{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LWSR7EID57J77NOVHJNS552LRF","short_pith_number":"pith:LWSR7EID","schema_version":"1.0","canonical_sha256":"5da51f9103efd3ffb5d53a5b2ef74b895041483aae16c56df9ec9ce04bec3f4c","source":{"kind":"arxiv","id":"1908.02729","version":1},"attestation_state":"computed","paper":{"title":"Robust Learning with Jacobian Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Daniel A. Roberts, Judy Hoffman, Sho Yaida","submitted_at":"2019-08-07T17:04:26Z","abstract_excerpt":"Design of reliable systems must guarantee stability against input perturbations. In machine learning, such guarantee entails preventing overfitting and ensuring robustness of models against corruption of input data. In order to maximize stability, we analyze and develop a computationally efficient implementation of Jacobian regularization that increases classification margins of neural networks. The stabilizing effect of the Jacobian regularizer leads to significant improvements in robustness, as measured against both random and adversarial input perturbations, without severely degrading gener"},"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":"1908.02729","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-07T17:04:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"913489d03dedf6d8ec7ff9e4a871f5b92f7779ea3b2bce8b2ad4c1548ce3d9d1","abstract_canon_sha256":"7f93e82d4d924d55ce5558bd14765f077a43f68790c94dd28ea5bf7ac39ccfef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:11.670246Z","signature_b64":"UepHj/OKZn4DajlTepUjXQnqlVK9N3q3plUezDj8P99oXrEv7A5Gr+77/oJjNFBrA8KaNvsvRXukMTUUwuSxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5da51f9103efd3ffb5d53a5b2ef74b895041483aae16c56df9ec9ce04bec3f4c","last_reissued_at":"2026-07-04T23:52:11.669734Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:11.669734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Learning with Jacobian Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Daniel A. Roberts, Judy Hoffman, Sho Yaida","submitted_at":"2019-08-07T17:04:26Z","abstract_excerpt":"Design of reliable systems must guarantee stability against input perturbations. In machine learning, such guarantee entails preventing overfitting and ensuring robustness of models against corruption of input data. In order to maximize stability, we analyze and develop a computationally efficient implementation of Jacobian regularization that increases classification margins of neural networks. The stabilizing effect of the Jacobian regularizer leads to significant improvements in robustness, as measured against both random and adversarial input perturbations, without severely degrading gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02729","kind":"arxiv","version":1},"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/1908.02729/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":"1908.02729","created_at":"2026-07-04T23:52:11.669797+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.02729v1","created_at":"2026-07-04T23:52:11.669797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02729","created_at":"2026-07-04T23:52:11.669797+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWSR7EID57J7","created_at":"2026-07-04T23:52:11.669797+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWSR7EID57J77NOV","created_at":"2026-07-04T23:52:11.669797+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWSR7EID","created_at":"2026-07-04T23:52:11.669797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07375","citing_title":"On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23942","citing_title":"DREG: A Layer-Wise Jacobian Regularization as a General-Purpose Penalty","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00931","citing_title":"Explainable AI for Cancer Drug Response Prediction: Beyond Univariate Feature Attributions","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31581","citing_title":"Robustness of neural networks to random noise perturbations of their inputs","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29823","citing_title":"Quantifying and Optimizing Simplicity via Polynomial Representations","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09742","citing_title":"Upper Generalization Bounds for Neural Oscillators","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06680","citing_title":"On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21395","citing_title":"Supervised Learning Has a Necessary Geometric Blind Spot: Theory, Consequences, and Minimal Repair","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWSR7EID57J77NOVHJNS552LRF","json":"https://pith.science/pith/LWSR7EID57J77NOVHJNS552LRF.json","graph_json":"https://pith.science/api/pith-number/LWSR7EID57J77NOVHJNS552LRF/graph.json","events_json":"https://pith.science/api/pith-number/LWSR7EID57J77NOVHJNS552LRF/events.json","paper":"https://pith.science/paper/LWSR7EID"},"agent_actions":{"view_html":"https://pith.science/pith/LWSR7EID57J77NOVHJNS552LRF","download_json":"https://pith.science/pith/LWSR7EID57J77NOVHJNS552LRF.json","view_paper":"https://pith.science/paper/LWSR7EID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.02729&json=true","fetch_graph":"https://pith.science/api/pith-number/LWSR7EID57J77NOVHJNS552LRF/graph.json","fetch_events":"https://pith.science/api/pith-number/LWSR7EID57J77NOVHJNS552LRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWSR7EID57J77NOVHJNS552LRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWSR7EID57J77NOVHJNS552LRF/action/storage_attestation","attest_author":"https://pith.science/pith/LWSR7EID57J77NOVHJNS552LRF/action/author_attestation","sign_citation":"https://pith.science/pith/LWSR7EID57J77NOVHJNS552LRF/action/citation_signature","submit_replication":"https://pith.science/pith/LWSR7EID57J77NOVHJNS552LRF/action/replication_record"}},"created_at":"2026-07-04T23:52:11.669797+00:00","updated_at":"2026-07-04T23:52:11.669797+00:00"}