{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q24F4WTDUUZJBKFTRIHYLH3REB","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4e20f71ee5616c5cc507607d492961abe5750987a67f1c05c55ce506af380193","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T14:27:46Z","title_canon_sha256":"576af77fe98996cd3d6760a49ddcff94fdd18a1544ad9ff8b8792152ee644a68"},"schema_version":"1.0","source":{"id":"2605.22544","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22544","created_at":"2026-05-22T01:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22544v1","created_at":"2026-05-22T01:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22544","created_at":"2026-05-22T01:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"Q24F4WTDUUZJ","created_at":"2026-05-22T01:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"Q24F4WTDUUZJBKFT","created_at":"2026-05-22T01:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"Q24F4WTD","created_at":"2026-05-22T01:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:441f15dfda18647f4bdf42504b51fa4957ae138680d36a88af6a90e91f808d6c","target":"graph","created_at":"2026-05-22T01:04:56Z","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/2605.22544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction embedding models have become common among state-of-the-art models, however are evaluated using a single prompt per task. The single-point evaluation ignores a main problem of the instruction-based approach namely: sensitivity to the phrasing of the instruction. We present an empirical study of prompt sensitivity across 6 embedding models, 11 datasets, and 15 task-specific prompts per dataset, a total of 990. We show that reported scores misrepresent the distribution of scores over plausible prompts. The default prompt can both systematically understate or overstate performance. Fur","authors_text":"Kenneth Enevoldsen, Yevhen Kostiuk","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T14:27:46Z","title":"One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22544","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:e84c5193f11d1e828dc7913f106b8e2cec8355dcd89d9fdc6a7350c19b285c4c","target":"record","created_at":"2026-05-22T01:04:56Z","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":"4e20f71ee5616c5cc507607d492961abe5750987a67f1c05c55ce506af380193","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T14:27:46Z","title_canon_sha256":"576af77fe98996cd3d6760a49ddcff94fdd18a1544ad9ff8b8792152ee644a68"},"schema_version":"1.0","source":{"id":"2605.22544","kind":"arxiv","version":1}},"canonical_sha256":"86b85e5a63a53290a8b38a0f859f71207df16b4f2642e6762684fdad869f3fba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86b85e5a63a53290a8b38a0f859f71207df16b4f2642e6762684fdad869f3fba","first_computed_at":"2026-05-22T01:04:56.575939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:56.575939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lb3b1tlK+gttWOE2wfiMBRANUFJtXfpBl1iNok68QmS5oCa1geaxRuHdmnUK57BTKfzz9uvPZkWUUe+Kd6W7BA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:56.576770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22544","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e84c5193f11d1e828dc7913f106b8e2cec8355dcd89d9fdc6a7350c19b285c4c","sha256:441f15dfda18647f4bdf42504b51fa4957ae138680d36a88af6a90e91f808d6c","sha256:1fe4b254eaa6096e1e7f20efcfd3b5b5c71969599efc9082f2ea34dacd22321c"],"state_sha256":"a54301b9e39a0f156c92ddb8dc699443b783b7075608220efb8d3dfda2ac2771"}