{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZW7QPK3OXBRVIWCBKSHXG2VQ7B","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":"c11dd7b89747427435fd8c772fbf0a957cbbc54e4e61844433aca41dc9bbb7d3","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-08T14:44:23Z","title_canon_sha256":"fff650b8a8d661f722264a644f0ac6b9fd4b0e821a79eb04aa0c669ccf622751"},"schema_version":"1.0","source":{"id":"2306.05245","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05245","created_at":"2026-07-05T06:18:54Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05245v1","created_at":"2026-07-05T06:18:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05245","created_at":"2026-07-05T06:18:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZW7QPK3OXBRV","created_at":"2026-07-05T06:18:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZW7QPK3OXBRVIWCB","created_at":"2026-07-05T06:18:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZW7QPK3O","created_at":"2026-07-05T06:18:54Z"}],"graph_snapshots":[{"event_id":"sha256:7a7d1b1b6ffe867e708927589338b022980b2468b23f3d597b191eb0d3aa6e11","target":"graph","created_at":"2026-07-05T06:18:54Z","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/2306.05245/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using audio and text embeddings jointly for Keyword Spotting (KWS) has shown high-quality results, but the key challenge of how to semantically align two embeddings for multi-word keywords of different sequence lengths remains largely unsolved. In this paper, we propose an audio-text-based end-to-end model architecture for flexible keyword spotting (KWS), which builds upon learned audio and text embeddings. Our architecture uses a novel dynamic programming-based algorithm, Dynamic Sequence Partitioning (DSP), to optimally partition the audio sequence into the same length as the word-based text","authors_text":"Devang Naik, Kumari Nishu, Minsik Cho","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-08T14:44:23Z","title":"Matching Latent Encoding for Audio-Text based Keyword Spotting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05245","kind":"arxiv","version":1},"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":"sha256:63e9181e6a198e03f9a82006eb84192a887ef6e9b9994db60280faf55667fedf","target":"record","created_at":"2026-07-05T06:18:54Z","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":"c11dd7b89747427435fd8c772fbf0a957cbbc54e4e61844433aca41dc9bbb7d3","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-08T14:44:23Z","title_canon_sha256":"fff650b8a8d661f722264a644f0ac6b9fd4b0e821a79eb04aa0c669ccf622751"},"schema_version":"1.0","source":{"id":"2306.05245","kind":"arxiv","version":1}},"canonical_sha256":"cdbf07ab6eb863545841548f736ab0f84deb4794155ed6322676e7011a36c522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdbf07ab6eb863545841548f736ab0f84deb4794155ed6322676e7011a36c522","first_computed_at":"2026-07-05T06:18:54.453818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:18:54.453818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XX+7amQdl+Jv0WMRMFEv8Z+oxaF2+9Ek+xvXRb7xDuPKwYR3f0MPwW+BDTU2CS53adHodIdeNoyngtxvoX3rCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:18:54.454330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05245","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63e9181e6a198e03f9a82006eb84192a887ef6e9b9994db60280faf55667fedf","sha256:7a7d1b1b6ffe867e708927589338b022980b2468b23f3d597b191eb0d3aa6e11"],"state_sha256":"0b69c1d9543c287e152c8601b6e00ab3e05187c0d75e9dea0939191d7011f787"}