{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ACU7XKWFB3JNGFI3VYTJI5OHVT","short_pith_number":"pith:ACU7XKWF","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"},"canonical_sha256":"00a9fbaac50ed2d3151bae269475c7acd927b5339c9886630ae6c59a1db583fb","source":{"kind":"arxiv","id":"2605.26002","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26002","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26002v1","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26002","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"ACU7XKWFB3JN","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"ACU7XKWFB3JNGFI3","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"ACU7XKWF","created_at":"2026-05-26T02:05:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ACU7XKWFB3JNGFI3VYTJI5OHVT","target":"record","payload":{"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"},"canonical_sha256":"00a9fbaac50ed2d3151bae269475c7acd927b5339c9886630ae6c59a1db583fb","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"},"source_kind":"arxiv","source_id":"2605.26002","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:05:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aLxgVo1FH4lzcDcJ2gwTo9mST4q8IJ+PdAvvnUZwTBmujiNQhsLoYpBqAByZTDggWtoyDnlz/GBb0nHm0hi4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:36:44.062898Z"},"content_sha256":"696f625e094eaba4db75d9a1ebebee84acec5c370caceb6012600706f0b09693","schema_version":"1.0","event_id":"sha256:696f625e094eaba4db75d9a1ebebee84acec5c370caceb6012600706f0b09693"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ACU7XKWFB3JNGFI3VYTJI5OHVT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:05:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DJ/ugCoMOlz3WqDCv8FNsX49yVZGjzeI0gnKT86TrOA1CAAyyhddVZ7PzVsEiPHL+DYMeOD2LanSW2p1RpTFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:36:44.063281Z"},"content_sha256":"adac58ac1a1b2c7a145f1e4dc9d153375ee7b8733f2ffb3ea8209d4ae858c4d4","schema_version":"1.0","event_id":"sha256:adac58ac1a1b2c7a145f1e4dc9d153375ee7b8733f2ffb3ea8209d4ae858c4d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT/bundle.json","state_url":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T04:36:44Z","links":{"resolver":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT","bundle":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT/bundle.json","state":"https://pith.science/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACU7XKWFB3JNGFI3VYTJI5OHVT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ACU7XKWFB3JNGFI3VYTJI5OHVT","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":"ce3beccc6a735e5a5ba40bc31ca7ebc6d4b7e9847147c41722375450349c3abc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-25T16:20:03Z","title_canon_sha256":"fa0cebe4aceecb7b14441d5e86d2c4485cf5693519ccde0c9b704a8ee0bb6216"},"schema_version":"1.0","source":{"id":"2605.26002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26002","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26002v1","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26002","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"ACU7XKWFB3JN","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"ACU7XKWFB3JNGFI3","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"ACU7XKWF","created_at":"2026-05-26T02:05:22Z"}],"graph_snapshots":[{"event_id":"sha256:adac58ac1a1b2c7a145f1e4dc9d153375ee7b8733f2ffb3ea8209d4ae858c4d4","target":"graph","created_at":"2026-05-26T02:05:22Z","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/2605.26002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Heuiseok Lim, Hyeonseok Moon, Jia-Heui Ju, Seongtae Hong, Youngjoon Jang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-25T16:20:03Z","title":"SemBridge: Language Transfer in Sparse Encoders via Multilingual Semantic Bridges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26002","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":"sha256:696f625e094eaba4db75d9a1ebebee84acec5c370caceb6012600706f0b09693","target":"record","created_at":"2026-05-26T02:05:22Z","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":"ce3beccc6a735e5a5ba40bc31ca7ebc6d4b7e9847147c41722375450349c3abc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-25T16:20:03Z","title_canon_sha256":"fa0cebe4aceecb7b14441d5e86d2c4485cf5693519ccde0c9b704a8ee0bb6216"},"schema_version":"1.0","source":{"id":"2605.26002","kind":"arxiv","version":1}},"canonical_sha256":"00a9fbaac50ed2d3151bae269475c7acd927b5339c9886630ae6c59a1db583fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00a9fbaac50ed2d3151bae269475c7acd927b5339c9886630ae6c59a1db583fb","first_computed_at":"2026-05-26T02:05:22.694750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:22.694750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XszDwy/4daL0bv4+h8wg/0Xa3VuEYE2+4yTkfolqlanvcn0CRiVgpat/CRf0+CjlNyHQeS6fUs4ePdDmZANuAQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:22.695520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:696f625e094eaba4db75d9a1ebebee84acec5c370caceb6012600706f0b09693","sha256:adac58ac1a1b2c7a145f1e4dc9d153375ee7b8733f2ffb3ea8209d4ae858c4d4"],"state_sha256":"7b30d22fdc9da1874c500dd1db5767ea8553bf7b9b608e871976040a0c2075a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oHzFl09nJGbuaRF4ymf0vU4Thpa295P7SRlFf2/05WqdejhsKncsKbNKrwsOo7ANl9VMf5vHKPBY2HNKfbxcAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T04:36:44.065457Z","bundle_sha256":"feaa9675592c2cec66ce89ee91ccc43028c76d7c84bc4479661ec2c7f27f5225"}}