{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GIZ5PMKY6QEMKGN6DI4KRHAGDI","short_pith_number":"pith:GIZ5PMKY","schema_version":"1.0","canonical_sha256":"3233d7b158f408c519be1a38a89c061a11986c88427cc6d38fa5f9b10494e0b1","source":{"kind":"arxiv","id":"2509.04357","version":1},"attestation_state":"computed","paper":{"title":"PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Jiajun He, Koichi Miyazaki, Naoki Sawada, Tomoki Toda","submitted_at":"2025-09-04T16:18:34Z","abstract_excerpt":"Automatic speech recognition (ASR) systems struggle with domain-specific named entities, especially homophones. Contextual ASR improves recognition but often fails to capture fine-grained phoneme variations due to limited entity diversity. Moreover, prior methods treat entities as independent tokens, leading to incomplete multi-token biasing. To address these issues, we propose Phoneme-Augmented Robust Contextual ASR via COntrastive entity disambiguation (PARCO), which integrates phoneme-aware encoding, contrastive entity disambiguation, entity-level supervision, and hierarchical entity filter"},"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":"2509.04357","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-04T16:18:34Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"title_canon_sha256":"295fcfd89bf42609e2a48a1469d49f40169128d579075e1c08d504b991ecbc86","abstract_canon_sha256":"a39443e1ece618b87c2223411e88bdf2799fb5cd284d5b1111911bd5732d8f32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:57.960415Z","signature_b64":"wnD3T1BpYPg5M/a+lozoI509e9stGYwwvk3YTwi6Gw9ewfTYrukae434xay206PYX6ImyieYQd6ACbMl1vERCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3233d7b158f408c519be1a38a89c061a11986c88427cc6d38fa5f9b10494e0b1","last_reissued_at":"2026-07-05T12:04:57.959849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:57.959849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Jiajun He, Koichi Miyazaki, Naoki Sawada, Tomoki Toda","submitted_at":"2025-09-04T16:18:34Z","abstract_excerpt":"Automatic speech recognition (ASR) systems struggle with domain-specific named entities, especially homophones. Contextual ASR improves recognition but often fails to capture fine-grained phoneme variations due to limited entity diversity. Moreover, prior methods treat entities as independent tokens, leading to incomplete multi-token biasing. To address these issues, we propose Phoneme-Augmented Robust Contextual ASR via COntrastive entity disambiguation (PARCO), which integrates phoneme-aware encoding, contrastive entity disambiguation, entity-level supervision, and hierarchical entity filter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04357","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/2509.04357/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":"2509.04357","created_at":"2026-07-05T12:04:57.959911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04357v1","created_at":"2026-07-05T12:04:57.959911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04357","created_at":"2026-07-05T12:04:57.959911+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIZ5PMKY6QEM","created_at":"2026-07-05T12:04:57.959911+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIZ5PMKY6QEMKGN6","created_at":"2026-07-05T12:04:57.959911+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIZ5PMKY","created_at":"2026-07-05T12:04:57.959911+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12398","citing_title":"Contextual Biasing for ASR in Speech LLM with Common Word Cues and Bias Word Position Prediction","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GIZ5PMKY6QEMKGN6DI4KRHAGDI","json":"https://pith.science/pith/GIZ5PMKY6QEMKGN6DI4KRHAGDI.json","graph_json":"https://pith.science/api/pith-number/GIZ5PMKY6QEMKGN6DI4KRHAGDI/graph.json","events_json":"https://pith.science/api/pith-number/GIZ5PMKY6QEMKGN6DI4KRHAGDI/events.json","paper":"https://pith.science/paper/GIZ5PMKY"},"agent_actions":{"view_html":"https://pith.science/pith/GIZ5PMKY6QEMKGN6DI4KRHAGDI","download_json":"https://pith.science/pith/GIZ5PMKY6QEMKGN6DI4KRHAGDI.json","view_paper":"https://pith.science/paper/GIZ5PMKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04357&json=true","fetch_graph":"https://pith.science/api/pith-number/GIZ5PMKY6QEMKGN6DI4KRHAGDI/graph.json","fetch_events":"https://pith.science/api/pith-number/GIZ5PMKY6QEMKGN6DI4KRHAGDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIZ5PMKY6QEMKGN6DI4KRHAGDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIZ5PMKY6QEMKGN6DI4KRHAGDI/action/storage_attestation","attest_author":"https://pith.science/pith/GIZ5PMKY6QEMKGN6DI4KRHAGDI/action/author_attestation","sign_citation":"https://pith.science/pith/GIZ5PMKY6QEMKGN6DI4KRHAGDI/action/citation_signature","submit_replication":"https://pith.science/pith/GIZ5PMKY6QEMKGN6DI4KRHAGDI/action/replication_record"}},"created_at":"2026-07-05T12:04:57.959911+00:00","updated_at":"2026-07-05T12:04:57.959911+00:00"}