{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7IEWHSGXMINS6C7A4CJS5RKUCJ","short_pith_number":"pith:7IEWHSGX","schema_version":"1.0","canonical_sha256":"fa0963c8d7621b2f0be0e0932ec554127144174f70237db3550273957dab99f5","source":{"kind":"arxiv","id":"2307.07171","version":1},"attestation_state":"computed","paper":{"title":"Certified Robustness for Large Language Models with Self-Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bairu Hou, Guanhua Zhang, Qing Li, Shiyu Chang, Sijia Liu, Wenqi Fan, Yang Zhang, Zhen Zhang","submitted_at":"2023-07-14T05:40:24Z","abstract_excerpt":"Although large language models (LLMs) have achieved great success in vast real-world applications, their vulnerabilities towards noisy inputs have significantly limited their uses, especially in high-stake environments. In these contexts, it is crucial to ensure that every prediction made by large language models is stable, i.e., LLM predictions should be consistent given minor differences in the input. This largely falls into the study of certified robust LLMs, i.e., all predictions of LLM are certified to be correct in a local region around the input. Randomized smoothing has demonstrated gr"},"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":"2307.07171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T05:40:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"86635aa9cb531136354f556831fd3747d83205f978870ee665d2917a35b39dc3","abstract_canon_sha256":"21696e23377de45722ebc135163d74470fe8fcff349b80298135982058f14edc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:52.258645Z","signature_b64":"CBcYuSS+XC9gmRlgGXBGZgVicTlLszqTqUv7jeML//xWgB8K4wnzTTPIp6B06uQ12L2abPBScasOCUB+YLVfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa0963c8d7621b2f0be0e0932ec554127144174f70237db3550273957dab99f5","last_reissued_at":"2026-07-05T06:30:52.258132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:52.258132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Certified Robustness for Large Language Models with Self-Denoising","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bairu Hou, Guanhua Zhang, Qing Li, Shiyu Chang, Sijia Liu, Wenqi Fan, Yang Zhang, Zhen Zhang","submitted_at":"2023-07-14T05:40:24Z","abstract_excerpt":"Although large language models (LLMs) have achieved great success in vast real-world applications, their vulnerabilities towards noisy inputs have significantly limited their uses, especially in high-stake environments. In these contexts, it is crucial to ensure that every prediction made by large language models is stable, i.e., LLM predictions should be consistent given minor differences in the input. This largely falls into the study of certified robust LLMs, i.e., all predictions of LLM are certified to be correct in a local region around the input. Randomized smoothing has demonstrated gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07171","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/2307.07171/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":"2307.07171","created_at":"2026-07-05T06:30:52.258198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07171v1","created_at":"2026-07-05T06:30:52.258198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07171","created_at":"2026-07-05T06:30:52.258198+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IEWHSGXMINS","created_at":"2026-07-05T06:30:52.258198+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IEWHSGXMINS6C7A","created_at":"2026-07-05T06:30:52.258198+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IEWHSGX","created_at":"2026-07-05T06:30:52.258198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08068","citing_title":"DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29816","citing_title":"Harnessing non-adversarial robustness in large language models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2409.10102","citing_title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17288","citing_title":"When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2309.00614","citing_title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10693","citing_title":"FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IEWHSGXMINS6C7A4CJS5RKUCJ","json":"https://pith.science/pith/7IEWHSGXMINS6C7A4CJS5RKUCJ.json","graph_json":"https://pith.science/api/pith-number/7IEWHSGXMINS6C7A4CJS5RKUCJ/graph.json","events_json":"https://pith.science/api/pith-number/7IEWHSGXMINS6C7A4CJS5RKUCJ/events.json","paper":"https://pith.science/paper/7IEWHSGX"},"agent_actions":{"view_html":"https://pith.science/pith/7IEWHSGXMINS6C7A4CJS5RKUCJ","download_json":"https://pith.science/pith/7IEWHSGXMINS6C7A4CJS5RKUCJ.json","view_paper":"https://pith.science/paper/7IEWHSGX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07171&json=true","fetch_graph":"https://pith.science/api/pith-number/7IEWHSGXMINS6C7A4CJS5RKUCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7IEWHSGXMINS6C7A4CJS5RKUCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IEWHSGXMINS6C7A4CJS5RKUCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IEWHSGXMINS6C7A4CJS5RKUCJ/action/storage_attestation","attest_author":"https://pith.science/pith/7IEWHSGXMINS6C7A4CJS5RKUCJ/action/author_attestation","sign_citation":"https://pith.science/pith/7IEWHSGXMINS6C7A4CJS5RKUCJ/action/citation_signature","submit_replication":"https://pith.science/pith/7IEWHSGXMINS6C7A4CJS5RKUCJ/action/replication_record"}},"created_at":"2026-07-05T06:30:52.258198+00:00","updated_at":"2026-07-05T06:30:52.258198+00:00"}