{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PONPCCGDLSV3MWKQXQEEAQQEB4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"20d2ac1ef485fd365a3f9bf5c2182abf093f9f29bcf4179d8845e958b01dfe36","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T05:13:28Z","title_canon_sha256":"2bec50ed729cf2d43d4052d05cc6e4335f52c99a20c1d855c040e18ca8323f71"},"schema_version":"1.0","source":{"id":"2407.02811","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02811","created_at":"2026-07-05T11:46:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02811v3","created_at":"2026-07-05T11:46:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02811","created_at":"2026-07-05T11:46:34Z"},{"alias_kind":"pith_short_12","alias_value":"PONPCCGDLSV3","created_at":"2026-07-05T11:46:34Z"},{"alias_kind":"pith_short_16","alias_value":"PONPCCGDLSV3MWKQ","created_at":"2026-07-05T11:46:34Z"},{"alias_kind":"pith_short_8","alias_value":"PONPCCGD","created_at":"2026-07-05T11:46:34Z"}],"graph_snapshots":[{"event_id":"sha256:baf5320af69e60bb6798a189828df0f342b60d21dee9cd311dbe6794f623ff05","target":"graph","created_at":"2026-07-05T11:46:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.02811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Certifiable robustness gives the guarantee that small perturbations around an input to a classifier will not change the prediction. There are two approaches to provide certifiable robustness to adversarial examples: a) explicitly training classifiers with small Lipschitz constants, and b) Randomized smoothing, which adds random noise to the input to create a smooth classifier. We propose SPLITZ, a practical and novel approach which leverages the synergistic benefits of both the above ideas into a single framework. Our main idea is to split a classifier into two halves, constrain the Lipschitz ","authors_text":"Meiyu Zhong, Ravi Tandon","cross_cats":["cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T05:13:28Z","title":"SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02811","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:42f882c93ea9578d0a7bac4986dd6b6669cda557353d5935dea183cd9eac6c90","target":"record","created_at":"2026-07-05T11:46:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"20d2ac1ef485fd365a3f9bf5c2182abf093f9f29bcf4179d8845e958b01dfe36","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T05:13:28Z","title_canon_sha256":"2bec50ed729cf2d43d4052d05cc6e4335f52c99a20c1d855c040e18ca8323f71"},"schema_version":"1.0","source":{"id":"2407.02811","kind":"arxiv","version":3}},"canonical_sha256":"7b9af108c35cabb65950bc084042040f2bd5067d38d39498269e8203ba4eee2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b9af108c35cabb65950bc084042040f2bd5067d38d39498269e8203ba4eee2f","first_computed_at":"2026-07-05T11:46:34.981062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:34.981062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TFjr7hCpehNvf2wWRUedfqcynyuySpvd6PFelUXiTRtk5E64Mh/C5ciwsxY4OKJaXbd9BW0q3+XzQWUNq0OYCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:34.981544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02811","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42f882c93ea9578d0a7bac4986dd6b6669cda557353d5935dea183cd9eac6c90","sha256:baf5320af69e60bb6798a189828df0f342b60d21dee9cd311dbe6794f623ff05"],"state_sha256":"03107e58a728b2390f33c41838693b0fe63b8dc2b7b73677b8206cb5d57581ef"}