eaecb0c70fd79a9f61e0939864c1fcf3d8e44eaa93f172b10238b214ccd4af","observation_id":"8485b09d-721c-4b6c-b0b9-9ed1b35fb49a","resolution":{"observed_at":"2026-08-08T15:34:17.482272Z","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":"2026-08-08T15:34:17.463475Z","title":"Distributional and L^q norm inequalities for polynomials over convex bodies in R^n","venue":null,"work_id":"b414f145-d279-4214-bf5b-10a882c90eeb","year":2001},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.633976Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:3f4e7afb228d0086c67bb301ed4ec513e89aff4514f113a4e8948763aaf9ef47","observation_id":"01185546-a602-4cff-af0d-cf8f1ea75734","resolution":{"observed_at":"2026-08-08T15:34:17.468442Z","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":"2026-08-08T15:34:17.449132Z","title":"Learning single-index models in G aussian space","venue":null,"work_id":"586698e1-c871-4917-a149-a0ba31626752","year":1930},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.638427Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:89e6c4f28ac1bf3ca1eacade28c181b1adac17910c121a36393542d5d53b5a71","observation_id":"ac8ada27-9886-401a-8624-895ac76c6e22","resolution":{"observed_at":"2026-08-08T15:34:17.453559Z","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":"2305.18270","last_updated":"2025-06-03T19:12:56Z","snapshot_observed_at":"2026-08-08T04:11:57.213673Z","submitted_at":"2023-05-29T17:43:44Z","title":"How Two-Layer Neural Networks Learn, One (Giant) Step at a Time","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18270","snapshot_observed_at":"2026-08-08T15:34:16.642638Z","title":"How two-layer neural networks learn, one (giant) step at a time","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.642638Z"},"links":{"cited_paper":"/paper/2305.18270","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:e62c1a054fc7203644323a60fef00f81af4dd15e6af659a705e6ce7c3d1f7e04","observation_id":"a261ff52-bf6c-4edb-a572-9f73bdb300c6","resolution":{"observed_at":"2026-08-08T15:34:16.642638Z","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":"2026-08-08T15:34:17.435480Z","title":"Neural networks can learn representations with gradient descent","venue":null,"work_id":"87a22851-3f70-40ab-a298-442b6880cc0f","year":2022},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.647278Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:7569457f0ca6bfcc516aa58a48781d17fdbc172f36f30d2c6fb5dec23a2dac6a","observation_id":"d90ad22c-f32d-452d-bf5e-e0e762e937cd","resolution":{"observed_at":"2026-08-08T15:34:17.439989Z","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":"2026-08-08T15:34:17.422789Z","title":"Learning parities with neural networks","venue":null,"work_id":"9f15e51d-99f3-4ac4-81ab-fde12ddaea8d","year":2020},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.651417Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:f052393261f89fc3adcd460da041d368ca62a9880c1ea44f72fed091dbaaa9b7","observation_id":"2695e3a6-a8e4-48a0-9c3c-f4d194ce5c8e","resolution":{"observed_at":"2026-08-08T15:34:17.426636Z","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":"2026-08-08T15:34:17.410204Z","title":"Smoothing the landscape boosts the signal for SGD : Optimal sample complexity for learning single index models","venue":null,"work_id":"da46c60a-2894-46b9-b061-69bf41600b33","year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.655411Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:fe795dceaf43e51d3374eaf22f8772ece04cf49920b7304c9ddef2a1ba0ac32f","observation_id":"905ce3da-a044-4fcc-b529-726afde5c623","resolution":{"observed_at":"2026-08-08T15:34:17.414177Z","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":"2026-08-08T15:34:17.397396Z","title":"Computational-statistical gaps in G aussian single-index models","venue":null,"work_id":"528a6f5c-3c51-4257-9350-29d557c8c738","year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.659528Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:a10e1797bf45c632e6098dd385b6784084b33d360ee23ff3f02a1f7594017c73","observation_id":"3d49df39-c687-49e0-aa0c-051e576e32a8","resolution":{"observed_at":"2026-08-08T15:34:17.401375Z","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":"2402.03220","last_updated":"2024-06-30T17:01:45Z","snapshot_observed_at":"2026-08-08T07:14:14.108661Z","submitted_at":"2024-02-05T17:30:42Z","title":"The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03220","snapshot_observed_at":"2026-08-08T15:34:16.663507Z","title":"The benefits of reusing batches for gradient descent in two-layer networks: Breaking the curse of information and leap exponents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.663507Z"},"links":{"cited_paper":"/paper/2402.03220","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:0cac3b91beff103f911b6fccabc1b4c03911f3621e73077c28a37e370ef7b035","observation_id":"ee8bc199-455b-4a47-835c-df4c2a974aed","resolution":{"observed_at":"2026-08-08T15:34:16.663507Z","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":"2026-08-08T15:34:16.667821Z","title":null,"venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.667821Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:9286a094a2b3434669111103587a7b2b606278ffad9ace6a42d515c7da524901","observation_id":"6eab725f-eda3-4c43-8874-72275576eb62","resolution":{"observed_at":"2026-08-08T15:34:16.667821Z","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":"2026-08-08T15:34:17.375793Z","title":"Agnostic learning of a single neuron with gradient descent","venue":null,"work_id":"66925305-33f0-418f-b55d-eff1af0dcce2","year":2020},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.672963Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:6f8eef949dc2d05319892fe9df10e06586ecf8b2e16c94cf59767840550dfc51","observation_id":"0cf070d6-52e8-42cb-9cdc-fe018b53435f","resolution":{"observed_at":"2026-08-08T15:34:17.380025Z","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":"2026-08-08T15:34:17.362365Z","title":"Superpolynomial lower bounds for learning one-layer neural networks using gradient descent","venue":null,"work_id":"5df4a275-944e-4871-b728-f02c5500fa64","year":2020},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.676940Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:34ad6958ca1f4703cb5877fd45dc4b7c96a48cae3e60f995d8e462f7d13815a4","observation_id":"2a94d408-05ea-43ea-a96e-528d186302e6","resolution":{"observed_at":"2026-08-08T15:34:17.367001Z","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":"2026-08-08T15:34:17.349267Z","title":"Modeling the influence of data structure on learning in neural networks: The hidden manifold model","venue":null,"work_id":"8cd100f5-6ded-466e-80ec-3b727ff46e0f","year":2020},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.681065Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:30f82e682682545ef2ccc490839c06ca8174eb5702a184133f8c799d3faa325f","observation_id":"14e4a8c8-0b24-41c3-bbf0-04784e488cc6","resolution":{"observed_at":"2026-08-08T15:34:17.353552Z","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":"2407.05622","last_updated":"2024-07-08T05:30:34Z","snapshot_observed_at":"2026-08-01T15:37:53.369157Z","submitted_at":"2024-07-08T05:30:34Z","title":"On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries","version":1},"cited_work":{"arxiv_id":"2407.05622","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.05622","snapshot_observed_at":"2026-08-08T15:34:17.012725Z","title":"On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries","venue":"cs.LG","work_id":"793bb87e-2b6f-43d5-a6d2-4ee7af04bc59","year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.685134Z"},"links":{"cited_paper":"/paper/2407.05622","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:180079661634ec95e017f5aa5d2d4ef618481a7f97fa4365f7965f62a7de81e0","observation_id":"d7219710-d2b4-403d-be77-1e150fc454e7","resolution":{"observed_at":"2026-08-08T15:34:17.020132Z","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":"2404.12376","last_updated":"2024-12-06T02:58:51Z","snapshot_observed_at":"2026-08-01T20:56:40.171963Z","submitted_at":"2024-04-18T17:57:53Z","title":"Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Sign Stochastic Gradient Descent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.12376","snapshot_observed_at":"2026-08-08T15:34:16.689515Z","title":"Matching the statistical query lower bound for k-sparse parity problems with stochastic gradient descent","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.689515Z"},"links":{"cited_paper":"/paper/2404.12376","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:995ee383e28a1460a009590e3757814cc7cd3eb98ba926245cc6e94471bcdb83","observation_id":"a906c605-35c1-4f03-b88f-f8e075149755","resolution":{"observed_at":"2026-08-08T15:34:16.689515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1301.0820","last_updated":"2013-01-04T20:43:46Z","snapshot_observed_at":"2026-07-06T03:03:17.807263Z","submitted_at":"2013-01-04T20:43:46Z","title":"Moment-Matching Polynomials","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1301.0820","snapshot_observed_at":"2026-08-08T15:34:16.693733Z","title":"Moment-matching polynomials","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.693733Z"},"links":{"cited_paper":"/paper/1301.0820","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:a545eb510b0daad2ced35df914c46c9729c9f43f26913bda97da5083c0a9e9e4","observation_id":"1c4b4ba2-2629-4af5-b6d6-a7585ced4ab9","resolution":{"observed_at":"2026-08-08T15:34:16.693733Z","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":"2026-08-08T15:34:17.336339Z","title":"Learning and smoothed analysis","venue":null,"work_id":"771c1994-629d-4a3d-a97f-9b131ea18cd6","year":2009},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.697575Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:35af1c31ee1b410e2c3977724824c72423917c1506d26a5f5d0b9e8904ae3647","observation_id":"07a6a7db-d15c-468b-a607-ff3fb2e6e790","resolution":{"observed_at":"2026-08-08T15:34:17.340479Z","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":"0812.0933","last_updated":"2008-12-04T13:34:26Z","snapshot_observed_at":"2026-07-06T01:46:51.846123Z","submitted_at":"2008-12-04T13:34:26Z","title":"Decision trees are PAC-learnable from most product distributions: a smoothed analysis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"0812.0933","snapshot_observed_at":"2026-08-08T15:34:16.701205Z","title":"Decision trees are pac-learnable from most product distributions: a smoothed analysis","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.701205Z"},"links":{"cited_paper":"/paper/0812.0933","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:e226c6c6ef21fbb44793ddcaf4126396240d68eb632946a983fe55cf4765a26d","observation_id":"ff7b3fda-ee11-457a-8c7f-ced04434b9ce","resolution":{"observed_at":"2026-08-08T15:34:16.701205Z","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":"2026-08-08T15:34:17.322610Z","title":"In\\'egalit\\'es isop\\'erim\\'etriques en analyse et probabilit\\'es","venue":null,"work_id":"f5af38aa-a68c-48a9-b192-bf8f71332e60","year":1993},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.705602Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:409ec829e713e14c73ae9b75746fc9286b2e869016842b79c1d2ef4e94586824","observation_id":"f3d56de1-9fe4-4e5e-b1fa-b50bb635619e","resolution":{"observed_at":"2026-08-08T15:34:17.327070Z","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":"2406.01581","last_updated":"2024-12-22T09:59:09Z","snapshot_observed_at":"2026-08-04T02:53:19.400873Z","submitted_at":"2024-06-03T17:56:58Z","title":"Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01581","snapshot_observed_at":"2026-08-08T15:34:16.709105Z","title":"Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.709105Z"},"links":{"cited_paper":"/paper/2406.01581","citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:c4c3915e84234500a544c421106fa4aa8d69d43959855bb5e2124195631f83f4","observation_id":"048d95b9-6d3e-4161-a529-51d4dcb91ca0","resolution":{"observed_at":"2026-08-08T15:34:16.709105Z","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":"2026-08-08T15:34:17.308449Z","title":"Gradient-based feature learning under structured data","venue":null,"work_id":"d214f6cd-079e-4d38-a683-9aa9c31282ec","year":2023},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.712940Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:8557598322a4d566a6dae0890b43b4dca804c2da9de399ae213469e7717c1a62","observation_id":"938358ae-9035-4b93-82e8-9a8dfd13b6dd","resolution":{"observed_at":"2026-08-08T15:34:17.313298Z","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":"2026-08-08T15:34:17.293667Z","title":"Quantifying the benefit of using differentiable learning over tangent kernels","venue":null,"work_id":"6c988bfd-a8a1-4974-bb3d-f572de44c244","year":2021},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.717069Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:993e26656dd455d6010225d1955add8945813c6b8e862a39bb757679d9a0cda4","observation_id":"b5a2bf39-2c45-4581-9f20-7566c727d531","resolution":{"observed_at":"2026-08-08T15:34:17.298228Z","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":"2026-08-08T15:34:17.279960Z","title":"Learning functions of k relevant variables","venue":null,"work_id":"8af303b3-af99-40e5-b868-2d09623d7fb7","year":2004},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.721364Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:e5d1b6d062c7ea704d9528bd10b8313c456de2636049226b559c295563b194f1","observation_id":"c09bdb26-4a94-4859-ac56-f7581795ecf3","resolution":{"observed_at":"2026-08-08T15:34:17.284387Z","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":"2026-08-08T15:34:17.266190Z","title":"Concentration inequalities under sub- G aussian and sub-exponential conditions","venue":null,"work_id":"322a6bcf-1050-49c3-a14d-1ad94e1d929f","year":2021},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.725494Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:dc3f8274d2a7c4c831f57e20e958f291de6697bbbbbbad6d762392f46b8e3f73","observation_id":"1a756173-9421-42c6-8cb7-f1feddc0a282","resolution":{"observed_at":"2026-08-08T15:34:17.270756Z","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":"2026-08-08T15:34:17.252275Z","title":"Improved statistical and computational complexity of the mean-field L angevin dynamics under structured data","venue":null,"work_id":"a2447d44-61d3-4f6f-b2c1-96265768675c","year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.729622Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:6f79a3e401572b5f53f92c684d8c0126a7e8ba51ce5a50c4705b9a2e19606e02","observation_id":"b0e1cfe9-d2bf-4d28-8b35-c611a5bea50f","resolution":{"observed_at":"2026-08-08T15:34:17.257092Z","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":"2026-08-08T15:34:17.239133Z","title":"Nazarov, M","venue":null,"work_id":"4aa12258-6efc-4b10-8d1b-89fe119ecc0d","year":2003},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.733631Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:cd0c3e87d32b9cb235c41b8b7e1b132d276ab7562a7fb1bf37ad5d8b183b6f76","observation_id":"3baf2ad4-39ab-4ae9-8714-7e929712ae70","resolution":{"observed_at":"2026-08-08T15:34:17.243310Z","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":"2026-08-08T15:34:16.737858Z","title":"Analysis of Boolean Functions","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.737858Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:bf84f1baae4cffe14698143e6bb95e67378d9708b05c3b0315a656a501fcb6ae","observation_id":"1c431418-582c-4e8f-9f5b-9b163aa59e7f","resolution":{"observed_at":"2026-08-08T15:34:16.737858Z","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":"2026-08-08T15:34:17.217087Z","title":"Distribution-specific hardness of learning neural networks","venue":null,"work_id":"0c382a4d-e15b-431d-b69f-aacc39ed257d","year":2018},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.742129Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:2ace55d59d19fe46a76ba78b41e3a0fa56181499390b1a01e32164b5968045a1","observation_id":"659b52ab-6a49-4803-993c-28fc5935c072","resolution":{"observed_at":"2026-08-08T15:34:17.221516Z","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":"2026-08-08T15:34:16.746356Z","title":"Understanding machine learning: From theory to algorithms","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.746356Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:35d988d0f847e0f966effb20d042ab7760d8042958b57c45638ee95aae2a5aa0","observation_id":"9e85e2f9-be02-4b90-91a1-5907b9b1a006","resolution":{"observed_at":"2026-08-08T15:34:16.746356Z","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":"2026-08-08T15:34:17.195365Z","title":"Smoothed analysis of algorithms: Why the simplex algorithm usually takes polynomial time","venue":null,"work_id":"5ba16cac-643a-4f95-a2fc-97c75c14a8c3","year":2001},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.750526Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:74f85edc30b61987ed5596deac46ab1bfda04904fd2aff5d2a9d488363ab7eec","observation_id":"3aa2e627-3c88-41d3-ad02-f3c7fe8f649f","resolution":{"observed_at":"2026-08-08T15:34:17.199475Z","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":"2026-08-08T15:34:17.181365Z","title":"On the cryptographic hardness of learning single periodic neurons","venue":null,"work_id":"bd1948a1-e7aa-474b-a6a7-5bc446261921","year":2021},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.754722Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:383a671a6cf07fcb0d914beb945a361af46df12402074550f60bbf64d721576d","observation_id":"da7c7c31-73f0-497c-9602-dc602e4cdebd","resolution":{"observed_at":"2026-08-08T15:34:17.185624Z","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":"2026-08-08T15:34:16.758763Z","title":"Fundamental limits of weak learnability in high-dimensional multi-index models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.758763Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:553db6c1eb567d0b5684dc40edd9c8641b4d6fb30fb62113fe551d1cc10accb1","observation_id":"b3580926-7514-4c0c-87f7-36a62cb99ca3","resolution":{"observed_at":"2026-08-08T15:34:16.758763Z","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":"2026-08-08T15:34:16.762720Z","title":"Finding correlations in subquadratic time, with applications to learning parities and juntas","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.762720Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:fa2dacec3915d23f1bfc1df635c9bfe73c6b2b3671ae4fed9f3ff8dfe773a0c3","observation_id":"35c627cf-c135-4abc-9339-488718355a1d","resolution":{"observed_at":"2026-08-08T15:34:16.762720Z","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":"2026-08-08T15:34:17.159849Z","title":"Learning a single neuron for non-monotonic activation functions","venue":null,"work_id":"b7d21a4f-3602-4f2c-9204-33ec1a934302","year":2022},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.766940Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:bb1888e22d9946384612611474f5eca7a3ee32918f727dcd600f9ffbd5c20e6c","observation_id":"f488407b-4d6b-4e70-a5d9-42ca546aa736","resolution":{"observed_at":"2026-08-08T15:34:17.163944Z","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":"2026-08-08T15:34:17.146850Z","title":"Learning a single neuron with gradient methods","venue":null,"work_id":"350ccdff-320a-4d35-bc69-d2fd1d6893af","year":2020},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.771353Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:3336c75690532b113e3c700b60c299d047c6feaee9aed7ec4c39e702dc41a3bf","observation_id":"b509c07e-1dd2-4af9-b201-fe406fa9287c","resolution":{"observed_at":"2026-08-08T15:34:17.151188Z","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":"2026-08-08T15:34:17.133113Z","title":"On single-index models beyond G aussian data","venue":null,"work_id":"fa04be5f-d4f5-4343-812c-33ca9bdcdcd0","year":2024},"citing_paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-08T15:34:16.775757Z"},"links":{"citing_paper":"/paper/2502.06443"},"observation_digest":"sha256:216dfd894e16bc644b4bfeab7e8deb6c14eac8d191989588cac88774152f357a","observation_id":"6a79dd2e-dad1-43f2-a6e0-01ab24b836db","resolution":{"observed_at":"2026-08-08T15:34:17.137644Z","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"}}],"paper":{"arxiv_id":"2502.06443","last_updated":"2025-07-21T10:48:50Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T15:22:58.731880Z","submitted_at":"2025-02-10T13:19:30Z","title":"Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions"},"reference_resolution":{"displayed":53,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":2,"verified_fuzzy":35},"total_outbound_references":53},"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 9 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 3 inbound Pith citation observations for arXiv:2502.06443."}