{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YUTNEHI7YIRD4EB2T22NSS4RTB","short_pith_number":"pith:YUTNEHI7","schema_version":"1.0","canonical_sha256":"c526d21d1fc2223e103a9eb4d94b91984670e9f62598ecfa06cb70cc44dae273","source":{"kind":"arxiv","id":"2410.21696","version":4},"attestation_state":"computed","paper":{"title":"The Effects of Multi-Task Learning on ReLU Neural Network Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Joseph Shenouda, Julia Nakhleh, Robert D. Nowak","submitted_at":"2024-10-29T03:27:08Z","abstract_excerpt":"This paper studies the properties of solutions to multi-task shallow ReLU neural network learning problems, wherein the network is trained to fit a dataset with minimal sum of squared weights. Remarkably, the solutions learned for each individual task resemble those obtained by solving a kernel regression problem, revealing a novel connection between neural networks and kernel methods. It is known that single-task neural network learning problems are equivalent to a minimum norm interpolation problem in a non-Hilbertian Banach space, and that the solutions of such problems are generally non-un"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.21696","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-29T03:27:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b968609bb319c19713e8c7494961245441a00e3061a5b592cdfa5b4df4a7d63d","abstract_canon_sha256":"1f469f4f93382615591db75e2d04182d2f600a0333952a7e212e249e7e7ffb91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:41.310953Z","signature_b64":"kum+XosyWtAmm3Xakb4IztF+hdNJTR0I7fhNLJkVBfF60uCAx9TECZSMzwMN7gv5/bmwG5OQpzLgzB0mkey2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c526d21d1fc2223e103a9eb4d94b91984670e9f62598ecfa06cb70cc44dae273","last_reissued_at":"2026-07-05T10:20:41.310426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:41.310426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Effects of Multi-Task Learning on ReLU Neural Network Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Joseph Shenouda, Julia Nakhleh, Robert D. Nowak","submitted_at":"2024-10-29T03:27:08Z","abstract_excerpt":"This paper studies the properties of solutions to multi-task shallow ReLU neural network learning problems, wherein the network is trained to fit a dataset with minimal sum of squared weights. Remarkably, the solutions learned for each individual task resemble those obtained by solving a kernel regression problem, revealing a novel connection between neural networks and kernel methods. It is known that single-task neural network learning problems are equivalent to a minimum norm interpolation problem in a non-Hilbertian Banach space, and that the solutions of such problems are generally non-un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21696","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.21696/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.21696","created_at":"2026-07-05T10:20:41.310499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21696v4","created_at":"2026-07-05T10:20:41.310499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21696","created_at":"2026-07-05T10:20:41.310499+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUTNEHI7YIRD","created_at":"2026-07-05T10:20:41.310499+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUTNEHI7YIRD4EB2","created_at":"2026-07-05T10:20:41.310499+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUTNEHI7","created_at":"2026-07-05T10:20:41.310499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01763","citing_title":"On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning","ref_index":88,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YUTNEHI7YIRD4EB2T22NSS4RTB","json":"https://pith.science/pith/YUTNEHI7YIRD4EB2T22NSS4RTB.json","graph_json":"https://pith.science/api/pith-number/YUTNEHI7YIRD4EB2T22NSS4RTB/graph.json","events_json":"https://pith.science/api/pith-number/YUTNEHI7YIRD4EB2T22NSS4RTB/events.json","paper":"https://pith.science/paper/YUTNEHI7"},"agent_actions":{"view_html":"https://pith.science/pith/YUTNEHI7YIRD4EB2T22NSS4RTB","download_json":"https://pith.science/pith/YUTNEHI7YIRD4EB2T22NSS4RTB.json","view_paper":"https://pith.science/paper/YUTNEHI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21696&json=true","fetch_graph":"https://pith.science/api/pith-number/YUTNEHI7YIRD4EB2T22NSS4RTB/graph.json","fetch_events":"https://pith.science/api/pith-number/YUTNEHI7YIRD4EB2T22NSS4RTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUTNEHI7YIRD4EB2T22NSS4RTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUTNEHI7YIRD4EB2T22NSS4RTB/action/storage_attestation","attest_author":"https://pith.science/pith/YUTNEHI7YIRD4EB2T22NSS4RTB/action/author_attestation","sign_citation":"https://pith.science/pith/YUTNEHI7YIRD4EB2T22NSS4RTB/action/citation_signature","submit_replication":"https://pith.science/pith/YUTNEHI7YIRD4EB2T22NSS4RTB/action/replication_record"}},"created_at":"2026-07-05T10:20:41.310499+00:00","updated_at":"2026-07-05T10:20:41.310499+00:00"}