{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KJ3PBVED7RXPZZIVD2V7HMROZ6","short_pith_number":"pith:KJ3PBVED","schema_version":"1.0","canonical_sha256":"5276f0d483fc6efce5151eabf3b22ecfa88e2ac22532d0f0ee8cc60dde2b4cc1","source":{"kind":"arxiv","id":"2507.16456","version":1},"attestation_state":"computed","paper":{"title":"An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Nihar Desai, Prasanta Kumar Ghosh, Sahapthan K, Sujith Pulikodan, Visruth Sanka","submitted_at":"2025-07-22T10:59:21Z","abstract_excerpt":"Automatic Speech Recognition (ASR) plays a crucial role in human-machine interaction and serves as an interface for a wide range of applications. Traditionally, ASR performance has been evaluated using Word Error Rate (WER), a metric that quantifies the number of insertions, deletions, and substitutions in the generated transcriptions. However, with the increasing adoption of large and powerful Large Language Models (LLMs) as the core processing component in various applications, the significance of different types of ASR errors in downstream tasks warrants further exploration. In this work, w"},"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":"2507.16456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-22T10:59:21Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"66c106aeb9e54a83ff5713257f7d7dd8e3405d17af3b98b1b1250a22623f3bc4","abstract_canon_sha256":"af1ada705366689de36a2db94634c93e8deb8f8d0020c341c84bd06bf795e0b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:09.774502Z","signature_b64":"tLRGVHEeHqb6KTncvjz90+At6dYeW/5XXI7YqfUplokHtoQoVUuyOa9+3HHFP/5byaSL0B5W2wd09vkvLmCsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5276f0d483fc6efce5151eabf3b22ecfa88e2ac22532d0f0ee8cc60dde2b4cc1","last_reissued_at":"2026-07-05T11:41:09.774096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:09.774096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An approach to measuring the performance of Automatic Speech Recognition (ASR) models in the context of Large Language Model (LLM) powered applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Nihar Desai, Prasanta Kumar Ghosh, Sahapthan K, Sujith Pulikodan, Visruth Sanka","submitted_at":"2025-07-22T10:59:21Z","abstract_excerpt":"Automatic Speech Recognition (ASR) plays a crucial role in human-machine interaction and serves as an interface for a wide range of applications. Traditionally, ASR performance has been evaluated using Word Error Rate (WER), a metric that quantifies the number of insertions, deletions, and substitutions in the generated transcriptions. However, with the increasing adoption of large and powerful Large Language Models (LLMs) as the core processing component in various applications, the significance of different types of ASR errors in downstream tasks warrants further exploration. In this work, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16456","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/2507.16456/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":"2507.16456","created_at":"2026-07-05T11:41:09.774153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16456v1","created_at":"2026-07-05T11:41:09.774153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16456","created_at":"2026-07-05T11:41:09.774153+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJ3PBVED7RXP","created_at":"2026-07-05T11:41:09.774153+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJ3PBVED7RXPZZIV","created_at":"2026-07-05T11:41:09.774153+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJ3PBVED","created_at":"2026-07-05T11:41:09.774153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23060","citing_title":"From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29430","citing_title":"Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJ3PBVED7RXPZZIVD2V7HMROZ6","json":"https://pith.science/pith/KJ3PBVED7RXPZZIVD2V7HMROZ6.json","graph_json":"https://pith.science/api/pith-number/KJ3PBVED7RXPZZIVD2V7HMROZ6/graph.json","events_json":"https://pith.science/api/pith-number/KJ3PBVED7RXPZZIVD2V7HMROZ6/events.json","paper":"https://pith.science/paper/KJ3PBVED"},"agent_actions":{"view_html":"https://pith.science/pith/KJ3PBVED7RXPZZIVD2V7HMROZ6","download_json":"https://pith.science/pith/KJ3PBVED7RXPZZIVD2V7HMROZ6.json","view_paper":"https://pith.science/paper/KJ3PBVED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16456&json=true","fetch_graph":"https://pith.science/api/pith-number/KJ3PBVED7RXPZZIVD2V7HMROZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/KJ3PBVED7RXPZZIVD2V7HMROZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJ3PBVED7RXPZZIVD2V7HMROZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJ3PBVED7RXPZZIVD2V7HMROZ6/action/storage_attestation","attest_author":"https://pith.science/pith/KJ3PBVED7RXPZZIVD2V7HMROZ6/action/author_attestation","sign_citation":"https://pith.science/pith/KJ3PBVED7RXPZZIVD2V7HMROZ6/action/citation_signature","submit_replication":"https://pith.science/pith/KJ3PBVED7RXPZZIVD2V7HMROZ6/action/replication_record"}},"created_at":"2026-07-05T11:41:09.774153+00:00","updated_at":"2026-07-05T11:41:09.774153+00:00"}