{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WJAG6LDFZ6GABSOQ2FVQEF3JPN","short_pith_number":"pith:WJAG6LDF","schema_version":"1.0","canonical_sha256":"b2406f2c65cf8c00c9d0d16b0217697b50c08fb4f719a50bdda7b90a5456880f","source":{"kind":"arxiv","id":"2509.05908","version":1},"attestation_state":"computed","paper":{"title":"Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jiqing Han, Qian Chen, Shiliang Zhang, Ying Shi, Yue Gu, Zhihao Du","submitted_at":"2025-09-07T03:46:59Z","abstract_excerpt":"Recently, cross-attention-based contextual automatic speech recognition (ASR) models have made notable advancements in recognizing personalized biasing phrases. However, the effectiveness of cross-attention is affected by variations in biasing information volume, especially when the length of the biasing list increases significantly. We find that, regardless of the length of the biasing list, only a limited amount of biasing information is most relevant to a specific ASR intermediate representation. Therefore, by identifying and integrating the most relevant biasing information rather than the"},"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":"2509.05908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T03:46:59Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"cedccbde8450aaf0f7978e074a0853a5e4b296780cfb24593f47266c27e6ea19","abstract_canon_sha256":"70f0694fc4665674db60688fb9f1406a0f864e3a660c8d6ea0c821f7c76e2a38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:26.333687Z","signature_b64":"vfP8bYeRKlW/C8Yx6fJ4sDC1tfe1H695t3nSxBKUfRDliyVbevDOLZPD4WYfu6g2R57YOe4jsnpjtlymbcSUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2406f2c65cf8c00c9d0d16b0217697b50c08fb4f719a50bdda7b90a5456880f","last_reissued_at":"2026-07-05T12:06:26.333252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:26.333252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jiqing Han, Qian Chen, Shiliang Zhang, Ying Shi, Yue Gu, Zhihao Du","submitted_at":"2025-09-07T03:46:59Z","abstract_excerpt":"Recently, cross-attention-based contextual automatic speech recognition (ASR) models have made notable advancements in recognizing personalized biasing phrases. However, the effectiveness of cross-attention is affected by variations in biasing information volume, especially when the length of the biasing list increases significantly. We find that, regardless of the length of the biasing list, only a limited amount of biasing information is most relevant to a specific ASR intermediate representation. Therefore, by identifying and integrating the most relevant biasing information rather than the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05908","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/2509.05908/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":"2509.05908","created_at":"2026-07-05T12:06:26.333308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05908v1","created_at":"2026-07-05T12:06:26.333308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05908","created_at":"2026-07-05T12:06:26.333308+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJAG6LDFZ6GA","created_at":"2026-07-05T12:06:26.333308+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJAG6LDFZ6GABSOQ","created_at":"2026-07-05T12:06:26.333308+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJAG6LDF","created_at":"2026-07-05T12:06:26.333308+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/WJAG6LDFZ6GABSOQ2FVQEF3JPN","json":"https://pith.science/pith/WJAG6LDFZ6GABSOQ2FVQEF3JPN.json","graph_json":"https://pith.science/api/pith-number/WJAG6LDFZ6GABSOQ2FVQEF3JPN/graph.json","events_json":"https://pith.science/api/pith-number/WJAG6LDFZ6GABSOQ2FVQEF3JPN/events.json","paper":"https://pith.science/paper/WJAG6LDF"},"agent_actions":{"view_html":"https://pith.science/pith/WJAG6LDFZ6GABSOQ2FVQEF3JPN","download_json":"https://pith.science/pith/WJAG6LDFZ6GABSOQ2FVQEF3JPN.json","view_paper":"https://pith.science/paper/WJAG6LDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05908&json=true","fetch_graph":"https://pith.science/api/pith-number/WJAG6LDFZ6GABSOQ2FVQEF3JPN/graph.json","fetch_events":"https://pith.science/api/pith-number/WJAG6LDFZ6GABSOQ2FVQEF3JPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJAG6LDFZ6GABSOQ2FVQEF3JPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJAG6LDFZ6GABSOQ2FVQEF3JPN/action/storage_attestation","attest_author":"https://pith.science/pith/WJAG6LDFZ6GABSOQ2FVQEF3JPN/action/author_attestation","sign_citation":"https://pith.science/pith/WJAG6LDFZ6GABSOQ2FVQEF3JPN/action/citation_signature","submit_replication":"https://pith.science/pith/WJAG6LDFZ6GABSOQ2FVQEF3JPN/action/replication_record"}},"created_at":"2026-07-05T12:06:26.333308+00:00","updated_at":"2026-07-05T12:06:26.333308+00:00"}