{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EDIEDWY44TMYMY7HGREBIRS6ZP","short_pith_number":"pith:EDIEDWY4","schema_version":"1.0","canonical_sha256":"20d041db1ce4d98663e7344814465ecbeaf2655fde9b76092402b7f999e47f28","source":{"kind":"arxiv","id":"2608.12037","version":1},"attestation_state":"computed","paper":{"title":"Clustered Randomized Smoothing for Stochastic Prediction Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Arkady Zgonnikov, Eduardo Figueiredo, Frederik Mathiesen, Jens Kober, Julian Schumann, Luca Laurenti","submitted_at":"2026-08-12T13:20:36Z","abstract_excerpt":"Modern stochastic predictors can model rich, multi-modal outcome distributions. However, this expressive power comes with challenges in ensuring robust predictions $-$ a critical requirement in safety-critical domains. Randomized smoothing is a leading technique for improving robustness, particularly against adversarial perturbations. Yet, in stochastic multi-modal regression settings, randomized smoothing often fails due to mode collapse, yielding averaged predictions that do not reflect the underlying distribution. To address this limitation, we propose clustered $\\alpha$-smoothing, a framew"},"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":"2608.12037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T13:20:36Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"383f20da700441b1e62f9d78a8b41eac57b3938c042e6c18ca0e8f1a63364cef","abstract_canon_sha256":"3b907bdcca03c1ebdcf1901173947badde6fab93cb6d4f25bb85c3f1d3868f72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:29:19.357943Z","signature_b64":"mGJyCcmP3GbzwsT8JLgJJDc/QE/MGdxBYyiqa3v5/JgL2KjDQYCBXfuGYVbV+RVULQR8Y5/TyuAslCzS36RiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20d041db1ce4d98663e7344814465ecbeaf2655fde9b76092402b7f999e47f28","last_reissued_at":"2026-08-13T01:29:19.355354Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:29:19.355354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustered Randomized Smoothing for Stochastic Prediction Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Arkady Zgonnikov, Eduardo Figueiredo, Frederik Mathiesen, Jens Kober, Julian Schumann, Luca Laurenti","submitted_at":"2026-08-12T13:20:36Z","abstract_excerpt":"Modern stochastic predictors can model rich, multi-modal outcome distributions. However, this expressive power comes with challenges in ensuring robust predictions $-$ a critical requirement in safety-critical domains. Randomized smoothing is a leading technique for improving robustness, particularly against adversarial perturbations. Yet, in stochastic multi-modal regression settings, randomized smoothing often fails due to mode collapse, yielding averaged predictions that do not reflect the underlying distribution. To address this limitation, we propose clustered $\\alpha$-smoothing, a framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12037","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/2608.12037/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":"2608.12037","created_at":"2026-08-13T01:29:19.356865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12037v1","created_at":"2026-08-13T01:29:19.356865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12037","created_at":"2026-08-13T01:29:19.356865+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDIEDWY44TMY","created_at":"2026-08-13T01:29:19.356865+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDIEDWY44TMYMY7H","created_at":"2026-08-13T01:29:19.356865+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDIEDWY4","created_at":"2026-08-13T01:29:19.356865+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/EDIEDWY44TMYMY7HGREBIRS6ZP","json":"https://pith.science/pith/EDIEDWY44TMYMY7HGREBIRS6ZP.json","graph_json":"https://pith.science/api/pith-number/EDIEDWY44TMYMY7HGREBIRS6ZP/graph.json","events_json":"https://pith.science/api/pith-number/EDIEDWY44TMYMY7HGREBIRS6ZP/events.json","paper":"https://pith.science/paper/EDIEDWY4"},"agent_actions":{"view_html":"https://pith.science/pith/EDIEDWY44TMYMY7HGREBIRS6ZP","download_json":"https://pith.science/pith/EDIEDWY44TMYMY7HGREBIRS6ZP.json","view_paper":"https://pith.science/paper/EDIEDWY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12037&json=true","fetch_graph":"https://pith.science/api/pith-number/EDIEDWY44TMYMY7HGREBIRS6ZP/graph.json","fetch_events":"https://pith.science/api/pith-number/EDIEDWY44TMYMY7HGREBIRS6ZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDIEDWY44TMYMY7HGREBIRS6ZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDIEDWY44TMYMY7HGREBIRS6ZP/action/storage_attestation","attest_author":"https://pith.science/pith/EDIEDWY44TMYMY7HGREBIRS6ZP/action/author_attestation","sign_citation":"https://pith.science/pith/EDIEDWY44TMYMY7HGREBIRS6ZP/action/citation_signature","submit_replication":"https://pith.science/pith/EDIEDWY44TMYMY7HGREBIRS6ZP/action/replication_record"}},"created_at":"2026-08-13T01:29:19.356865+00:00","updated_at":"2026-08-13T01:29:19.356865+00:00"}