{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:766ZOBMO3DIG4T23VDCNBKINDQ","short_pith_number":"pith:766ZOBMO","schema_version":"1.0","canonical_sha256":"ffbd97058ed8d06e4f5ba8c4d0a90d1c38c253f5f27846f876927d53fdf18cc3","source":{"kind":"arxiv","id":"2605.28642","version":1},"attestation_state":"computed","paper":{"title":"Bandwidth-Efficient and Privacy-Preserving Edge-Cloud Many-to-Many Speech Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bing Qin, Bo Yang, Kaiyuan Liu, Ming Liu, Yang Xiang, Yexing Du, Youcheng Pan","submitted_at":"2026-05-27T15:47:33Z","abstract_excerpt":"Multimodal large language models (MLLMs) have demonstrated significant potential for speech-to-text translation (S2TT). However, existing deployment paradigms face critical challenges: pure on-device models suffer from resource constraints, while centralized cloud systems incur severe privacy risks and bandwidth bottlenecks by transmitting raw voice data. Furthermore, most models exhibit English-centric biases, restricting many-to-many translation scaling. In this paper, we propose Edge-cloud Speech Recognition and Translation (ESRT), a privacy-preserving and bandwidth-efficient collaborative "},"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":"2605.28642","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T15:47:33Z","cross_cats_sorted":[],"title_canon_sha256":"77a5df443e80e6d55074285bb4aa6f88d4b920d831abc9d6eab00fe33c485147","abstract_canon_sha256":"78e5a55d083c7c1da30ccb7c202a2ab55eaea1a994f1b71fb2923cd457420f80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:58.677368Z","signature_b64":"wVZH0h8TeNTNNlVtvlkwb7gNcImbUC9S4irs2Q5fKAANeE6eRffPKRsqgcpfmKcKudRZ5pPTsKwPbAxaAWRsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffbd97058ed8d06e4f5ba8c4d0a90d1c38c253f5f27846f876927d53fdf18cc3","last_reissued_at":"2026-05-28T02:04:58.676954Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:58.676954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bandwidth-Efficient and Privacy-Preserving Edge-Cloud Many-to-Many Speech Translation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bing Qin, Bo Yang, Kaiyuan Liu, Ming Liu, Yang Xiang, Yexing Du, Youcheng Pan","submitted_at":"2026-05-27T15:47:33Z","abstract_excerpt":"Multimodal large language models (MLLMs) have demonstrated significant potential for speech-to-text translation (S2TT). However, existing deployment paradigms face critical challenges: pure on-device models suffer from resource constraints, while centralized cloud systems incur severe privacy risks and bandwidth bottlenecks by transmitting raw voice data. Furthermore, most models exhibit English-centric biases, restricting many-to-many translation scaling. In this paper, we propose Edge-cloud Speech Recognition and Translation (ESRT), a privacy-preserving and bandwidth-efficient collaborative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28642","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/2605.28642/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":"2605.28642","created_at":"2026-05-28T02:04:58.677011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28642v1","created_at":"2026-05-28T02:04:58.677011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28642","created_at":"2026-05-28T02:04:58.677011+00:00"},{"alias_kind":"pith_short_12","alias_value":"766ZOBMO3DIG","created_at":"2026-05-28T02:04:58.677011+00:00"},{"alias_kind":"pith_short_16","alias_value":"766ZOBMO3DIG4T23","created_at":"2026-05-28T02:04:58.677011+00:00"},{"alias_kind":"pith_short_8","alias_value":"766ZOBMO","created_at":"2026-05-28T02:04:58.677011+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/766ZOBMO3DIG4T23VDCNBKINDQ","json":"https://pith.science/pith/766ZOBMO3DIG4T23VDCNBKINDQ.json","graph_json":"https://pith.science/api/pith-number/766ZOBMO3DIG4T23VDCNBKINDQ/graph.json","events_json":"https://pith.science/api/pith-number/766ZOBMO3DIG4T23VDCNBKINDQ/events.json","paper":"https://pith.science/paper/766ZOBMO"},"agent_actions":{"view_html":"https://pith.science/pith/766ZOBMO3DIG4T23VDCNBKINDQ","download_json":"https://pith.science/pith/766ZOBMO3DIG4T23VDCNBKINDQ.json","view_paper":"https://pith.science/paper/766ZOBMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28642&json=true","fetch_graph":"https://pith.science/api/pith-number/766ZOBMO3DIG4T23VDCNBKINDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/766ZOBMO3DIG4T23VDCNBKINDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/766ZOBMO3DIG4T23VDCNBKINDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/766ZOBMO3DIG4T23VDCNBKINDQ/action/storage_attestation","attest_author":"https://pith.science/pith/766ZOBMO3DIG4T23VDCNBKINDQ/action/author_attestation","sign_citation":"https://pith.science/pith/766ZOBMO3DIG4T23VDCNBKINDQ/action/citation_signature","submit_replication":"https://pith.science/pith/766ZOBMO3DIG4T23VDCNBKINDQ/action/replication_record"}},"created_at":"2026-05-28T02:04:58.677011+00:00","updated_at":"2026-05-28T02:04:58.677011+00:00"}