{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AB6VQ3WLADCB73J7CN3C2RC4HT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"659e8b4f583f387f73d7760b908bce2fe1572e60a239d9b8552464754998fac4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T03:15:05Z","title_canon_sha256":"079362101515395da02442dff08665a6bef0f68f9b1098635a28081faa24572a"},"schema_version":"1.0","source":{"id":"2311.00258","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00258","created_at":"2026-07-05T07:07:44Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00258v1","created_at":"2026-07-05T07:07:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00258","created_at":"2026-07-05T07:07:44Z"},{"alias_kind":"pith_short_12","alias_value":"AB6VQ3WLADCB","created_at":"2026-07-05T07:07:44Z"},{"alias_kind":"pith_short_16","alias_value":"AB6VQ3WLADCB73J7","created_at":"2026-07-05T07:07:44Z"},{"alias_kind":"pith_short_8","alias_value":"AB6VQ3WL","created_at":"2026-07-05T07:07:44Z"}],"graph_snapshots":[{"event_id":"sha256:070de5d830d189e13facf79a90238c7bbef9020d086d70f593add09d3b8934f1","target":"graph","created_at":"2026-07-05T07:07:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.00258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in prompt engineering enable large language models (LLMs) to solve multi-hop logical reasoning problems with impressive accuracy. However, there is little existing work investigating the robustness of LLMs with few-shot prompting techniques. Therefore, we introduce a systematic approach to test the robustness of LLMs in multi-hop reasoning tasks via domain-agnostic perturbations. We include perturbations at multiple levels of abstractions (e.g. lexical perturbations such as typos, and semantic perturbations such as the inclusion of intermediate reasoning steps in the questions)","authors_text":"Abulhair Saparov, Hongyi Zheng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T03:15:05Z","title":"Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00258","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b394681e148d00d9661c0ab0053a0295bd311e2fe2fb6a4c4a6efca630fcb1d3","target":"record","created_at":"2026-07-05T07:07:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"659e8b4f583f387f73d7760b908bce2fe1572e60a239d9b8552464754998fac4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T03:15:05Z","title_canon_sha256":"079362101515395da02442dff08665a6bef0f68f9b1098635a28081faa24572a"},"schema_version":"1.0","source":{"id":"2311.00258","kind":"arxiv","version":1}},"canonical_sha256":"007d586ecb00c41fed3f13762d445c3cec187256acd4dea75725d19bc1c3d9ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"007d586ecb00c41fed3f13762d445c3cec187256acd4dea75725d19bc1c3d9ac","first_computed_at":"2026-07-05T07:07:44.622077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:44.622077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oDcqLRYXw/oWMGGGhIGAUvaSKyUirWSQM18Q1QsNpnOFyCZgluA8/wkdjoHCrxcwm13QWNRXz2oU3Hcvy1tFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:44.622552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00258","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b394681e148d00d9661c0ab0053a0295bd311e2fe2fb6a4c4a6efca630fcb1d3","sha256:070de5d830d189e13facf79a90238c7bbef9020d086d70f593add09d3b8934f1"],"state_sha256":"d69686e3c8f0fea2bc7f210670806f278381ee94ce0b2224f4f2e5cfdc9f132b"}