{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VXBUWOUPSLHJCUAQ3SCUAPWZKI","short_pith_number":"pith:VXBUWOUP","schema_version":"1.0","canonical_sha256":"adc34b3a8f92ce915010dc85403ed952373a81fd3c6a4959b68feffff509246a","source":{"kind":"arxiv","id":"2205.09619","version":1},"attestation_state":"computed","paper":{"title":"Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"An Nguyen, Bj\\\"orn Eskofier, Dario Zanca, Doina Precup, Falk Pulsmeyer, Leon Bungert, Leo Schwinn, Ren\\'e Raab","submitted_at":"2022-05-19T15:25:55Z","abstract_excerpt":"The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to either real-world distribution shifts (e.g., common corruptions and perturbations, spatial transformations, and natural adversarial examples) or worst-case distribution shifts (e.g., optimized adversarial examples). In this work, we propose the Decision Region Quantification (DRQ) algorithm to improve the robustness of any differentiable pre-trained model against both real-world and worst-case distribution shifts in t"},"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":"2205.09619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-19T15:25:55Z","cross_cats_sorted":[],"title_canon_sha256":"bcbdd20c5095696a967bd89dbd91180bde1461a04c3245680be4e5091976f5ff","abstract_canon_sha256":"e1e0965575eb01dcfb3bf6d21728ca60d61723ac91e97feecda659a9160e4c05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:46.764372Z","signature_b64":"KLGowbQy2jI86zQfd7E4q+mPHIhg6ObeBH32u7lwluKNhv/WkgK7QGq3Qs73uGIsITdVffzTdWA4f8bBYV6BCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adc34b3a8f92ce915010dc85403ed952373a81fd3c6a4959b68feffff509246a","last_reissued_at":"2026-07-05T04:24:46.763976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:46.763976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"An Nguyen, Bj\\\"orn Eskofier, Dario Zanca, Doina Precup, Falk Pulsmeyer, Leon Bungert, Leo Schwinn, Ren\\'e Raab","submitted_at":"2022-05-19T15:25:55Z","abstract_excerpt":"The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to either real-world distribution shifts (e.g., common corruptions and perturbations, spatial transformations, and natural adversarial examples) or worst-case distribution shifts (e.g., optimized adversarial examples). In this work, we propose the Decision Region Quantification (DRQ) algorithm to improve the robustness of any differentiable pre-trained model against both real-world and worst-case distribution shifts in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09619","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/2205.09619/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":"2205.09619","created_at":"2026-07-05T04:24:46.764029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.09619v1","created_at":"2026-07-05T04:24:46.764029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09619","created_at":"2026-07-05T04:24:46.764029+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXBUWOUPSLHJ","created_at":"2026-07-05T04:24:46.764029+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXBUWOUPSLHJCUAQ","created_at":"2026-07-05T04:24:46.764029+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXBUWOUP","created_at":"2026-07-05T04:24:46.764029+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/VXBUWOUPSLHJCUAQ3SCUAPWZKI","json":"https://pith.science/pith/VXBUWOUPSLHJCUAQ3SCUAPWZKI.json","graph_json":"https://pith.science/api/pith-number/VXBUWOUPSLHJCUAQ3SCUAPWZKI/graph.json","events_json":"https://pith.science/api/pith-number/VXBUWOUPSLHJCUAQ3SCUAPWZKI/events.json","paper":"https://pith.science/paper/VXBUWOUP"},"agent_actions":{"view_html":"https://pith.science/pith/VXBUWOUPSLHJCUAQ3SCUAPWZKI","download_json":"https://pith.science/pith/VXBUWOUPSLHJCUAQ3SCUAPWZKI.json","view_paper":"https://pith.science/paper/VXBUWOUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.09619&json=true","fetch_graph":"https://pith.science/api/pith-number/VXBUWOUPSLHJCUAQ3SCUAPWZKI/graph.json","fetch_events":"https://pith.science/api/pith-number/VXBUWOUPSLHJCUAQ3SCUAPWZKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXBUWOUPSLHJCUAQ3SCUAPWZKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXBUWOUPSLHJCUAQ3SCUAPWZKI/action/storage_attestation","attest_author":"https://pith.science/pith/VXBUWOUPSLHJCUAQ3SCUAPWZKI/action/author_attestation","sign_citation":"https://pith.science/pith/VXBUWOUPSLHJCUAQ3SCUAPWZKI/action/citation_signature","submit_replication":"https://pith.science/pith/VXBUWOUPSLHJCUAQ3SCUAPWZKI/action/replication_record"}},"created_at":"2026-07-05T04:24:46.764029+00:00","updated_at":"2026-07-05T04:24:46.764029+00:00"}