{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QFIXZYXRH54CLK3RSLCBIIEJEV","short_pith_number":"pith:QFIXZYXR","schema_version":"1.0","canonical_sha256":"81517ce2f13f7825ab7192c4142089257ff46e93bea2846c00e8d068b4869f08","source":{"kind":"arxiv","id":"2305.12839","version":2},"attestation_state":"computed","paper":{"title":"CopyNE: Better Contextual ASR by Copying Named Entities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baoxing Huai, Min Zhang, Shilin Zhou, Yu Hong, Zhefeng Wang, Zhenghua Li","submitted_at":"2023-05-22T09:03:11Z","abstract_excerpt":"End-to-end automatic speech recognition (ASR) systems have made significant progress in general scenarios. However, it remains challenging to transcribe contextual named entities (NEs) in the contextual ASR scenario. Previous approaches have attempted to address this by utilizing the NE dictionary. These approaches treat entities as individual tokens and generate them token-by-token, which may result in incomplete transcriptions of entities. In this paper, we treat entities as indivisible wholes and introduce the idea of copying into ASR. We design a systematic mechanism called CopyNE, which c"},"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":"2305.12839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T09:03:11Z","cross_cats_sorted":[],"title_canon_sha256":"f5580d4616a419aa32fd2fc9ca48fe132f92a6a518e103e48d61f4e1d3b8a08d","abstract_canon_sha256":"acec9d956da18112382479e45d96f7dca927e511fc9099d111a15f0caea981a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:09.036209Z","signature_b64":"5m9c4YgGYGOUxLRL33S2/+ZShljCiTZCpYB3Ql5j2WIZDYU0HY6DXG7wASFdzSsVMKYlcePA8//m4O9FzvMgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81517ce2f13f7825ab7192c4142089257ff46e93bea2846c00e8d068b4869f08","last_reissued_at":"2026-07-05T08:23:09.035700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:09.035700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CopyNE: Better Contextual ASR by Copying Named Entities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baoxing Huai, Min Zhang, Shilin Zhou, Yu Hong, Zhefeng Wang, Zhenghua Li","submitted_at":"2023-05-22T09:03:11Z","abstract_excerpt":"End-to-end automatic speech recognition (ASR) systems have made significant progress in general scenarios. However, it remains challenging to transcribe contextual named entities (NEs) in the contextual ASR scenario. Previous approaches have attempted to address this by utilizing the NE dictionary. These approaches treat entities as individual tokens and generate them token-by-token, which may result in incomplete transcriptions of entities. In this paper, we treat entities as indivisible wholes and introduce the idea of copying into ASR. We design a systematic mechanism called CopyNE, which c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12839","kind":"arxiv","version":2},"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/2305.12839/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":"2305.12839","created_at":"2026-07-05T08:23:09.035771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12839v2","created_at":"2026-07-05T08:23:09.035771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12839","created_at":"2026-07-05T08:23:09.035771+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFIXZYXRH54C","created_at":"2026-07-05T08:23:09.035771+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFIXZYXRH54CLK3R","created_at":"2026-07-05T08:23:09.035771+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFIXZYXR","created_at":"2026-07-05T08:23:09.035771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10456","citing_title":"Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFIXZYXRH54CLK3RSLCBIIEJEV","json":"https://pith.science/pith/QFIXZYXRH54CLK3RSLCBIIEJEV.json","graph_json":"https://pith.science/api/pith-number/QFIXZYXRH54CLK3RSLCBIIEJEV/graph.json","events_json":"https://pith.science/api/pith-number/QFIXZYXRH54CLK3RSLCBIIEJEV/events.json","paper":"https://pith.science/paper/QFIXZYXR"},"agent_actions":{"view_html":"https://pith.science/pith/QFIXZYXRH54CLK3RSLCBIIEJEV","download_json":"https://pith.science/pith/QFIXZYXRH54CLK3RSLCBIIEJEV.json","view_paper":"https://pith.science/paper/QFIXZYXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12839&json=true","fetch_graph":"https://pith.science/api/pith-number/QFIXZYXRH54CLK3RSLCBIIEJEV/graph.json","fetch_events":"https://pith.science/api/pith-number/QFIXZYXRH54CLK3RSLCBIIEJEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFIXZYXRH54CLK3RSLCBIIEJEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFIXZYXRH54CLK3RSLCBIIEJEV/action/storage_attestation","attest_author":"https://pith.science/pith/QFIXZYXRH54CLK3RSLCBIIEJEV/action/author_attestation","sign_citation":"https://pith.science/pith/QFIXZYXRH54CLK3RSLCBIIEJEV/action/citation_signature","submit_replication":"https://pith.science/pith/QFIXZYXRH54CLK3RSLCBIIEJEV/action/replication_record"}},"created_at":"2026-07-05T08:23:09.035771+00:00","updated_at":"2026-07-05T08:23:09.035771+00:00"}