{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7R6K5ZP4DGW466C74LCAXH2X77","short_pith_number":"pith:7R6K5ZP4","schema_version":"1.0","canonical_sha256":"fc7caee5fc19adcf785fe2c40b9f57ffe9e2b2cdecd40b7146a1e60d42ec1109","source":{"kind":"arxiv","id":"2606.29534","version":1},"attestation_state":"computed","paper":{"title":"Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Desh Raj, Jagadeesh Balam, Nikolay Karpov, Nithin Rao Koluguri, Piotr Zelasko, Sasha Meister","submitted_at":"2026-06-28T17:57:41Z","abstract_excerpt":"Popular ASR test sets adopt inconsistent conventions for numbers, disfluencies, entities, and casing, while standard normalizers erase the format distinctions users care about. Current benchmarks therefore cannot measure whether a model follows user preferences for output style. We introduce PreferenceASR, a test set evaluating ASR systems on their ability to follow natural-language preference instructions across four categories: normalization, entities, disfluencies, and case. Built from seven open-source corpora via a two-stage LLM-assisted pipeline with human verification, it is evaluated 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":"2606.29534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T17:57:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1bae43c121ef641e867ca52fb761acabe8ce1e0a51677cc1fbb996939fffb939","abstract_canon_sha256":"a7cb9f102cdcbe52cdff5c86875601d81ef8b36fa7b76fcc28db6f3f6ae93647"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:10.742905Z","signature_b64":"9+g5FlLqc0N4MC1miRHqj4NdhB7tyvDFhaeXjBD9f8Pl1h7RK+TT4VMwlpOZe1DsDk+9mTdOXbOFettU5h9pAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc7caee5fc19adcf785fe2c40b9f57ffe9e2b2cdecd40b7146a1e60d42ec1109","last_reissued_at":"2026-06-30T01:18:10.742158Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:10.742158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Desh Raj, Jagadeesh Balam, Nikolay Karpov, Nithin Rao Koluguri, Piotr Zelasko, Sasha Meister","submitted_at":"2026-06-28T17:57:41Z","abstract_excerpt":"Popular ASR test sets adopt inconsistent conventions for numbers, disfluencies, entities, and casing, while standard normalizers erase the format distinctions users care about. Current benchmarks therefore cannot measure whether a model follows user preferences for output style. We introduce PreferenceASR, a test set evaluating ASR systems on their ability to follow natural-language preference instructions across four categories: normalization, entities, disfluencies, and case. Built from seven open-source corpora via a two-stage LLM-assisted pipeline with human verification, it is evaluated w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29534","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/2606.29534/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":"2606.29534","created_at":"2026-06-30T01:18:10.742284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29534v1","created_at":"2026-06-30T01:18:10.742284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29534","created_at":"2026-06-30T01:18:10.742284+00:00"},{"alias_kind":"pith_short_12","alias_value":"7R6K5ZP4DGW4","created_at":"2026-06-30T01:18:10.742284+00:00"},{"alias_kind":"pith_short_16","alias_value":"7R6K5ZP4DGW466C7","created_at":"2026-06-30T01:18:10.742284+00:00"},{"alias_kind":"pith_short_8","alias_value":"7R6K5ZP4","created_at":"2026-06-30T01:18:10.742284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.29534","citing_title":"Preference-ASR: A Preference-Aware Test Set for Benchmarking ASR in the Era of Speech LLMs","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7R6K5ZP4DGW466C74LCAXH2X77","json":"https://pith.science/pith/7R6K5ZP4DGW466C74LCAXH2X77.json","graph_json":"https://pith.science/api/pith-number/7R6K5ZP4DGW466C74LCAXH2X77/graph.json","events_json":"https://pith.science/api/pith-number/7R6K5ZP4DGW466C74LCAXH2X77/events.json","paper":"https://pith.science/paper/7R6K5ZP4"},"agent_actions":{"view_html":"https://pith.science/pith/7R6K5ZP4DGW466C74LCAXH2X77","download_json":"https://pith.science/pith/7R6K5ZP4DGW466C74LCAXH2X77.json","view_paper":"https://pith.science/paper/7R6K5ZP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29534&json=true","fetch_graph":"https://pith.science/api/pith-number/7R6K5ZP4DGW466C74LCAXH2X77/graph.json","fetch_events":"https://pith.science/api/pith-number/7R6K5ZP4DGW466C74LCAXH2X77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7R6K5ZP4DGW466C74LCAXH2X77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7R6K5ZP4DGW466C74LCAXH2X77/action/storage_attestation","attest_author":"https://pith.science/pith/7R6K5ZP4DGW466C74LCAXH2X77/action/author_attestation","sign_citation":"https://pith.science/pith/7R6K5ZP4DGW466C74LCAXH2X77/action/citation_signature","submit_replication":"https://pith.science/pith/7R6K5ZP4DGW466C74LCAXH2X77/action/replication_record"}},"created_at":"2026-06-30T01:18:10.742284+00:00","updated_at":"2026-06-30T01:18:10.742284+00:00"}