{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ACU7XKWFB3JNGFI3VYTJI5OHVT","short_pith_number":"pith:ACU7XKWF","schema_version":"1.0","canonical_sha256":"00a9fbaac50ed2d3151bae269475c7acd927b5339c9886630ae6c59a1db583fb","source":{"kind":"arxiv","id":"2605.26002","version":1},"attestation_state":"computed","paper":{"title":"SemBridge: Language Transfer in Sparse Encoders via Multilingual Semantic Bridges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Heuiseok Lim, Hyeonseok Moon, Jia-Heui Ju, Seongtae Hong, Youngjoon Jang","submitted_at":"2026-05-25T16:20:03Z","abstract_excerpt":"Sparse encoders offer high-precision retrieval by representing term importance within a vocabulary space, yet their English-centric structures pose a critical impediment to language transfer for non-English languages. To overcome this structural limitation, we propose SemBridge, a novel embedding initialization method designed for cross-lingual adaptation in sparse encoders by leveraging multilingual bridge models. SemBridge establishes semantic alignments between source and target vocabularies using multilingual dense embeddings as a bridge. Rather than directly relying on all source tokens, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.26002","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-25T16:20:03Z","cross_cats_sorted":[],"title_canon_sha256":"fa0cebe4aceecb7b14441d5e86d2c4485cf5693519ccde0c9b704a8ee0bb6216","abstract_canon_sha256":"ce3beccc6a735e5a5ba40bc31ca7ebc6d4b7e9847147c41722375450349c3abc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:22.695520Z","signature_b64":"XszDwy/4daL0bv4+h8wg/0Xa3VuEYE2+4yTkfolqlanvcn0CRiVgpat/CRf0+CjlNyHQeS6fUs4ePdDmZANuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00a9fbaac50ed2d3151bae269475c7acd927b5339c9886630ae6c59a1db583fb","last_reissued_at":"2026-05-26T02:05:22.694750Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:22.694750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemBridge: Language Transfer in Sparse Encoders via Multilingual Semantic Bridges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Heuiseok Lim, Hyeonseok Moon, Jia-Heui Ju, Seongtae Hong, Youngjoon Jang","submitted_at":"2026-05-25T16:20:03Z","abstract_excerpt":"Sparse encoders offer high-precision retrieval by representing term importance within a vocabulary space, yet their English-centric structures pose a critical impediment to language transfer for non-English languages. To overcome this structural limitation, we propose SemBridge, a novel embedding initialization method designed for cross-lingual adaptation in sparse encoders by leveraging multilingual bridge models. SemBridge establishes semantic alignments between source and target vocabularies using multilingual dense embeddings as a bridge. Rather than directly relying on all source tokens, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26002","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.26002/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.26002","created_at":"2026-05-26T02:05:22.694883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26002v1","created_at":"2026-05-26T02:05:22.694883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26002","created_at":"2026-05-26T02:05:22.694883+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACU7XKWFB3JN","created_at":"2026-05-26T02:05:22.694883+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACU7XKWFB3JNGFI3","created_at":"2026-05-26T02:05:22.694883+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACU7XKWF","created_at":"2026-05-26T02:05:22.694883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT","json":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT.json","graph_json":"https://pith.science/api/pith-number/ACU7XKWFB3JNGFI3VYTJI5OHVT/graph.json","events_json":"https://pith.science/api/pith-number/ACU7XKWFB3JNGFI3VYTJI5OHVT/events.json","paper":"https://pith.science/paper/ACU7XKWF"},"agent_actions":{"view_html":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT","download_json":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT.json","view_paper":"https://pith.science/paper/ACU7XKWF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26002&json=true","fetch_graph":"https://pith.science/api/pith-number/ACU7XKWFB3JNGFI3VYTJI5OHVT/graph.json","fetch_events":"https://pith.science/api/pith-number/ACU7XKWFB3JNGFI3VYTJI5OHVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT/action/storage_attestation","attest_author":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT/action/author_attestation","sign_citation":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT/action/citation_signature","submit_replication":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT/action/replication_record"}},"created_at":"2026-05-26T02:05:22.694883+00:00","updated_at":"2026-05-26T02:05:22.694883+00:00"}