{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:62ZGKKBW26VPTGGSFXRTMDD47D","short_pith_number":"pith:62ZGKKBW","schema_version":"1.0","canonical_sha256":"f6b2652836d7aaf998d22de3360c7cf8cf810cb064f67ba09c1a86a4e3dbc0f7","source":{"kind":"arxiv","id":"2605.17762","version":1},"attestation_state":"computed","paper":{"title":"Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Paul Greyson, Wei Zhang, Yang Yang, Zhichao Geng","submitted_at":"2026-05-18T02:29:25Z","abstract_excerpt":"Music search at the scale of Amazon Music presents a unique challenge: queries frequently deviate from indexed metadata due to misspellings, transpositions, and phonetic variations, yet the retrieval system must operate under strict millisecond-level latency constraints. Our existing learning-to-retrieve system, the High Confidence Index (HCI), learns query-entity associations from customer behavior, relying on continual ``exploration'' to choose candidates. Traditional n-gram matching enables this exploration but suffers from poor semantic robustness and high noise, limiting the system's abil"},"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":"2605.17762","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T02:29:25Z","cross_cats_sorted":[],"title_canon_sha256":"74a8453b9d1aa6627137f35900ad6f30c4902d7396c35c0a13ebc18fabd60d1a","abstract_canon_sha256":"291e30fb6ed32a92e85426168467a3c41af23b816246d792ab92b4f0bf83e222"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:56.919936Z","signature_b64":"1hSFc234D0er29F2lJaYgsCU8C4FoZunmg+syxHpPN04fNLhMHrKJjrfI6agxjI0FKtA7bGG7hND6P/PcyfpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6b2652836d7aaf998d22de3360c7cf8cf810cb064f67ba09c1a86a4e3dbc0f7","last_reissued_at":"2026-05-20T00:04:56.919142Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:56.919142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Paul Greyson, Wei Zhang, Yang Yang, Zhichao Geng","submitted_at":"2026-05-18T02:29:25Z","abstract_excerpt":"Music search at the scale of Amazon Music presents a unique challenge: queries frequently deviate from indexed metadata due to misspellings, transpositions, and phonetic variations, yet the retrieval system must operate under strict millisecond-level latency constraints. Our existing learning-to-retrieve system, the High Confidence Index (HCI), learns query-entity associations from customer behavior, relying on continual ``exploration'' to choose candidates. Traditional n-gram matching enables this exploration but suffers from poor semantic robustness and high noise, limiting the system's abil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17762","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/2605.17762/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":"2605.17762","created_at":"2026-05-20T00:04:56.919243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17762v1","created_at":"2026-05-20T00:04:56.919243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17762","created_at":"2026-05-20T00:04:56.919243+00:00"},{"alias_kind":"pith_short_12","alias_value":"62ZGKKBW26VP","created_at":"2026-05-20T00:04:56.919243+00:00"},{"alias_kind":"pith_short_16","alias_value":"62ZGKKBW26VPTGGS","created_at":"2026-05-20T00:04:56.919243+00:00"},{"alias_kind":"pith_short_8","alias_value":"62ZGKKBW","created_at":"2026-05-20T00:04:56.919243+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/62ZGKKBW26VPTGGSFXRTMDD47D","json":"https://pith.science/pith/62ZGKKBW26VPTGGSFXRTMDD47D.json","graph_json":"https://pith.science/api/pith-number/62ZGKKBW26VPTGGSFXRTMDD47D/graph.json","events_json":"https://pith.science/api/pith-number/62ZGKKBW26VPTGGSFXRTMDD47D/events.json","paper":"https://pith.science/paper/62ZGKKBW"},"agent_actions":{"view_html":"https://pith.science/pith/62ZGKKBW26VPTGGSFXRTMDD47D","download_json":"https://pith.science/pith/62ZGKKBW26VPTGGSFXRTMDD47D.json","view_paper":"https://pith.science/paper/62ZGKKBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17762&json=true","fetch_graph":"https://pith.science/api/pith-number/62ZGKKBW26VPTGGSFXRTMDD47D/graph.json","fetch_events":"https://pith.science/api/pith-number/62ZGKKBW26VPTGGSFXRTMDD47D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62ZGKKBW26VPTGGSFXRTMDD47D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62ZGKKBW26VPTGGSFXRTMDD47D/action/storage_attestation","attest_author":"https://pith.science/pith/62ZGKKBW26VPTGGSFXRTMDD47D/action/author_attestation","sign_citation":"https://pith.science/pith/62ZGKKBW26VPTGGSFXRTMDD47D/action/citation_signature","submit_replication":"https://pith.science/pith/62ZGKKBW26VPTGGSFXRTMDD47D/action/replication_record"}},"created_at":"2026-05-20T00:04:56.919243+00:00","updated_at":"2026-05-20T00:04:56.919243+00:00"}