{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YYALUACAXRIOD6ZG745OQXBZII","short_pith_number":"pith:YYALUACA","schema_version":"1.0","canonical_sha256":"c600ba0040bc50e1fb26ff3ae85c394210845a7e6d45a8536601d6ca412fa70d","source":{"kind":"arxiv","id":"2507.12252","version":1},"attestation_state":"computed","paper":{"title":"Improving Contextual ASR via Multi-grained Fusion with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Shilin Zhou, Zhenghua Li","submitted_at":"2025-07-16T13:59:32Z","abstract_excerpt":"While end-to-end Automatic Speech Recognition (ASR) models have shown impressive performance in transcribing general speech, they often struggle to accurately recognize contextually relevant keywords, such as proper nouns or user-specific entities.\n  Previous approaches have explored leveraging keyword dictionaries in the textual modality to improve keyword recognition, either through token-level fusion that guides token-by-token generation or phrase-level fusion that enables direct copying of keyword phrases.\n  However, these methods operate at different granularities and have their own limit"},"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":"2507.12252","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T13:59:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f946530720c8c51279f5587f50fd4b3c70ebc466dbcdef99d71ecd0098ebce66","abstract_canon_sha256":"317409cd383bd2b708bb2ec3799ebd283c589103584ffdeafbb48aac371cecd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:17.448227Z","signature_b64":"9lNWtsuJJitgr/qZu7H+S8Uuf9D6JAX5Sl54/lkGBy1RlgYOXFU4xCmTOCETZ0ARbzhSAUqevKc1veEG8NdGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c600ba0040bc50e1fb26ff3ae85c394210845a7e6d45a8536601d6ca412fa70d","last_reissued_at":"2026-07-05T11:38:17.447758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:17.447758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Contextual ASR via Multi-grained Fusion with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Shilin Zhou, Zhenghua Li","submitted_at":"2025-07-16T13:59:32Z","abstract_excerpt":"While end-to-end Automatic Speech Recognition (ASR) models have shown impressive performance in transcribing general speech, they often struggle to accurately recognize contextually relevant keywords, such as proper nouns or user-specific entities.\n  Previous approaches have explored leveraging keyword dictionaries in the textual modality to improve keyword recognition, either through token-level fusion that guides token-by-token generation or phrase-level fusion that enables direct copying of keyword phrases.\n  However, these methods operate at different granularities and have their own limit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12252","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/2507.12252/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":"2507.12252","created_at":"2026-07-05T11:38:17.447812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12252v1","created_at":"2026-07-05T11:38:17.447812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12252","created_at":"2026-07-05T11:38:17.447812+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYALUACAXRIO","created_at":"2026-07-05T11:38:17.447812+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYALUACAXRIOD6ZG","created_at":"2026-07-05T11:38:17.447812+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYALUACA","created_at":"2026-07-05T11:38:17.447812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16896","citing_title":"JSPG: Dynamic Dictionary Filtering via Joint Semantic-Pinyin-Glyph Retrieval for Chinese Contextual ASR","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYALUACAXRIOD6ZG745OQXBZII","json":"https://pith.science/pith/YYALUACAXRIOD6ZG745OQXBZII.json","graph_json":"https://pith.science/api/pith-number/YYALUACAXRIOD6ZG745OQXBZII/graph.json","events_json":"https://pith.science/api/pith-number/YYALUACAXRIOD6ZG745OQXBZII/events.json","paper":"https://pith.science/paper/YYALUACA"},"agent_actions":{"view_html":"https://pith.science/pith/YYALUACAXRIOD6ZG745OQXBZII","download_json":"https://pith.science/pith/YYALUACAXRIOD6ZG745OQXBZII.json","view_paper":"https://pith.science/paper/YYALUACA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12252&json=true","fetch_graph":"https://pith.science/api/pith-number/YYALUACAXRIOD6ZG745OQXBZII/graph.json","fetch_events":"https://pith.science/api/pith-number/YYALUACAXRIOD6ZG745OQXBZII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYALUACAXRIOD6ZG745OQXBZII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYALUACAXRIOD6ZG745OQXBZII/action/storage_attestation","attest_author":"https://pith.science/pith/YYALUACAXRIOD6ZG745OQXBZII/action/author_attestation","sign_citation":"https://pith.science/pith/YYALUACAXRIOD6ZG745OQXBZII/action/citation_signature","submit_replication":"https://pith.science/pith/YYALUACAXRIOD6ZG745OQXBZII/action/replication_record"}},"created_at":"2026-07-05T11:38:17.447812+00:00","updated_at":"2026-07-05T11:38:17.447812+00:00"}