{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_a95a1bfb9f3d4792fc094eee57790cb417f93bd1ac63514b6f72e04c2acd0488","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_a95a1bfb9f3d4792fc094eee57790cb417f93bd1ac63514b6f72e04c2acd0488","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"aa55f5f74173002a1781f9575a8554a004865fa1be6a71a161e86a1e447ea490","published":"Tue, 19 May 2026 00:00:00 -0400","receipt_hash":"aa55f5f74173002a1781f9575a8554a004865fa1be6a71a161e86a1e447ea490","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"aa55f5f74173002a1781f9575a8554a004865fa1be6a71a161e86a1e447ea490","observed_at":"2026-05-19T04:43:36.782648Z","parent_run_hash":"fefa4c726316a95c5dda9fc1ca07a38a811cf7ffa9825b2f09b365abacd9b32d","published":"Tue, 19 May 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2605.17762v1 Announce Type: new \nAbstract: 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 ability to learn from long-tail queries. In this work, we present a \\textbf{robust neural sparse retrieval system} designed to maximize exploration efficiency. We adapt a state-of-the-art \\textbf{inference-free} sparse retrieval architecture to the music domain, combining it with an effective \\textbf{domain-specific granular subword tokenization strateg","title":"Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search","url":"https://arxiv.org/abs/2605.17762","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.17762v1 Announce Type: new \nAbstract: 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 ability to learn from long-tail queries. In this work, we present a \\textbf{robust neural sparse retrieval system} designed to maximize exploration efficiency. We adapt a state-of-the-art \\textbf{inference-free} sparse retrieval architecture to the music domain, combining it with an effective \\textbf{domain-specific granular subword tokenization strateg","title":"Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-19T04:43:36Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.17762"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ac32265cd7b52c7f6c76a14197c35a91d38bc6af3c1d18f4c4513be7f35fbcb90ebd01d5690af7b88acf60a2e8ef3e112af5fd2907edb203baf774e7bac68e0d","signer":"crovia.substrate","subject":{"observed_at":"2026-05-19T04:43:36Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.17762"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"8f58ee356f6b0017b67d18af3735e0b3a8811e3ed61265531077bf493c9678d6","leaf_index":142437,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"3d42c9e134a9cd18f5bcfb8d2428636fd027823174f64b5d826a1dac2074fa27","side":"left"},{"sibling":"ee0bec9e702a8c621214c18212324e6f1e433fdc9bb27ff80d54f235ac02d7a4","side":"right"},{"sibling":"b94acc79c19f8b8878401b4a3977638c9e0709d684a48d196a85a470d33e48d3","side":"left"},{"sibling":"6e9d45a5d0c78d61fd8ff60ee9854295ba5e0f0e7f559954a7860b0f95ba93be","side":"right"},{"sibling":"5ea3ab8731d2714ce8ee2e8fd166d33614ea750648fc4dcb8bcd89dfc7559705","side":"right"},{"sibling":"9ab16765688dc11b76e845a853bd1dad5ea996c09d650a840ee90d85838b1f58","side":"left"},{"sibling":"d0b56e9dc101b8d881b8d3739227c4d0aaca1cf96fef1945825f5d56fd5664ff","side":"left"},{"sibling":"6b37a038a508ab9f6e9513e2a88094021d9ee3a5e516d7a811c9cd8e3ad55e3c","side":"right"},{"sibling":"bbd9a0327a91b5df2093631f9bf2665ba64be214117a6f2060ca0e6e4c6bf27d","side":"right"},{"sibling":"2e0ce989d789c88e796991ef014ce7e4e1f96c0d4ede9da8d31afcf5ba6a8f46","side":"right"},{"sibling":"202f1bead178ef3785968d50d3d188264a95192a077654c331612e04a34cbfbe","side":"left"},{"sibling":"72249c8c8b068386e35d16f4bd0bbeb9ba820ca217ef0f0d28396c9fe493f5f0","side":"left"},{"sibling":"ea64599340f7ffdf17ad0cbc1d9401ef8870a347e3847bdc106d06b1673df09c","side":"right"},{"sibling":"8f4c0fbe56b6c010fbb8c782ebcd478079bb3f991d8704e2534209a075d9163c","side":"left"},{"sibling":"4db1f363729507e27a60851cf6ed334d7b9acdef194ed7d419aba4d2bd367a4a","side":"right"},{"sibling":"a86ee18c45e7fcc408b6007eaece05aa75b2d9ae30252e9e878462b4dffbef7b","side":"right"},{"sibling":"1d18e7663d43ccff0122ecc7ee12645bb16afb607b218e81b1ea2408f863cb78","side":"right"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":143302,"merkle_root":"999156d40a7c61d9ddd52b7338f3cbda3e68f53bace070c7b616ea194e23b123","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260519T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-19T05:37:30Z","sig_algorithm":"ed25519","signature":"b1a252cc66ff32bed1d10dd88a6b2a200e3856d3dbcfcc4ee55e02e00f3d548e854ed9c544704b222bd5d315492c4a935ba2d90d727c585a67899b0ad602fc05","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_a95a1bfb9f3d4792fc094eee57790cb417f93bd1ac63514b6f72e04c2acd0488"}}