{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7WAOPZ7OWZSTWRHOVFBH56LYBO","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":"c36c09c49f327ad87d9307f5b2d94756f998ddd6628ab5662fc1fc065a7520ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-11T10:44:09Z","title_canon_sha256":"4d8f4abdce62e7f2b1e68f8055777896174c1d0e37365c56ca0ffe2d1a72a98e"},"schema_version":"1.0","source":{"id":"2507.08480","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08480","created_at":"2026-05-20T01:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08480v2","created_at":"2026-05-20T01:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08480","created_at":"2026-05-20T01:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"7WAOPZ7OWZST","created_at":"2026-05-20T01:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"7WAOPZ7OWZSTWRHO","created_at":"2026-05-20T01:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"7WAOPZ7O","created_at":"2026-05-20T01:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:d898f7bfe5c58cebcd9bde3d23e932be1f4fb794e2f6bbebb36b64de623de4ce","target":"graph","created_at":"2026-05-20T01:04:55Z","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/2507.08480/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the increasing utilization of multilingual text information, Cross-Lingual Information Retrieval (CLIR) has become a crucial research area. However, the impact of training data composition on both CLIR and Mono-Lingual Information Retrieval (IR) performance remains under-explored. To systematically investigate this data-centric aspect, we construct linguistically parallel Korean-English datasets and train retrieval models with various language combinations. Our experiments reveal that the language composition of training data significantly influences IR performance, exhibiting important i","authors_text":"Andrew Matteson, Heuiseok Lim, Hyeonseok Moon, Junyoung Son, Seongtae Hong, Seungyoon Lee, Taemin Lee, Youngjoon Jang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-11T10:44:09Z","title":"Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08480","kind":"arxiv","version":2},"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:ea434061994591ba228d2db3f2928f35be8605047db746f18808c3a058efc8fe","target":"record","created_at":"2026-05-20T01:04:55Z","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":"c36c09c49f327ad87d9307f5b2d94756f998ddd6628ab5662fc1fc065a7520ac","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-11T10:44:09Z","title_canon_sha256":"4d8f4abdce62e7f2b1e68f8055777896174c1d0e37365c56ca0ffe2d1a72a98e"},"schema_version":"1.0","source":{"id":"2507.08480","kind":"arxiv","version":2}},"canonical_sha256":"fd80e7e7eeb6653b44eea9427ef9780bb1cbf020b642e136e111de18d85326cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd80e7e7eeb6653b44eea9427ef9780bb1cbf020b642e136e111de18d85326cb","first_computed_at":"2026-05-20T01:04:55.927331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:04:55.927331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"885AUD3bO5g1Yv3L9ZtQYl37UWu/HY9N+8/Wg4bw6haZt69rOkR5VIr1CyyEQSiwfk+BoK9Dtt1R+QzGaI6/DQ==","signature_status":"signed_v1","signed_at":"2026-05-20T01:04:55.928185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08480","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea434061994591ba228d2db3f2928f35be8605047db746f18808c3a058efc8fe","sha256:d898f7bfe5c58cebcd9bde3d23e932be1f4fb794e2f6bbebb36b64de623de4ce"],"state_sha256":"02cb4f28a1912757ce688dee0baf8f9d81bcfea5e1cd2840105e8071a0b5a9ef"}