{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E4NSPUJKHIZ6GQYRUPQXV5CO72","short_pith_number":"pith:E4NSPUJK","canonical_record":{"source":{"id":"2404.01616","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T03:42:28Z","cross_cats_sorted":["cs.IR","cs.SD","eess.AS"],"title_canon_sha256":"f3cd12d6849e996fa488008576990e7997737d4eb6d9fc1cf3486da54aa16ec9","abstract_canon_sha256":"9d87a674a8e3ecd2742b00a138200b55493cca26cd205193ff4c34c8d55bec2f"},"schema_version":"1.0"},"canonical_sha256":"271b27d12a3a33e34311a3e17af44efe92c1619cdd9863d3121327ba8fe2a94b","source":{"kind":"arxiv","id":"2404.01616","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01616","created_at":"2026-07-05T08:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01616v3","created_at":"2026-07-05T08:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01616","created_at":"2026-07-05T08:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"E4NSPUJKHIZ6","created_at":"2026-07-05T08:42:22Z"},{"alias_kind":"pith_short_16","alias_value":"E4NSPUJKHIZ6GQYR","created_at":"2026-07-05T08:42:22Z"},{"alias_kind":"pith_short_8","alias_value":"E4NSPUJK","created_at":"2026-07-05T08:42:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E4NSPUJKHIZ6GQYRUPQXV5CO72","target":"record","payload":{"canonical_record":{"source":{"id":"2404.01616","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T03:42:28Z","cross_cats_sorted":["cs.IR","cs.SD","eess.AS"],"title_canon_sha256":"f3cd12d6849e996fa488008576990e7997737d4eb6d9fc1cf3486da54aa16ec9","abstract_canon_sha256":"9d87a674a8e3ecd2742b00a138200b55493cca26cd205193ff4c34c8d55bec2f"},"schema_version":"1.0"},"canonical_sha256":"271b27d12a3a33e34311a3e17af44efe92c1619cdd9863d3121327ba8fe2a94b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:22.330183Z","signature_b64":"Sc8Gpzi6bTMzmJoIEP2WWNN4KnFcuJt8G60qRg9piZ8H+tWD8BN6GUgeVvv9yZdSrR2L0Xhj7SeinB8cPt4XAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"271b27d12a3a33e34311a3e17af44efe92c1619cdd9863d3121327ba8fe2a94b","last_reissued_at":"2026-07-05T08:42:22.329654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:22.329654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.01616","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X09IfI6aJo3bHp3PzrI/kqV7LR7+YBkZGRXE0UzAkdOcbs2b6y/oiusiZDCTdnkh0n1d+8kr8x6UwY4aSjemBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:58:49.613357Z"},"content_sha256":"02c6209bfb97e46affe6d4cd07e1bd17001e74107986693f3dfe7e265e9af90d","schema_version":"1.0","event_id":"sha256:02c6209bfb97e46affe6d4cd07e1bd17001e74107986693f3dfe7e265e9af90d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E4NSPUJKHIZ6GQYRUPQXV5CO72","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transforming LLMs into Cross-modal and Cross-lingual Retrieval Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Daniel Cer, Frank Palma Gomez, Gustavo Hernandez Abrego, Ramon Sanabria, Siddharth Dalmia, Yun-hsuan Sung","submitted_at":"2024-04-02T03:42:28Z","abstract_excerpt":"Large language models (LLMs) are trained on text-only data that go far beyond the languages with paired speech and text data. At the same time, Dual Encoder (DE) based retrieval systems project queries and documents into the same embedding space and have demonstrated their success in retrieval and bi-text mining. To match speech and text in many languages, we propose using LLMs to initialize multi-modal DE retrieval systems. Unlike traditional methods, our system doesn't require speech data during LLM pre-training and can exploit LLM's multilingual text understanding capabilities to match spee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01616","kind":"arxiv","version":3},"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/2404.01616/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":"2026-07-05T08:42:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MdFAdRzdptGdSzwsWxSGIZhBwiLhrU+OW9AwpvsLKGlxRW3PV1dd2vsnsDKnrN1yv8EMwt7PY7e7sQ9a1jt6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:58:49.614427Z"},"content_sha256":"b44ae729f8c568158dd0294e5ae226fb85c108455cde2032c8aae69e390e1f03","schema_version":"1.0","event_id":"sha256:b44ae729f8c568158dd0294e5ae226fb85c108455cde2032c8aae69e390e1f03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E4NSPUJKHIZ6GQYRUPQXV5CO72/bundle.json","state_url":"https://pith.science/pith/E4NSPUJKHIZ6GQYRUPQXV5CO72/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E4NSPUJKHIZ6GQYRUPQXV5CO72/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":"2026-08-19T19:58:49Z","links":{"resolver":"https://pith.science/pith/E4NSPUJKHIZ6GQYRUPQXV5CO72","bundle":"https://pith.science/pith/E4NSPUJKHIZ6GQYRUPQXV5CO72/bundle.json","state":"https://pith.science/pith/E4NSPUJKHIZ6GQYRUPQXV5CO72/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E4NSPUJKHIZ6GQYRUPQXV5CO72/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E4NSPUJKHIZ6GQYRUPQXV5CO72","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":"9d87a674a8e3ecd2742b00a138200b55493cca26cd205193ff4c34c8d55bec2f","cross_cats_sorted":["cs.IR","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T03:42:28Z","title_canon_sha256":"f3cd12d6849e996fa488008576990e7997737d4eb6d9fc1cf3486da54aa16ec9"},"schema_version":"1.0","source":{"id":"2404.01616","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01616","created_at":"2026-07-05T08:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01616v3","created_at":"2026-07-05T08:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01616","created_at":"2026-07-05T08:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"E4NSPUJKHIZ6","created_at":"2026-07-05T08:42:22Z"},{"alias_kind":"pith_short_16","alias_value":"E4NSPUJKHIZ6GQYR","created_at":"2026-07-05T08:42:22Z"},{"alias_kind":"pith_short_8","alias_value":"E4NSPUJK","created_at":"2026-07-05T08:42:22Z"}],"graph_snapshots":[{"event_id":"sha256:b44ae729f8c568158dd0294e5ae226fb85c108455cde2032c8aae69e390e1f03","target":"graph","created_at":"2026-07-05T08:42:22Z","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/2404.01616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are trained on text-only data that go far beyond the languages with paired speech and text data. At the same time, Dual Encoder (DE) based retrieval systems project queries and documents into the same embedding space and have demonstrated their success in retrieval and bi-text mining. To match speech and text in many languages, we propose using LLMs to initialize multi-modal DE retrieval systems. Unlike traditional methods, our system doesn't require speech data during LLM pre-training and can exploit LLM's multilingual text understanding capabilities to match spee","authors_text":"Daniel Cer, Frank Palma Gomez, Gustavo Hernandez Abrego, Ramon Sanabria, Siddharth Dalmia, Yun-hsuan Sung","cross_cats":["cs.IR","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T03:42:28Z","title":"Transforming LLMs into Cross-modal and Cross-lingual Retrieval Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01616","kind":"arxiv","version":3},"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":"sha256:02c6209bfb97e46affe6d4cd07e1bd17001e74107986693f3dfe7e265e9af90d","target":"record","created_at":"2026-07-05T08:42:22Z","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":"9d87a674a8e3ecd2742b00a138200b55493cca26cd205193ff4c34c8d55bec2f","cross_cats_sorted":["cs.IR","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T03:42:28Z","title_canon_sha256":"f3cd12d6849e996fa488008576990e7997737d4eb6d9fc1cf3486da54aa16ec9"},"schema_version":"1.0","source":{"id":"2404.01616","kind":"arxiv","version":3}},"canonical_sha256":"271b27d12a3a33e34311a3e17af44efe92c1619cdd9863d3121327ba8fe2a94b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"271b27d12a3a33e34311a3e17af44efe92c1619cdd9863d3121327ba8fe2a94b","first_computed_at":"2026-07-05T08:42:22.329654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:22.329654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sc8Gpzi6bTMzmJoIEP2WWNN4KnFcuJt8G60qRg9piZ8H+tWD8BN6GUgeVvv9yZdSrR2L0Xhj7SeinB8cPt4XAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:22.330183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01616","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02c6209bfb97e46affe6d4cd07e1bd17001e74107986693f3dfe7e265e9af90d","sha256:b44ae729f8c568158dd0294e5ae226fb85c108455cde2032c8aae69e390e1f03"],"state_sha256":"5218ffba673615b8921d4af38a4875acf6537f7a4a1b08a6f01d8e77bf87f148"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjSp1VKnHMRkE3nlMtT6uFYIecN3/YQBkFxw2Bqx8sAsSdyUxsB2Dle6bouRI4jLzeIpkCLRbhP2zS04SigsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T19:58:49.620471Z","bundle_sha256":"d0f9657df83d8d39b0a80a47a78cf1f008f122b698d4809cddf8be75ee7e4b9e"}}