{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MYW6MOCPH4ES2VBEPSJY77UPJV","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":"78a467d8c27d407cdf21b260355675660ad028320d81af3eb5094952b675161f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T13:40:38Z","title_canon_sha256":"d5cd2233c4b9b12c3e70a03a5fbbf035f127c38b226af0f7faf82a7a747e1395"},"schema_version":"1.0","source":{"id":"2406.10248","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10248","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10248v4","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10248","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"pith_short_12","alias_value":"MYW6MOCPH4ES","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"pith_short_16","alias_value":"MYW6MOCPH4ES2VBE","created_at":"2026-07-05T09:28:32Z"},{"alias_kind":"pith_short_8","alias_value":"MYW6MOCP","created_at":"2026-07-05T09:28:32Z"}],"graph_snapshots":[{"event_id":"sha256:a91599ce3ea3e0414438c211d0e1f0bd9831c8cdda984931fa67181712c462bd","target":"graph","created_at":"2026-07-05T09:28:32Z","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/2406.10248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of large language models (LLMs) is acutely sensitive to the phrasing of prompts, which raises significant concerns about their reliability in real-world scenarios. Existing studies often divide prompts into task-level instructions and case-level inputs and primarily focus on evaluating and improving robustness against variations in tasks-level instructions. However, this setup fails to fully address the diversity of real-world user queries and assumes the existence of task-specific datasets. To address these limitations, we introduce RobustAlpacaEval, a new benchmark that consi","authors_text":"Bowen Cao, Deng Cai, Wai Lam, Yuexian Zou, Zhisong Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T13:40:38Z","title":"On the Worst Prompt Performance of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10248","kind":"arxiv","version":4},"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:e36dc804ef58cf7e8a28e36626f871f9297757cb8e6381f1ba5128fafa2e5cfc","target":"record","created_at":"2026-07-05T09:28:32Z","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":"78a467d8c27d407cdf21b260355675660ad028320d81af3eb5094952b675161f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T13:40:38Z","title_canon_sha256":"d5cd2233c4b9b12c3e70a03a5fbbf035f127c38b226af0f7faf82a7a747e1395"},"schema_version":"1.0","source":{"id":"2406.10248","kind":"arxiv","version":4}},"canonical_sha256":"662de6384f3f092d54247c938ffe8f4d765ee8f7b555e13af23758933eef225d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"662de6384f3f092d54247c938ffe8f4d765ee8f7b555e13af23758933eef225d","first_computed_at":"2026-07-05T09:28:32.041931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:32.041931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zxbcn5jTAN7/5mSSwi+IFNtQoKe1QvhKKJ5tQsNWh55Z4ggxcEfqijMSZriPHwD4rFMVyd6x0wbcImb8n0X1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:32.042478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10248","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e36dc804ef58cf7e8a28e36626f871f9297757cb8e6381f1ba5128fafa2e5cfc","sha256:a91599ce3ea3e0414438c211d0e1f0bd9831c8cdda984931fa67181712c462bd"],"state_sha256":"0c8ac3eff7cbab43c6df8b076275eb869b58f3da3c75ad9d111d992a24faaef5"}