{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MTEU3CAJS3AMSCSMPXIMCG5BMD","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":"c7bb108596a255781662c7c300f7fbe9d62e7705bce147c64b0d23b9fafe791d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-13T10:09:51Z","title_canon_sha256":"6bd9107163cccc458a1fb6b3d9c4893dd2e2a0bba13490d02a9280181196e9c0"},"schema_version":"1.0","source":{"id":"2505.08411","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08411","created_at":"2026-07-05T11:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08411v1","created_at":"2026-07-05T11:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08411","created_at":"2026-07-05T11:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"MTEU3CAJS3AM","created_at":"2026-07-05T11:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"MTEU3CAJS3AMSCSM","created_at":"2026-07-05T11:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"MTEU3CAJ","created_at":"2026-07-05T11:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:67abe5740f8034fdb835513ff1c753e94f808dda43d0519b8d6c57c7a38bf7d3","target":"graph","created_at":"2026-07-05T11:02:30Z","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/2505.08411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most human languages use scripts other than the Latin alphabet. Search users in these languages often formulate their information needs in a transliterated -- usually Latinized -- form for ease of typing. For example, Greek speakers might use Greeklish, and Arabic speakers might use Arabizi. This paper shows that current search systems, including those that use multilingual dense embeddings such as BGE-M3, do not generalise to this setting, and their performance rapidly deteriorates when exposed to transliterated queries. This creates a ``script gap\" between the performance of the same queries","authors_text":"Andreas Chari, Iadh Ounis, Sean MacAvaney","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-13T10:09:51Z","title":"Lost in Transliteration: Bridging the Script Gap in Neural IR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08411","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":"sha256:45bf5e3b8a4850fa17db9e16f7baf0004d353793634a37c0249a2ecd71673644","target":"record","created_at":"2026-07-05T11:02:30Z","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":"c7bb108596a255781662c7c300f7fbe9d62e7705bce147c64b0d23b9fafe791d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-13T10:09:51Z","title_canon_sha256":"6bd9107163cccc458a1fb6b3d9c4893dd2e2a0bba13490d02a9280181196e9c0"},"schema_version":"1.0","source":{"id":"2505.08411","kind":"arxiv","version":1}},"canonical_sha256":"64c94d880996c0c90a4c7dd0c11ba160cfe776c7abeed10ac805000a2e525559","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64c94d880996c0c90a4c7dd0c11ba160cfe776c7abeed10ac805000a2e525559","first_computed_at":"2026-07-05T11:02:30.095259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:30.095259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SNiEwGCqZP6+W5YbIxZoLTzADIE5OmwLXVWMIt7mz003NjreWJVkjbQJWoFh/2nSlZKfOP9QSNegx5Aj/hEEDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:30.095833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08411","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45bf5e3b8a4850fa17db9e16f7baf0004d353793634a37c0249a2ecd71673644","sha256:67abe5740f8034fdb835513ff1c753e94f808dda43d0519b8d6c57c7a38bf7d3"],"state_sha256":"15e4f3fca4acd37cd2e401fc7c7804e33f1dcc5650baa65c386b6d5bd0325da0"}