{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZOQKHEORORI4QZRGAINOF5RIDQ","short_pith_number":"pith:ZOQKHEOR","schema_version":"1.0","canonical_sha256":"cba0a391d17451c86626021ae2f6281c17a8c41e19e377747e81421630177741","source":{"kind":"arxiv","id":"1802.08760","version":3},"attestation_state":"computed","paper":{"title":"Sensitivity and Generalization in Neural Networks: an Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Daniel A. Abolafia, Jascha Sohl-Dickstein, Jeffrey Pennington, Roman Novak, Yasaman Bahri","submitted_at":"2018-02-23T23:11:07Z","abstract_excerpt":"In practice it is often found that large over-parameterized neural networks generalize better than their smaller counterparts, an observation that appears to conflict with classical notions of function complexity, which typically favor smaller models. In this work, we investigate this tension between complexity and generalization through an extensive empirical exploration of two natural metrics of complexity related to sensitivity to input perturbations. Our experiments survey thousands of models with various fully-connected architectures, optimizers, and other hyper-parameters, as well as fou"},"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":"1802.08760","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-23T23:11:07Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"60171ff3691a5411cdb28d2ac31292d12f7f0d4665d89ee346a880db54dac3b0","abstract_canon_sha256":"21e6707154bfeff28f92fae137532d946bf53bdc0c07b4b33686188f3dacdff7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:58.500585Z","signature_b64":"d82aMedEesaDY9YEK0iuJEIA4Xa9M0MHvYr6CfFxrCEbCvfswlBn3GBvRGmqVGNsuYiv+7C0ZSysCmRnoQjoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cba0a391d17451c86626021ae2f6281c17a8c41e19e377747e81421630177741","last_reissued_at":"2026-05-18T00:12:58.499853Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:58.499853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sensitivity and Generalization in Neural Networks: an Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Daniel A. Abolafia, Jascha Sohl-Dickstein, Jeffrey Pennington, Roman Novak, Yasaman Bahri","submitted_at":"2018-02-23T23:11:07Z","abstract_excerpt":"In practice it is often found that large over-parameterized neural networks generalize better than their smaller counterparts, an observation that appears to conflict with classical notions of function complexity, which typically favor smaller models. In this work, we investigate this tension between complexity and generalization through an extensive empirical exploration of two natural metrics of complexity related to sensitivity to input perturbations. Our experiments survey thousands of models with various fully-connected architectures, optimizers, and other hyper-parameters, as well as fou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08760","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.08760","created_at":"2026-05-18T00:12:58.499969+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08760v3","created_at":"2026-05-18T00:12:58.499969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08760","created_at":"2026-05-18T00:12:58.499969+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOQKHEORORI4","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOQKHEORORI4QZRG","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOQKHEOR","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16349","citing_title":"Geometric Asymmetry in MoE Specialization: Functional Decorrelation and Representational Overlap","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03068","citing_title":"Escape dynamics and implicit bias of one-pass SGD in overparameterized quadratic networks","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24393","citing_title":"Complexity of Linear Regions in Self-supervised Deep ReLU Networks","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00510","citing_title":"Scale-Aware Adversarial Analysis: A Diagnostic for Generative AI in Multiscale Complex Systems","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOQKHEORORI4QZRGAINOF5RIDQ","json":"https://pith.science/pith/ZOQKHEORORI4QZRGAINOF5RIDQ.json","graph_json":"https://pith.science/api/pith-number/ZOQKHEORORI4QZRGAINOF5RIDQ/graph.json","events_json":"https://pith.science/api/pith-number/ZOQKHEORORI4QZRGAINOF5RIDQ/events.json","paper":"https://pith.science/paper/ZOQKHEOR"},"agent_actions":{"view_html":"https://pith.science/pith/ZOQKHEORORI4QZRGAINOF5RIDQ","download_json":"https://pith.science/pith/ZOQKHEORORI4QZRGAINOF5RIDQ.json","view_paper":"https://pith.science/paper/ZOQKHEOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08760&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOQKHEORORI4QZRGAINOF5RIDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOQKHEORORI4QZRGAINOF5RIDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOQKHEORORI4QZRGAINOF5RIDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOQKHEORORI4QZRGAINOF5RIDQ/action/storage_attestation","attest_author":"https://pith.science/pith/ZOQKHEORORI4QZRGAINOF5RIDQ/action/author_attestation","sign_citation":"https://pith.science/pith/ZOQKHEORORI4QZRGAINOF5RIDQ/action/citation_signature","submit_replication":"https://pith.science/pith/ZOQKHEORORI4QZRGAINOF5RIDQ/action/replication_record"}},"created_at":"2026-05-18T00:12:58.499969+00:00","updated_at":"2026-05-18T00:12:58.499969+00:00"}