{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WV5UTD4MZYQPEU5RHSQCDYSSOJ","short_pith_number":"pith:WV5UTD4M","schema_version":"1.0","canonical_sha256":"b57b498f8cce20f253b13ca021e2527265425f3ad8d9ebc5cabc7097d4e7e6de","source":{"kind":"arxiv","id":"2102.08093","version":2},"attestation_state":"computed","paper":{"title":"A Law of Robustness for Weight-bounded Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Borja Balle, Hisham Husain","submitted_at":"2021-02-16T11:28:59Z","abstract_excerpt":"Robustness of deep neural networks against adversarial perturbations is a pressing concern motivated by recent findings showing the pervasive nature of such vulnerabilities. One method of characterizing the robustness of a neural network model is through its Lipschitz constant, which forms a robustness certificate. A natural question to ask is, for a fixed model class (such as neural networks) and a dataset of size $n$, what is the smallest achievable Lipschitz constant among all models that fit the dataset? Recently, (Bubeck et al., 2020) conjectured that when using two-layer networks with $k"},"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":"2102.08093","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-16T11:28:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"225993e39cbfc893b9666c73df9ad55f9a92a60b7dbeb7c8240854d2009fa1b2","abstract_canon_sha256":"a52e7ed9efda99bfea78f21f430bc8a4d44d230e2968af4b6b0583188c9578af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:25.844712Z","signature_b64":"QGIkNq/r5BpX0y5VykC1uiV+zr8Sdb2rPBD9TiEYb3Xau5V/eeYEKSWTyBRmpCVRnfSarqiCKevQfbKyCmzlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b57b498f8cce20f253b13ca021e2527265425f3ad8d9ebc5cabc7097d4e7e6de","last_reissued_at":"2026-07-05T02:22:25.844305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:25.844305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Law of Robustness for Weight-bounded Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Borja Balle, Hisham Husain","submitted_at":"2021-02-16T11:28:59Z","abstract_excerpt":"Robustness of deep neural networks against adversarial perturbations is a pressing concern motivated by recent findings showing the pervasive nature of such vulnerabilities. One method of characterizing the robustness of a neural network model is through its Lipschitz constant, which forms a robustness certificate. A natural question to ask is, for a fixed model class (such as neural networks) and a dataset of size $n$, what is the smallest achievable Lipschitz constant among all models that fit the dataset? Recently, (Bubeck et al., 2020) conjectured that when using two-layer networks with $k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08093","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/2102.08093/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":"2102.08093","created_at":"2026-07-05T02:22:25.844378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.08093v2","created_at":"2026-07-05T02:22:25.844378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08093","created_at":"2026-07-05T02:22:25.844378+00:00"},{"alias_kind":"pith_short_12","alias_value":"WV5UTD4MZYQP","created_at":"2026-07-05T02:22:25.844378+00:00"},{"alias_kind":"pith_short_16","alias_value":"WV5UTD4MZYQPEU5R","created_at":"2026-07-05T02:22:25.844378+00:00"},{"alias_kind":"pith_short_8","alias_value":"WV5UTD4M","created_at":"2026-07-05T02:22:25.844378+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/WV5UTD4MZYQPEU5RHSQCDYSSOJ","json":"https://pith.science/pith/WV5UTD4MZYQPEU5RHSQCDYSSOJ.json","graph_json":"https://pith.science/api/pith-number/WV5UTD4MZYQPEU5RHSQCDYSSOJ/graph.json","events_json":"https://pith.science/api/pith-number/WV5UTD4MZYQPEU5RHSQCDYSSOJ/events.json","paper":"https://pith.science/paper/WV5UTD4M"},"agent_actions":{"view_html":"https://pith.science/pith/WV5UTD4MZYQPEU5RHSQCDYSSOJ","download_json":"https://pith.science/pith/WV5UTD4MZYQPEU5RHSQCDYSSOJ.json","view_paper":"https://pith.science/paper/WV5UTD4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.08093&json=true","fetch_graph":"https://pith.science/api/pith-number/WV5UTD4MZYQPEU5RHSQCDYSSOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WV5UTD4MZYQPEU5RHSQCDYSSOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WV5UTD4MZYQPEU5RHSQCDYSSOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WV5UTD4MZYQPEU5RHSQCDYSSOJ/action/storage_attestation","attest_author":"https://pith.science/pith/WV5UTD4MZYQPEU5RHSQCDYSSOJ/action/author_attestation","sign_citation":"https://pith.science/pith/WV5UTD4MZYQPEU5RHSQCDYSSOJ/action/citation_signature","submit_replication":"https://pith.science/pith/WV5UTD4MZYQPEU5RHSQCDYSSOJ/action/replication_record"}},"created_at":"2026-07-05T02:22:25.844378+00:00","updated_at":"2026-07-05T02:22:25.844378+00:00"}