{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AASXFFKMBZRKDLTFVC7I53KKBD","short_pith_number":"pith:AASXFFKM","schema_version":"1.0","canonical_sha256":"002572954c0e62a1ae65a8be8eed4a08d22081f34efd37adf1d05cb199f1cae3","source":{"kind":"arxiv","id":"2607.08117","version":1},"attestation_state":"computed","paper":{"title":"COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Berlin Chen, Bi-Cheng Yan, Jhih-Rong Guo, Tien-Hong Lo","submitted_at":"2026-07-09T05:26:22Z","abstract_excerpt":"Contextual biasing seeks to integrate external knowledge into automatic speech recognition (ASR) systems to accurately recognize domain-specific entities. In this paper, we propose COALA (Contextualized ASR Leveraging Biasing Scoring), a robust framework designed to enhance speech-augmented language models (SLMs) in complex multi-entity scenarios. Considering the inherent context-window limitations of SLMs, identifying relevant target entities from a large-scale biasing list is crucial for effective recognition. To this end, COALA maps SLM latent representations into a specialized discriminati"},"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":"2607.08117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T05:26:22Z","cross_cats_sorted":[],"title_canon_sha256":"7410eecdca0de37d528d676b2a90785bffefcfe8d20b5c9fb5a0581dd464d54d","abstract_canon_sha256":"5b0a026efefec196399b01aa896a0841e5b40178bab4cf02b2171b9ab38edc6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:27.142976Z","signature_b64":"SQAsld2Ju7Ds9K8jTPq3an7rnPsLXTjzwHC/1dXs2gnzYZYUPItRLtta6vySx5ZD01gUp1r5yGqQ/z91SPrzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"002572954c0e62a1ae65a8be8eed4a08d22081f34efd37adf1d05cb199f1cae3","last_reissued_at":"2026-07-10T01:19:27.142479Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:27.142479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Berlin Chen, Bi-Cheng Yan, Jhih-Rong Guo, Tien-Hong Lo","submitted_at":"2026-07-09T05:26:22Z","abstract_excerpt":"Contextual biasing seeks to integrate external knowledge into automatic speech recognition (ASR) systems to accurately recognize domain-specific entities. In this paper, we propose COALA (Contextualized ASR Leveraging Biasing Scoring), a robust framework designed to enhance speech-augmented language models (SLMs) in complex multi-entity scenarios. Considering the inherent context-window limitations of SLMs, identifying relevant target entities from a large-scale biasing list is crucial for effective recognition. To this end, COALA maps SLM latent representations into a specialized discriminati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08117","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/2607.08117/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":"2607.08117","created_at":"2026-07-10T01:19:27.142539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08117v1","created_at":"2026-07-10T01:19:27.142539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08117","created_at":"2026-07-10T01:19:27.142539+00:00"},{"alias_kind":"pith_short_12","alias_value":"AASXFFKMBZRK","created_at":"2026-07-10T01:19:27.142539+00:00"},{"alias_kind":"pith_short_16","alias_value":"AASXFFKMBZRKDLTF","created_at":"2026-07-10T01:19:27.142539+00:00"},{"alias_kind":"pith_short_8","alias_value":"AASXFFKM","created_at":"2026-07-10T01:19:27.142539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08117","citing_title":"COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AASXFFKMBZRKDLTFVC7I53KKBD","json":"https://pith.science/pith/AASXFFKMBZRKDLTFVC7I53KKBD.json","graph_json":"https://pith.science/api/pith-number/AASXFFKMBZRKDLTFVC7I53KKBD/graph.json","events_json":"https://pith.science/api/pith-number/AASXFFKMBZRKDLTFVC7I53KKBD/events.json","paper":"https://pith.science/paper/AASXFFKM"},"agent_actions":{"view_html":"https://pith.science/pith/AASXFFKMBZRKDLTFVC7I53KKBD","download_json":"https://pith.science/pith/AASXFFKMBZRKDLTFVC7I53KKBD.json","view_paper":"https://pith.science/paper/AASXFFKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08117&json=true","fetch_graph":"https://pith.science/api/pith-number/AASXFFKMBZRKDLTFVC7I53KKBD/graph.json","fetch_events":"https://pith.science/api/pith-number/AASXFFKMBZRKDLTFVC7I53KKBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AASXFFKMBZRKDLTFVC7I53KKBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AASXFFKMBZRKDLTFVC7I53KKBD/action/storage_attestation","attest_author":"https://pith.science/pith/AASXFFKMBZRKDLTFVC7I53KKBD/action/author_attestation","sign_citation":"https://pith.science/pith/AASXFFKMBZRKDLTFVC7I53KKBD/action/citation_signature","submit_replication":"https://pith.science/pith/AASXFFKMBZRKDLTFVC7I53KKBD/action/replication_record"}},"created_at":"2026-07-10T01:19:27.142539+00:00","updated_at":"2026-07-10T01:19:27.142539+00:00"}