{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CSKD2ZGCP7IVSWX2JPVZZTUS4L","short_pith_number":"pith:CSKD2ZGC","schema_version":"1.0","canonical_sha256":"14943d64c27fd1595afa4beb9cce92e2c2e7a5fbda46954ffae5081c99f843c0","source":{"kind":"arxiv","id":"2607.10239","version":1},"attestation_state":"computed","paper":{"title":"Multilingual Semantic Retrieval for Apple Music Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Kevin Sebastian, Leo Le, Nick Tucey, Santosh Shankar, Vishalaksh Aggarwal, Vivek Kanojiya","submitted_at":"2026-07-11T10:00:48Z","abstract_excerpt":"Apple Music serves listeners across 150+ storefronts in dozens of languages, with a catalog that grows by hundreds of thousands of new tracks daily. At this scale, search recall on misspelled, transliterated, and cross-lingual queries becomes a dominant driver of session quality, particularly for tail queries that account for the majority of unique queries. We present a multilingual semantic retrieval system built on a 305M-parameter Siamese bi-encoder fine-tuned from GTE-multilingual-base with curriculum-scheduled multi-objective training. The model is integrated into the search stack via a h"},"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":"2607.10239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-11T10:00:48Z","cross_cats_sorted":[],"title_canon_sha256":"e4e3f65ef9cb0dc089c4a6ed1e78a117d976469be1b1e79519f7972ea36ad1c0","abstract_canon_sha256":"1d10c5d8e25678284f64713d41188a00c94a668f9e663f755b757f13294f4bef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:20:32.279975Z","signature_b64":"Cb3ITfJEyA4FVt23QxaTZBnUcsx8Ra+7y4QhBRB/oBSRkpI389inYC+m0yByG8INMoEkuoLodbFr+KDHXpQiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14943d64c27fd1595afa4beb9cce92e2c2e7a5fbda46954ffae5081c99f843c0","last_reissued_at":"2026-07-14T01:20:32.279163Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:20:32.279163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Semantic Retrieval for Apple Music Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Kevin Sebastian, Leo Le, Nick Tucey, Santosh Shankar, Vishalaksh Aggarwal, Vivek Kanojiya","submitted_at":"2026-07-11T10:00:48Z","abstract_excerpt":"Apple Music serves listeners across 150+ storefronts in dozens of languages, with a catalog that grows by hundreds of thousands of new tracks daily. At this scale, search recall on misspelled, transliterated, and cross-lingual queries becomes a dominant driver of session quality, particularly for tail queries that account for the majority of unique queries. We present a multilingual semantic retrieval system built on a 305M-parameter Siamese bi-encoder fine-tuned from GTE-multilingual-base with curriculum-scheduled multi-objective training. The model is integrated into the search stack via a h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10239","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/2607.10239/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":"2607.10239","created_at":"2026-07-14T01:20:32.279590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10239v1","created_at":"2026-07-14T01:20:32.279590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10239","created_at":"2026-07-14T01:20:32.279590+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSKD2ZGCP7IV","created_at":"2026-07-14T01:20:32.279590+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSKD2ZGCP7IVSWX2","created_at":"2026-07-14T01:20:32.279590+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSKD2ZGC","created_at":"2026-07-14T01:20:32.279590+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/CSKD2ZGCP7IVSWX2JPVZZTUS4L","json":"https://pith.science/pith/CSKD2ZGCP7IVSWX2JPVZZTUS4L.json","graph_json":"https://pith.science/api/pith-number/CSKD2ZGCP7IVSWX2JPVZZTUS4L/graph.json","events_json":"https://pith.science/api/pith-number/CSKD2ZGCP7IVSWX2JPVZZTUS4L/events.json","paper":"https://pith.science/paper/CSKD2ZGC"},"agent_actions":{"view_html":"https://pith.science/pith/CSKD2ZGCP7IVSWX2JPVZZTUS4L","download_json":"https://pith.science/pith/CSKD2ZGCP7IVSWX2JPVZZTUS4L.json","view_paper":"https://pith.science/paper/CSKD2ZGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10239&json=true","fetch_graph":"https://pith.science/api/pith-number/CSKD2ZGCP7IVSWX2JPVZZTUS4L/graph.json","fetch_events":"https://pith.science/api/pith-number/CSKD2ZGCP7IVSWX2JPVZZTUS4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSKD2ZGCP7IVSWX2JPVZZTUS4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSKD2ZGCP7IVSWX2JPVZZTUS4L/action/storage_attestation","attest_author":"https://pith.science/pith/CSKD2ZGCP7IVSWX2JPVZZTUS4L/action/author_attestation","sign_citation":"https://pith.science/pith/CSKD2ZGCP7IVSWX2JPVZZTUS4L/action/citation_signature","submit_replication":"https://pith.science/pith/CSKD2ZGCP7IVSWX2JPVZZTUS4L/action/replication_record"}},"created_at":"2026-07-14T01:20:32.279590+00:00","updated_at":"2026-07-14T01:20:32.279590+00:00"}