{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LSG3BAFDTAJQT5XT6WOYWX27S4","short_pith_number":"pith:LSG3BAFD","schema_version":"1.0","canonical_sha256":"5c8db080a3981309f6f3f59d8b5f5f97213b9faf4d58b9a9b8ce54b8e22bdedd","source":{"kind":"arxiv","id":"2307.00426","version":2},"attestation_state":"computed","paper":{"title":"Sparsity-aware generalization theory for deep neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jeremias Sulam, Ramchandran Muthukumar","submitted_at":"2023-07-01T20:59:05Z","abstract_excerpt":"Deep artificial neural networks achieve surprising generalization abilities that remain poorly understood. In this paper, we present a new approach to analyzing generalization for deep feed-forward ReLU networks that takes advantage of the degree of sparsity that is achieved in the hidden layer activations. By developing a framework that accounts for this reduced effective model size for each input sample, we are able to show fundamental trade-offs between sparsity and generalization. Importantly, our results make no strong assumptions about the degree of sparsity achieved by the model, and it"},"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":"2307.00426","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-01T20:59:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"361339761ddc52a2c91eb9ad0e5c3904de212ba2dcd290b1a93d487d69869667","abstract_canon_sha256":"32d142677838fd205f5e42a5feacd60034d526824cb4888bbd9e03d0ffc6080f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:52.591834Z","signature_b64":"uQPz63NSCo3hOK7fMacxjnKHmuyDhcGoIRcWXkx8bve51nlsrSWJ6huw3KBzOEpArxlX+vMR6PIDROvmRVa7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c8db080a3981309f6f3f59d8b5f5f97213b9faf4d58b9a9b8ce54b8e22bdedd","last_reissued_at":"2026-07-05T06:27:52.591416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:52.591416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparsity-aware generalization theory for deep neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jeremias Sulam, Ramchandran Muthukumar","submitted_at":"2023-07-01T20:59:05Z","abstract_excerpt":"Deep artificial neural networks achieve surprising generalization abilities that remain poorly understood. In this paper, we present a new approach to analyzing generalization for deep feed-forward ReLU networks that takes advantage of the degree of sparsity that is achieved in the hidden layer activations. By developing a framework that accounts for this reduced effective model size for each input sample, we are able to show fundamental trade-offs between sparsity and generalization. Importantly, our results make no strong assumptions about the degree of sparsity achieved by the model, and it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00426","kind":"arxiv","version":2},"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/2307.00426/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":"2307.00426","created_at":"2026-07-05T06:27:52.591468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00426v2","created_at":"2026-07-05T06:27:52.591468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00426","created_at":"2026-07-05T06:27:52.591468+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSG3BAFDTAJQ","created_at":"2026-07-05T06:27:52.591468+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSG3BAFDTAJQT5XT","created_at":"2026-07-05T06:27:52.591468+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSG3BAFD","created_at":"2026-07-05T06:27:52.591468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSG3BAFDTAJQT5XT6WOYWX27S4","json":"https://pith.science/pith/LSG3BAFDTAJQT5XT6WOYWX27S4.json","graph_json":"https://pith.science/api/pith-number/LSG3BAFDTAJQT5XT6WOYWX27S4/graph.json","events_json":"https://pith.science/api/pith-number/LSG3BAFDTAJQT5XT6WOYWX27S4/events.json","paper":"https://pith.science/paper/LSG3BAFD"},"agent_actions":{"view_html":"https://pith.science/pith/LSG3BAFDTAJQT5XT6WOYWX27S4","download_json":"https://pith.science/pith/LSG3BAFDTAJQT5XT6WOYWX27S4.json","view_paper":"https://pith.science/paper/LSG3BAFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00426&json=true","fetch_graph":"https://pith.science/api/pith-number/LSG3BAFDTAJQT5XT6WOYWX27S4/graph.json","fetch_events":"https://pith.science/api/pith-number/LSG3BAFDTAJQT5XT6WOYWX27S4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSG3BAFDTAJQT5XT6WOYWX27S4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSG3BAFDTAJQT5XT6WOYWX27S4/action/storage_attestation","attest_author":"https://pith.science/pith/LSG3BAFDTAJQT5XT6WOYWX27S4/action/author_attestation","sign_citation":"https://pith.science/pith/LSG3BAFDTAJQT5XT6WOYWX27S4/action/citation_signature","submit_replication":"https://pith.science/pith/LSG3BAFDTAJQT5XT6WOYWX27S4/action/replication_record"}},"created_at":"2026-07-05T06:27:52.591468+00:00","updated_at":"2026-07-05T06:27:52.591468+00:00"}