{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5JOCWO7IIDGCCTF3CD5GQDM3FS","short_pith_number":"pith:5JOCWO7I","schema_version":"1.0","canonical_sha256":"ea5c2b3be840cc214cbb10fa680d9b2c873441f21c24272bb74f1e9452ed7634","source":{"kind":"arxiv","id":"2412.10535","version":1},"attestation_state":"computed","paper":{"title":"On Adversarial Robustness and Out-of-Distribution Robustness of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"April Yang, Jordan Tab, Parth Shah, Paul Kotchavong","submitted_at":"2024-12-13T20:04:25Z","abstract_excerpt":"The increasing reliance on large language models (LLMs) for diverse applications necessitates a thorough understanding of their robustness to adversarial perturbations and out-of-distribution (OOD) inputs. In this study, we investigate the correlation between adversarial robustness and OOD robustness in LLMs, addressing a critical gap in robustness evaluation. By applying methods originally designed to improve one robustness type across both contexts, we analyze their performance on adversarial and out-of-distribution benchmark datasets. The input of the model consists of text samples, with 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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.10535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T20:04:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a195d74fccf45969dc7365514e7fd27409be26314881313bcd2bc6497346708f","abstract_canon_sha256":"94f7bff2cf2e96ae16dd21a4025f54742036dba50da8915af386ff71e77341c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:17.346699Z","signature_b64":"dkqCK/r6qlXO689csTUdpcpz9fum/WcwNZEmv2Db0Jpb73XT5GTwWhpnHbK08sHZAJur/p3KFADuVoXNoAyPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea5c2b3be840cc214cbb10fa680d9b2c873441f21c24272bb74f1e9452ed7634","last_reissued_at":"2026-07-05T09:49:17.345933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:17.345933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Adversarial Robustness and Out-of-Distribution Robustness of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"April Yang, Jordan Tab, Parth Shah, Paul Kotchavong","submitted_at":"2024-12-13T20:04:25Z","abstract_excerpt":"The increasing reliance on large language models (LLMs) for diverse applications necessitates a thorough understanding of their robustness to adversarial perturbations and out-of-distribution (OOD) inputs. In this study, we investigate the correlation between adversarial robustness and OOD robustness in LLMs, addressing a critical gap in robustness evaluation. By applying methods originally designed to improve one robustness type across both contexts, we analyze their performance on adversarial and out-of-distribution benchmark datasets. The input of the model consists of text samples, with th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10535","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/2412.10535/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":"2412.10535","created_at":"2026-07-05T09:49:17.346033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10535v1","created_at":"2026-07-05T09:49:17.346033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10535","created_at":"2026-07-05T09:49:17.346033+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JOCWO7IIDGC","created_at":"2026-07-05T09:49:17.346033+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JOCWO7IIDGCCTF3","created_at":"2026-07-05T09:49:17.346033+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JOCWO7I","created_at":"2026-07-05T09:49:17.346033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24544","citing_title":"STELLAR-E: a Synthetic, Tailored, End-to-end LLM Application Rigorous Evaluator","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5JOCWO7IIDGCCTF3CD5GQDM3FS","json":"https://pith.science/pith/5JOCWO7IIDGCCTF3CD5GQDM3FS.json","graph_json":"https://pith.science/api/pith-number/5JOCWO7IIDGCCTF3CD5GQDM3FS/graph.json","events_json":"https://pith.science/api/pith-number/5JOCWO7IIDGCCTF3CD5GQDM3FS/events.json","paper":"https://pith.science/paper/5JOCWO7I"},"agent_actions":{"view_html":"https://pith.science/pith/5JOCWO7IIDGCCTF3CD5GQDM3FS","download_json":"https://pith.science/pith/5JOCWO7IIDGCCTF3CD5GQDM3FS.json","view_paper":"https://pith.science/paper/5JOCWO7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10535&json=true","fetch_graph":"https://pith.science/api/pith-number/5JOCWO7IIDGCCTF3CD5GQDM3FS/graph.json","fetch_events":"https://pith.science/api/pith-number/5JOCWO7IIDGCCTF3CD5GQDM3FS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JOCWO7IIDGCCTF3CD5GQDM3FS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JOCWO7IIDGCCTF3CD5GQDM3FS/action/storage_attestation","attest_author":"https://pith.science/pith/5JOCWO7IIDGCCTF3CD5GQDM3FS/action/author_attestation","sign_citation":"https://pith.science/pith/5JOCWO7IIDGCCTF3CD5GQDM3FS/action/citation_signature","submit_replication":"https://pith.science/pith/5JOCWO7IIDGCCTF3CD5GQDM3FS/action/replication_record"}},"created_at":"2026-07-05T09:49:17.346033+00:00","updated_at":"2026-07-05T09:49:17.346033+00:00"}