{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U6LJ4UY4VLPGEGZMNUU6P3GRON","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":"779e43112f195fe09f384cf75715bfaf685b171fee8272c5f0f568699fc805e9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T10:32:50Z","title_canon_sha256":"04a6bb13a583ec7eb16769c4782bdf09b8e047de01e607f077161e17c37bf3c1"},"schema_version":"1.0","source":{"id":"2508.11383","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11383","created_at":"2026-07-05T11:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11383v1","created_at":"2026-07-05T11:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11383","created_at":"2026-07-05T11:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"U6LJ4UY4VLPG","created_at":"2026-07-05T11:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"U6LJ4UY4VLPGEGZM","created_at":"2026-07-05T11:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"U6LJ4UY4","created_at":"2026-07-05T11:54:32Z"}],"graph_snapshots":[{"event_id":"sha256:7c34e362b4c7a9857cc6589a2baccb72e3b3a2bbb17d36d80bbab997bae71fd3","target":"graph","created_at":"2026-07-05T11:54:32Z","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/2508.11383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are highly sensitive to subtle, non-semantic variations in prompt phrasing and formatting. In this work, we present the first systematic evaluation of 5 methods for improving prompt robustness within a unified experimental framework. We benchmark these techniques on 8 models from Llama, Qwen and Gemma families across 52 tasks from Natural Instructions dataset. Our evaluation covers robustness methods from both fine-tuned and in-context learning paradigms, and tests their generalization against multiple types of distribution shifts. Finally, we extend our analysis t","authors_text":"Alexander Panchenko, Elena Tutubalina, Gleb Ershov, Mikhail Chaichuk, Mikhail Seleznyov, Oleg Somov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T10:32:50Z","title":"When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11383","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:ecf13772b7af8ae0204fa3f98d276fd5ec8c8d8d12e6ba4219c9e76f3e192169","target":"record","created_at":"2026-07-05T11:54:32Z","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":"779e43112f195fe09f384cf75715bfaf685b171fee8272c5f0f568699fc805e9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T10:32:50Z","title_canon_sha256":"04a6bb13a583ec7eb16769c4782bdf09b8e047de01e607f077161e17c37bf3c1"},"schema_version":"1.0","source":{"id":"2508.11383","kind":"arxiv","version":1}},"canonical_sha256":"a7969e531caade621b2c6d29e7ecd1735213372260b0a32d85b880d1cfa06dc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7969e531caade621b2c6d29e7ecd1735213372260b0a32d85b880d1cfa06dc0","first_computed_at":"2026-07-05T11:54:32.536037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:32.536037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QAau+Hl/nktfCzHTHvnQwTnZ1gUpz9iZ9ZgN4hkVMS/4FLSA7a/nU0vmGsv0T067Ocu5SQJfO5cF394V+WpYAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:32.536493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.11383","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecf13772b7af8ae0204fa3f98d276fd5ec8c8d8d12e6ba4219c9e76f3e192169","sha256:7c34e362b4c7a9857cc6589a2baccb72e3b3a2bbb17d36d80bbab997bae71fd3"],"state_sha256":"8051121b1d5f37bd193324d63c75b66d8e3e2c75e0f591df7f7dc29af2747098"}