{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RIVHURFMCK3NXFYDRLXVNZBEKT","short_pith_number":"pith:RIVHURFM","schema_version":"1.0","canonical_sha256":"8a2a7a44ac12b6db97038aef56e42454ed21a423ea5219052c9c2ba2e877eb80","source":{"kind":"arxiv","id":"2605.12876","version":1},"attestation_state":"computed","paper":{"title":"Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Hybrid randomized smoothing yields a closed-form one-dimensional certificate that generalizes both Gaussian and discrete smoothing for joint discrete-continuous inputs.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Blaise Delattre, Hengyu Wu, Paul Caillon, Wei Yang Bryan Lim, Yang Cao","submitted_at":"2026-05-13T01:44:31Z","abstract_excerpt":"Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continuous and discrete inputs in isolation. This limitation becomes critical in multimodal models, where decisions depend on cross-modal semantics and adversaries can jointly perturb heterogeneous inputs, rendering unimodal certificates insufficient. We introduce a unified randomized smoothing framework for mixed discrete--continuous inputs based on an analytically tractable Neyman--Pearson formulation of the joint worst-case problem. By analyzing th"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T01:44:31Z","cross_cats_sorted":[],"title_canon_sha256":"069b08904844747f7c099c7513b19d1577d7dcb1e047a95182c64180e360d5a9","abstract_canon_sha256":"42a7e94add9dd79146598653c2462e5a6f2e250ada794afda1afee7286258a27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:11.204418Z","signature_b64":"SsvB51zXjEIGncsEzW0lW2nq2du/4ExpfLpgcUQAPxCM8RKk2/Gaf6l7JBEK/mVWXWquPhAHvI5MOKzK5W7PAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a2a7a44ac12b6db97038aef56e42454ed21a423ea5219052c9c2ba2e877eb80","last_reissued_at":"2026-05-18T03:09:11.203825Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:11.203825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Hybrid randomized smoothing yields a closed-form one-dimensional certificate that generalizes both Gaussian and discrete smoothing for joint discrete-continuous inputs.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Blaise Delattre, Hengyu Wu, Paul Caillon, Wei Yang Bryan Lim, Yang Cao","submitted_at":"2026-05-13T01:44:31Z","abstract_excerpt":"Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continuous and discrete inputs in isolation. This limitation becomes critical in multimodal models, where decisions depend on cross-modal semantics and adversaries can jointly perturb heterogeneous inputs, rendering unimodal certificates insufficient. We introduce a unified randomized smoothing framework for mixed discrete--continuous inputs based on an analytically tractable Neyman--Pearson formulation of the joint worst-case problem. By analyzing th"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our approach yields a closed-form, one-dimensional certificate that strictly generalizes both Gaussian (image-only) and discrete (text-only) randomized smoothing","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The joint likelihood ordering induced by factorized discrete and continuous noise permits an analytically tractable Neyman-Pearson formulation of the worst-case problem.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A hybrid randomized smoothing method yields a closed-form certificate for joint discrete-continuous perturbations that generalizes prior Gaussian and discrete smoothing approaches.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Hybrid randomized smoothing yields a closed-form one-dimensional certificate that generalizes both Gaussian and discrete smoothing for joint discrete-continuous inputs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"088c8bbfae37d832f33018c35686e1e70681cb98aff6a45f16c0e5d230f6f090"},"source":{"id":"2605.12876","kind":"arxiv","version":1},"verdict":{"id":"88a2435d-c52f-43e5-bd14-adfb509870d7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:19:40.652530Z","strongest_claim":"our approach yields a closed-form, one-dimensional certificate that strictly generalizes both Gaussian (image-only) and discrete (text-only) randomized smoothing","one_line_summary":"A hybrid randomized smoothing method yields a closed-form certificate for joint discrete-continuous perturbations that generalizes prior Gaussian and discrete smoothing approaches.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The joint likelihood ordering induced by factorized discrete and continuous noise permits an analytically tractable Neyman-Pearson formulation of the worst-case problem.","pith_extraction_headline":"Hybrid randomized smoothing yields a closed-form one-dimensional certificate that generalizes both Gaussian and discrete smoothing for joint discrete-continuous inputs."},"references":{"count":22,"sample":[{"doi":"","year":2023,"title":"A., Jagielski, M., Gao, I., Awadalla, A., Koh, P","work_id":"490b95c3-2f53-4701-a7a7-c9ad219de0e6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"A Survey on Multimodal Large Language Models for Autonomous Driving","work_id":"184f4f4a-d36f-4593-94cb-4b6420fa77b0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Defeating Prompt Injections by Design","work_id":"86405b86-1c51-4042-9b04-aff0b6541411","ref_index":4,"cited_arxiv_id":"2503.18813","is_internal_anchor":true},{"doi":"","year":null,"title":"Ad- versarial attacks to multi-modal models.arXiv preprint arXiv:2409.06793,","work_id":"25ac5b53-65c4-42b2-8069-27b5dfd6311e","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Llavaguard: An open vlm- based framework for safeguarding vision datasets and mod- els","work_id":"6428946a-91bd-4dbe-b263-a8f502ab8aa0","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":22,"snapshot_sha256":"c2284d38c6b069473c5988ad3246014f7007ae9a218f7fa3fb1d43bdbce5dbf5","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d7be81a3f67da361da43c82a6500f303f6b52a7a5355a318c0f2d7bf34bc667e"},"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":"2605.12876","created_at":"2026-05-18T03:09:11.203926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12876v1","created_at":"2026-05-18T03:09:11.203926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12876","created_at":"2026-05-18T03:09:11.203926+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIVHURFMCK3N","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIVHURFMCK3NXFYD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIVHURFM","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RIVHURFMCK3NXFYDRLXVNZBEKT","json":"https://pith.science/pith/RIVHURFMCK3NXFYDRLXVNZBEKT.json","graph_json":"https://pith.science/api/pith-number/RIVHURFMCK3NXFYDRLXVNZBEKT/graph.json","events_json":"https://pith.science/api/pith-number/RIVHURFMCK3NXFYDRLXVNZBEKT/events.json","paper":"https://pith.science/paper/RIVHURFM"},"agent_actions":{"view_html":"https://pith.science/pith/RIVHURFMCK3NXFYDRLXVNZBEKT","download_json":"https://pith.science/pith/RIVHURFMCK3NXFYDRLXVNZBEKT.json","view_paper":"https://pith.science/paper/RIVHURFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12876&json=true","fetch_graph":"https://pith.science/api/pith-number/RIVHURFMCK3NXFYDRLXVNZBEKT/graph.json","fetch_events":"https://pith.science/api/pith-number/RIVHURFMCK3NXFYDRLXVNZBEKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIVHURFMCK3NXFYDRLXVNZBEKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIVHURFMCK3NXFYDRLXVNZBEKT/action/storage_attestation","attest_author":"https://pith.science/pith/RIVHURFMCK3NXFYDRLXVNZBEKT/action/author_attestation","sign_citation":"https://pith.science/pith/RIVHURFMCK3NXFYDRLXVNZBEKT/action/citation_signature","submit_replication":"https://pith.science/pith/RIVHURFMCK3NXFYDRLXVNZBEKT/action/replication_record"}},"created_at":"2026-05-18T03:09:11.203926+00:00","updated_at":"2026-05-18T03:09:11.203926+00:00"}