{"as_of":"2026-08-09T19:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:99f33a462a19afed18e8853f16dc3e48d0f589df5fe65cde3b35f894c855b682","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T16:11:46.109289Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.06300/citation-record","integrity":"/paper/2502.06300/integrity","json":"/paper/2502.06300/citation-record.json","paper":"/paper/2502.06300"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.744578Z","title":"Thirst regulates motivated behavior through modulation of brainwide neural population dynamics","venue":null,"work_id":"56f3fd4f-cf62-4deb-91fd-3331d5aa8874","year":2019},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.954617Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:533d1a3fa2a24f0dacca4a0f176efbc65e099643f1ea779f30675972d7651de6","observation_id":"657d6430-3bd4-4355-9257-79195d253727","resolution":{"observed_at":"2026-08-08T16:12:31.747971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1002/9780470434642","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:11:46.159349Z","title":"Level sets and extrema of random processes and fields","venue":null,"work_id":"24e200b5-5509-4922-8bf6-44654bbe8858","year":2009},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.958412Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:502452257aa837624132ff2541581df00bf5abae87117f3f43df343d63644692","observation_id":"b4f11b1e-3675-42c5-8619-352fc3601918","resolution":{"observed_at":"2026-08-08T16:11:46.162863Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.735820Z","title":"Recurrent neural networks as versatile tools of neuroscience research","venue":null,"work_id":"917f0da9-58c1-48a3-b419-ab749d9a3078","year":2017},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.962188Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:7c12dd795b52117d7b59ea497eda6129a2069e32377b42a52e345ec039c34310","observation_id":"5e836c03-24b8-47ee-8b2e-a3a317a7877d","resolution":{"observed_at":"2026-08-08T16:12:31.738948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.727605Z","title":"A map of anticipatory activity in mouse motor cortex","venue":null,"work_id":"5029c803-3642-41f9-9ff3-b1e1d1cf9063","year":2017},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.965588Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:f0548e8608efd14a7e98abbbff0a08485c14dfef2763239e8ea0375957f19a6e","observation_id":"d42cea96-24a0-445f-9e98-b65800d503dc","resolution":{"observed_at":"2026-08-08T16:12:31.730546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1509.05009","last_updated":"2016-05-27T19:07:22Z","snapshot_observed_at":"2026-08-06T16:54:38.783792Z","submitted_at":"2015-09-16T19:32:54Z","title":"On the Expressive Power of Deep Learning: A Tensor Analysis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1509.05009","snapshot_observed_at":"2026-08-08T16:11:45.969646Z","title":"On the expressive power of deep learning: A tensor analysis, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.969646Z"},"links":{"cited_paper":"/paper/1509.05009","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:5e3845923447ea62052ed9b277557f34411841af7402ed8b151f06b0fb9e7f0b","observation_id":"3e7bb256-ecdc-4fc4-87c4-e55f6c07cc58","resolution":{"observed_at":"2026-08-08T16:11:45.969646Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.09913","last_updated":"2017-03-03T17:39:34Z","snapshot_observed_at":"2026-07-06T05:20:39.825511Z","submitted_at":"2016-11-29T22:13:20Z","title":"Capacity and Trainability in Recurrent Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.09913","snapshot_observed_at":"2026-08-08T16:11:45.973770Z","title":"Capacity and trainability in recurrent neural networks, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.973770Z"},"links":{"cited_paper":"/paper/1611.09913","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:9f4b53d3c3c277d7add0175ddb5943383bdae0409b23bdf320932d69ff872b7e","observation_id":"eb840a72-9483-4216-8dd7-133fe6a15caf","resolution":{"observed_at":"2026-08-08T16:11:45.973770Z","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":"2026-08-08T16:12:31.718745Z","title":"Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition","venue":null,"work_id":"8c075882-02d7-4c22-88ab-0cfabae7e074","year":1965},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.977629Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:f12bf7ecff0e92d263aff91c1a77aed69a84229260de14eb68c31b3d85c3aeec","observation_id":"561be448-1a59-4610-9298-954e8feede17","resolution":{"observed_at":"2026-08-08T16:12:31.722146Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.710210Z","title":null,"venue":null,"work_id":"dfbf40a1-68f4-4109-97f5-cc45e4532255","year":1989},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.980806Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:c27f9b20dff3d0bc30487b6f1c598269cf43e9e2d1ed146a73b25c783ff7ea7a","observation_id":"56bbb126-6744-4775-8123-115a2e81a5d5","resolution":{"observed_at":"2026-08-08T16:12:31.713252Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.701111Z","title":"Targeted photostimulation uncovers circuit motifs supporting short-term memory","venue":null,"work_id":"03f7fa01-20db-416c-be5c-8d9d28d16e7e","year":2021},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.983720Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:b4459b19f08174982fb6a44c3c168d429127e963668fee054caf34b63419dd65","observation_id":"0b0b4f8b-2024-491b-94da-4ff28146895a","resolution":{"observed_at":"2026-08-08T16:12:31.704882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:11:45.986254Z","title":"Finding structure in time","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.986254Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:489a0a05dc0ed94e8ab05cde149af8f1df620462ab8662bdba8de7a2b92f067b","observation_id":"08ca4648-043b-4629-b11f-bcb26777cd34","resolution":{"observed_at":"2026-08-08T16:11:45.986254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.11146","last_updated":"2018-11-29T22:50:01Z","snapshot_observed_at":"2026-08-08T11:28:36.813476Z","submitted_at":"2018-06-28T19:06:26Z","title":"Adversarial Reprogramming of Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.11146","snapshot_observed_at":"2026-08-08T16:11:45.989204Z","title":"Elsayed, Ian Goodfellow, and Jascha Sohl-Dickstein","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.989204Z"},"links":{"cited_paper":"/paper/1806.11146","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:427dd0e273809d8cae7504698a395d617f150f554ef27b90abcb27484eb3ff48","observation_id":"bf27834c-4bf9-4fe0-a1bc-4ca301c2c666","resolution":{"observed_at":"2026-08-08T16:11:45.989204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.03466","last_updated":"2022-10-11T17:52:35Z","snapshot_observed_at":"2026-08-09T01:12:15.126211Z","submitted_at":"2022-06-07T17:37:22Z","title":"Adversarial Reprogramming Revisited","version":2},"cited_work":{"arxiv_id":"2206.03466","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.03466","snapshot_observed_at":"2026-08-08T16:12:31.525389Z","title":"Adversarial Reprogramming Revisited","venue":"cs.LG","work_id":"cc0cd70c-a97a-4382-8375-e51e184160ab","year":2022},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.992111Z"},"links":{"cited_paper":"/paper/2206.03466","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:082f76fde027b650ed37ef237c6518ed1f098abf56c5a5a68711a37ebf32d385","observation_id":"97b8bc65-ada3-467c-92b1-d9ce47ea2c8d","resolution":{"observed_at":"2026-08-08T16:12:31.528729Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.686654Z","title":"Connectivity underlying motor cortex activity during naturalistic goal-directed behavior","venue":null,"work_id":"72ae9ac0-8515-4c41-a689-23e9baff06de","year":2023},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.995112Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:f4b95aa725ce8c15f86f44385192081b64f5af3111c154bc840138c150dda5f7","observation_id":"d3a37d32-a0ad-4b17-9aa7-334863b21699","resolution":{"observed_at":"2026-08-08T16:12:31.689997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.03635","last_updated":"2019-03-04T15:51:11Z","snapshot_observed_at":"2026-08-05T23:54:27.386622Z","submitted_at":"2018-03-09T18:51:28Z","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.03635","snapshot_observed_at":"2026-08-08T16:11:45.997704Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:45.997704Z"},"links":{"cited_paper":"/paper/1803.03635","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:a29f0b0fe106e0a633ecd411ca77321893a4a379478a0da54716e699d9811479","observation_id":"4b2badcf-0e7f-43e6-8585-5851276d9d63","resolution":{"observed_at":"2026-08-08T16:11:45.997704Z","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":"2026-08-08T16:11:46.000898Z","title":"Three unfinished works on the optimal storage capacity of networks","venue":null,"work_id":null,"year":1983},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.000898Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:d65f80288f73df43c8f348d03afb0f592eba2824d67a292021e1b91724accf62","observation_id":"53b11dc5-4bed-4b72-9beb-441532fbe992","resolution":{"observed_at":"2026-08-08T16:11:46.000898Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.07937","last_updated":"2023-07-04T21:33:17Z","snapshot_observed_at":"2026-08-09T17:52:57.311558Z","submitted_at":"2023-02-15T20:44:31Z","title":"The Expressive Power of Tuning Only the Normalization Layers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.07937","snapshot_observed_at":"2026-08-08T16:11:46.003613Z","title":"The expressive power of tuning only the normalization layers, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.003613Z"},"links":{"cited_paper":"/paper/2302.07937","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:c906b7f6ca37449b446872f32a5dfafb729d21fe5005ead41429e08fc7c96cb8","observation_id":"ff89c698-7111-4163-8de0-ba3202f95ce3","resolution":{"observed_at":"2026-08-08T16:11:46.003613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.07463","last_updated":"2021-06-09T14:39:17Z","snapshot_observed_at":"2026-08-08T10:12:13.760366Z","submitted_at":"2020-12-14T12:34:01Z","title":"Parameter-Efficient Transfer Learning with Diff Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.07463","snapshot_observed_at":"2026-08-08T16:11:46.006589Z","title":"Rush, and Yoon Kim","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.006589Z"},"links":{"cited_paper":"/paper/2012.07463","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:3f2f495330f26770efead6af436a0022798ca8236a82d34b7c8ee36106e06133","observation_id":"7838acaa-e838-4641-b511-077621ac80ec","resolution":{"observed_at":"2026-08-08T16:11:46.006589Z","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":"2026-08-08T16:12:31.677873Z","title":"Labelling and optical erasure of synaptic memory traces in the motor cortex","venue":null,"work_id":"a4236514-8d96-4a6c-8cd0-af81758559f4","year":2015},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.009948Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:9a4e270c4f557c7aea4f60d0e9806639e94831a6f54424f7a6839f92ed80e954","observation_id":"49a81fee-9ee7-4f9c-8f28-fe2e6238a23f","resolution":{"observed_at":"2026-08-08T16:12:31.681104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.668487Z","title":"Heij, A.C.M","venue":null,"work_id":"c57c09ca-5c42-41d1-9b15-a39b9b43c098","year":2006},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.013005Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:7595723b075dd8b6cb2a183807b53ca3dabb5453f3866152afca63c7d958e223","observation_id":"92c08cad-12f2-4d76-bb45-5d8b4a3ff7b6","resolution":{"observed_at":"2026-08-08T16:12:31.671941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:11:46.015591Z","title":"Neural networks and physical systems with emergent collective computational abilities","venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.015591Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:a2495d93494e012d52ee9b3be3e48e279e5259da74429c825693c46a88cb78b8","observation_id":"ad01171d-b7ac-4f98-af0f-c8b4d25adb6f","resolution":{"observed_at":"2026-08-08T16:11:46.015591Z","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":"2026-08-08T16:12:31.653950Z","title":"Horn and Charles R","venue":null,"work_id":"f7720c32-29bd-49a6-91a5-51ca0c212936","year":1991},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.018454Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:a9a5c5b27af698863ad587771d8df641f39edea2956e85f4a0e42da1a1250c3c","observation_id":"dcfbea6f-0d05-450a-801a-5c22b75678e0","resolution":{"observed_at":"2026-08-08T16:12:31.657413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:11:46.021284Z","title":"Multilayer feedforward networks are universal approximators","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.021284Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:e385ee5fad717aee0c8559ce4250374dd06eeb949066eeee357129c2179e28bb","observation_id":"3184fa93-0ba0-49ce-89ab-b9e75c1e226a","resolution":{"observed_at":"2026-08-08T16:11:46.021284Z","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":"2026-08-08T16:12:31.645526Z","title":"The next generation of approaches to investigate the link between synaptic plasticity and learning","venue":null,"work_id":"ebf3dbce-f377-4717-b99d-90a85a91555f","year":2019},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.023735Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:d13681da60577fd72c90dae985e61a509ee4223b7c0b32199492d393bd611ed4","observation_id":"08cf2d93-915e-4be2-ab80-d4595af65d60","resolution":{"observed_at":"2026-08-08T16:12:31.648674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.636480Z","title":"Bci learning phenomena can be explained by gradient-based optimization","venue":null,"work_id":"9acfab7a-7f33-417a-b40e-0b2c645bb71a","year":2022},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.026666Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:1154e8c2808ace357b62a884275b94653d41d1c7311c481bffaca348db4b4da1","observation_id":"a0180c4a-e2fb-4844-8319-55ca774207d9","resolution":{"observed_at":"2026-08-08T16:12:31.639711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.09308","last_updated":"2024-03-03T20:32:24Z","snapshot_observed_at":"2026-07-06T14:43:38.836337Z","submitted_at":"2023-01-23T08:08:10Z","title":"On the Expressive Power of Geometric Graph Neural Networks","version":3},"cited_work":{"arxiv_id":"2301.09308","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.09308","snapshot_observed_at":"2026-08-08T16:12:16.444591Z","title":"On the Expressive Power of Geometric Graph Neural Networks","venue":"cs.LG","work_id":"e38679f0-bff0-4dfa-9ac6-eebf95c75b68","year":2023},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.029538Z"},"links":{"cited_paper":"/paper/2301.09308","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:b8af48831fd014b694fff533b7ecda41634e6a51df08db625637c2a2ec624f62","observation_id":"b6daeb80-7bf4-41a9-b51f-10ddb7217b47","resolution":{"observed_at":"2026-08-08T16:12:16.448213Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.00811","last_updated":"2018-02-07T21:43:25Z","snapshot_observed_at":"2026-08-09T02:20:50.224151Z","submitted_at":"2017-11-02T16:49:19Z","title":"Expressive power of recurrent neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.00811","snapshot_observed_at":"2026-08-08T16:11:46.032703Z","title":"Expressive power of recurrent neural networks, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.032703Z"},"links":{"cited_paper":"/paper/1711.00811","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:9ecba0306fab0ad1b130b0019e735c7c9e6aa3172f08ce95054484d632c603b2","observation_id":"239fb816-a744-4ed0-9333-ee38cecba0b5","resolution":{"observed_at":"2026-08-08T16:11:46.032703Z","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":"10.1038/s41467-023-38529-y","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:11:46.144427Z","title":"Kim, Arseny Finkelstein, Carson C","venue":null,"work_id":"cb9281c2-3c67-49f9-8676-bcc9bf13d5fc","year":2023},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.036038Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:bcb271b54a6e44f292355a105938fbe1e3f66ca13a3719387c98cd90f277f87d","observation_id":"b640e5c9-7073-40e1-9264-ba6ac8431a67","resolution":{"observed_at":"2026-08-08T16:11:46.147114Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-08T16:11:46.038690Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.038690Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:b0d85ecfc7e331b26d1eafd4031767a9875035efdd962043d569746315d9d01f","observation_id":"183fb14f-7871-4234-bdc5-789d1f57bff3","resolution":{"observed_at":"2026-08-08T16:11:46.038690Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.00585","last_updated":"2020-02-03T07:23:11Z","snapshot_observed_at":"2026-07-06T08:54:25.868963Z","submitted_at":"2020-02-03T07:23:11Z","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","version":1},"cited_work":{"arxiv_id":"2002.00585","doi":null,"metadata_source":"pith","pith_arxiv_id":"2002.00585","snapshot_observed_at":"2026-08-08T16:12:16.412776Z","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","venue":"cs.LG","work_id":"84195ee8-8d7c-480f-a5a0-40642b889e45","year":2020},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.041906Z"},"links":{"cited_paper":"/paper/2002.00585","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:8e40f7f1c730e534d0284f164b2eed99b92aff7fd17f5bdfb09a2195ca085fb5","observation_id":"b6bbba82-903d-4761-bb47-cbf4eb739b12","resolution":{"observed_at":"2026-08-08T16:12:16.416808Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05769","last_updated":"2018-05-13T16:48:51Z","snapshot_observed_at":"2026-08-09T02:59:37.531805Z","submitted_at":"2017-11-15T19:36:51Z","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05769","snapshot_observed_at":"2026-08-08T16:11:46.044751Z","title":"Packnet: Adding multiple tasks to a single network by iterative pruning, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.044751Z"},"links":{"cited_paper":"/paper/1711.05769","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:d3844ba6d55237f8ff333be4a8a17d54ac4db1685af66d2b53cf4c9b9339823a","observation_id":"0d8b0f5a-e18e-4202-938a-c8d361f16c67","resolution":{"observed_at":"2026-08-08T16:11:46.044751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.06519","last_updated":"2018-03-16T21:29:28Z","snapshot_observed_at":"2026-08-08T18:04:54.971362Z","submitted_at":"2018-01-19T18:25:59Z","title":"Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.06519","snapshot_observed_at":"2026-08-08T16:11:46.047526Z","title":"Piggyback: Adapting a single network to multiple tasks by learning to mask weights, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.047526Z"},"links":{"cited_paper":"/paper/1801.06519","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:27094f042717e3153f5dbde440d0cc6f3af3c2e08a6fd3c7bfa560a970c114a0","observation_id":"e8c25f34-005c-4cf5-ae1c-13b5840c63d6","resolution":{"observed_at":"2026-08-08T16:11:46.047526Z","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":"2026-08-08T16:12:31.626891Z","title":"Cortical layer--specific critical dynamics triggering perception","venue":null,"work_id":"c66aa860-031e-4161-9ea8-be27cdc37e48","year":2019},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.050709Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:408bb2b6b7209b911d2c54fedcbb479f19a5e8e1029741d8307e48e6717af5f8","observation_id":"6067268c-7c71-439d-b8c8-7b73bbcf2bbd","resolution":{"observed_at":"2026-08-08T16:12:31.630406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.618187Z","title":"Synaptic plasticity and memory: an evaluation of the hypothesis","venue":null,"work_id":"7b2dc25d-9516-4ddc-b7ec-e5b980b63983","year":2000},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.053515Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:708dfbb6f6eaf8b91059459f71cb598cab8522866a08fa4753c60586ba3187d4","observation_id":"9fdb45b3-e3a0-4854-8cdb-f2d02c11e721","resolution":{"observed_at":"2026-08-08T16:12:31.621168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1402.1869","last_updated":"2014-06-07T19:56:14Z","snapshot_observed_at":"2026-07-06T03:35:28.758073Z","submitted_at":"2014-02-08T17:16:27Z","title":"On the Number of Linear Regions of Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1402.1869","snapshot_observed_at":"2026-08-08T16:11:46.056357Z","title":"On the number of linear regions of deep neural networks, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.056357Z"},"links":{"cited_paper":"/paper/1402.1869","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:1e82a1123f322a0ea6ef487a4ed270fe29f4b24b77f5e227fec98a5f6b90aeeb","observation_id":"e3e3b201-32a8-4aa1-9a83-cee93919fcea","resolution":{"observed_at":"2026-08-08T16:11:46.056357Z","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":"2026-08-08T16:12:31.609970Z","title":"Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics","venue":null,"work_id":"6c0e36d8-7b97-48dc-b34f-819f98b39799","year":2024},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.059722Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:8c8b41154a432e0879611011454604e2f146813bc991bedd59a8cc5657171a14","observation_id":"412c2b68-479e-48f4-acc7-a46ee63e6784","resolution":{"observed_at":"2026-08-08T16:12:31.613000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.05336","last_updated":"2017-06-18T13:24:34Z","snapshot_observed_at":"2026-07-06T05:00:17.202185Z","submitted_at":"2016-06-16T19:55:29Z","title":"On the Expressive Power of Deep Neural Networks","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.05336","snapshot_observed_at":"2026-08-08T16:11:46.062877Z","title":"On the expressive power of deep neural networks, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.062877Z"},"links":{"cited_paper":"/paper/1606.05336","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:3b0ad5583b595cb526c58b0ffa0d813cfac3d21474ef6fd5cc18532c24c4a7a1","observation_id":"967d6b3f-9a22-400e-81d8-9bb198919690","resolution":{"observed_at":"2026-08-08T16:11:46.062877Z","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":"2026-08-08T16:12:31.601078Z","title":"Targeted activation of hippocampal place cells drives memory-guided spatial behavior","venue":null,"work_id":"6418c482-34c7-4e86-bb9d-4e497a7c2d08","year":2020},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.066407Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:062975e20495723b46db4b61bf74fdeff46aceea64b9d1aacd412778efb11a1a","observation_id":"abcf3b3f-3680-42bd-97b5-c2f951acefa0","resolution":{"observed_at":"2026-08-08T16:12:31.604138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.592495Z","title":"An analytical theory of curriculum learning in teacher-student networks","venue":null,"work_id":"f594a53f-ce8e-405b-95b0-a1e9f991b32f","year":2022},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.069539Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:be0e9b96f7aaa205ccda8013b4fa0eff9fda7ac009a2c5b30efb724453613998","observation_id":"ef47eeff-466d-44a9-82bc-f92df961fe8b","resolution":{"observed_at":"2026-08-08T16:12:31.595583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6120","last_updated":"2014-02-19T17:26:57Z","snapshot_observed_at":"2026-08-08T04:46:43.735461Z","submitted_at":"2013-12-20T20:24:00Z","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6120","snapshot_observed_at":"2026-08-08T16:11:46.072210Z","title":"Saxe, James L","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.072210Z"},"links":{"cited_paper":"/paper/1312.6120","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:d6d5ece20cc42099838647081f31a3d5ee92d344a9b07f7c59d1498fec65938d","observation_id":"fb8e4e09-6980-4712-81c6-59ae5cccb61c","resolution":{"observed_at":"2026-08-08T16:11:46.072210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.01423","last_updated":"2018-05-29T09:00:04Z","snapshot_observed_at":"2026-08-06T14:07:22.157424Z","submitted_at":"2018-01-04T16:22:22Z","title":"Overcoming catastrophic forgetting with hard attention to the task","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.01423","snapshot_observed_at":"2026-08-08T16:11:46.074773Z","title":"Overcoming catastrophic forgetting with hard attention to the task, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.074773Z"},"links":{"cited_paper":"/paper/1801.01423","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:4941bb6ebb87fa7f2c0b118c27ebe373e2e9664ec4c6dd487261ec3aae172d7a","observation_id":"44ca3ebe-4a4d-4d6e-8cae-d79635d997b4","resolution":{"observed_at":"2026-08-08T16:11:46.074773Z","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":"2026-08-08T16:11:46.077786Z","title":"Siegelmann and E.D","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.077786Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:d8164a44cfcd6aacbecf2d4523a61bac8739382754c52527649588b532ae8a47","observation_id":"c68534be-cc3a-41a8-96cb-9a22e55d447c","resolution":{"observed_at":"2026-08-08T16:11:46.077786Z","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":"10.1007/bf03025291","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:11:46.133883Z","title":"Mathematical problems for the next century","venue":null,"work_id":"cfc543c7-d8db-4e7b-a6f9-ba2b8e3e6416","year":1998},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.080680Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:77c19b9ccbe86f092670ffeb2be3192bb927bbe2d78f852d7d900ebd5f9b2668","observation_id":"f76e73ab-eaa2-4fab-b1b9-ff410664ae99","resolution":{"observed_at":"2026-08-08T16:11:46.138414Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.583516Z","title":"Distributed coding of choice, action and engagement across the mouse brain","venue":null,"work_id":"fe91a48d-54e9-4894-8fcf-11b895e01255","year":2019},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.083713Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:4951fdabc730cc0ffc36a0f2b7699e33905e487f533fcbdf0c220614c63c5e4c","observation_id":"1dd26141-ced0-4669-b36f-9ede40ea3f5d","resolution":{"observed_at":"2026-08-08T16:12:31.587215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.11924","last_updated":"2024-05-18T13:29:27Z","snapshot_observed_at":"2026-07-06T15:06:15.576863Z","submitted_at":"2023-03-21T15:15:48Z","title":"Concentration for the zero set of large random polynomial systems","version":2},"cited_work":{"arxiv_id":"2303.11924","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.11924","snapshot_observed_at":"2026-08-08T16:12:01.297938Z","title":"Concentration for the zero set of large random polynomial systems","venue":"math.PR","work_id":"570bed32-d54b-4e1a-8c28-ef8ea4a8ae47","year":2023},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.086448Z"},"links":{"cited_paper":"/paper/2303.11924","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:d83442bcf8635f317df169950a5a60aedde76fafd5176b2935476a8cc10c5a66","observation_id":"64819185-03e7-4095-8268-03c3983d178c","resolution":{"observed_at":"2026-08-08T16:12:01.301896Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.09839","last_updated":"2021-11-18T18:06:01Z","snapshot_observed_at":"2026-08-07T01:37:17.867619Z","submitted_at":"2021-11-18T18:06:01Z","title":"Training Neural Networks with Fixed Sparse Masks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.09839","snapshot_observed_at":"2026-08-08T16:11:46.089474Z","title":"Training neural networks with fixed sparse masks, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.089474Z"},"links":{"cited_paper":"/paper/2111.09839","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:04b9aeb335bc96a4bc43e26af820ede48e44875726b75bcb2d99a7d9aa288ea7","observation_id":"e9df0622-c8be-46af-9563-28cf55acb6fb","resolution":{"observed_at":"2026-08-08T16:11:46.089474Z","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":"2026-08-08T16:12:31.574511Z","title":"Spdf: sparse pre-training and dense fine-tuning for large language models","venue":null,"work_id":"d69fc22d-25a0-4875-8716-158aaf0d452e","year":2023},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.092504Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:8e03fe9a058e659a5e0a221ea109e34bbf50a9e3429dba3bb9db283cfe93be14","observation_id":"3f1e5748-9014-4869-a00a-6a08ce1496d5","resolution":{"observed_at":"2026-08-08T16:12:31.577823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:12:31.565227Z","title":"Optical interrogation of multi-scale neuronal plasticity underlying behavioral learning","venue":null,"work_id":"782b7427-4f2d-4c01-9f40-3c0f09a71834","year":2021},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.095268Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:c0c7851a1a5c361a7493ed7ee0c1d2131f8f38b63d5e3a921eb55a85a98fea72","observation_id":"7d7bd026-ee08-4764-a71b-63c835beac8c","resolution":{"observed_at":"2026-08-08T16:12:31.568450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.00487","last_updated":"2024-02-06T09:12:09Z","snapshot_observed_at":"2026-08-04T15:12:27.741364Z","submitted_at":"2023-01-31T11:34:56Z","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.00487","snapshot_observed_at":"2026-08-08T16:11:46.098179Z","title":"A comprehensive survey of continual learning: Theory, method and application, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.098179Z"},"links":{"cited_paper":"/paper/2302.00487","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:c722703916c9f098138c3a910065796a29a2cd80ce6073458592704ff4ba9a4a","observation_id":"d020ca52-96ca-4cf7-b4c8-21d4350f1402","resolution":{"observed_at":"2026-08-08T16:11:46.098179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.14769","last_updated":"2020-10-22T00:32:49Z","snapshot_observed_at":"2026-07-06T09:32:55.288150Z","submitted_at":"2020-06-26T03:16:44Z","title":"Supermasks in Superposition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.14769","snapshot_observed_at":"2026-08-08T16:11:46.101237Z","title":"Supermasks in superposition, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.101237Z"},"links":{"cited_paper":"/paper/2006.14769","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:a4565c01f67b2e7269a38544b30712bcf60d2f7866154f81241674ecc312acb5","observation_id":"41d4cfb0-7034-4d25-91fd-259b538edd32","resolution":{"observed_at":"2026-08-08T16:11:46.101237Z","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":"2026-08-08T16:12:31.556111Z","title":"Adahessian: An adaptive second order optimizer for machine learning","venue":null,"work_id":"f9367ebe-590b-412a-b40e-40f34fcc03f9","year":2021},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.104067Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:ae644696894d5ae683b0a939c88ee5cd2360bc292a4b32cfc1753961fcbee801","observation_id":"c132fa33-0180-4be6-9701-3edef01c3ffc","resolution":{"observed_at":"2026-08-08T16:12:31.559216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T16:11:46.106765Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.106765Z"},"links":{"citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:07b202f791f8d4f962295b240fb7dde6c69468037cf6fd34c9b88e43b0f453b4","observation_id":"7d90cd0b-db6e-4932-8f9b-8c821e872261","resolution":{"observed_at":"2026-08-08T16:11:46.106765Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.17513","last_updated":"2024-03-18T02:13:24Z","snapshot_observed_at":"2026-07-06T16:39:04.459332Z","submitted_at":"2023-10-26T16:08:33Z","title":"The Expressive Power of Low-Rank Adaptation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.17513","snapshot_observed_at":"2026-08-08T16:11:46.109289Z","title":"The expressive power of low-rank adaptation, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:46.109289Z"},"links":{"cited_paper":"/paper/2310.17513","citing_paper":"/paper/2502.06300"},"observation_digest":"sha256:e2dfc10ba6d1c834b0c6c80e5a0ba4591a794c80918208c071bc60e4ba11db1e","observation_id":"325e0aab-bde8-4d87-a78c-b91a0f83f94f","resolution":{"observed_at":"2026-08-08T16:11:46.109289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.06300","last_updated":"2025-02-10T09:43:43Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T13:45:52.887809Z","submitted_at":"2025-02-10T09:43:43Z","title":"The impact of allocation strategies in subset learning on the expressive power of neural networks"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":25,"verified_exact":6,"verified_fuzzy":20},"total_outbound_references":52},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2502.06300."}