{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CRZ3TTR55LHV7U7JBM4G4ONSWC","short_pith_number":"pith:CRZ3TTR5","schema_version":"1.0","canonical_sha256":"1473b9ce3deacf5fd3e90b386e39b2b08b37c7d7036c286db071373f3c4916db","source":{"kind":"arxiv","id":"2605.17860","version":1},"attestation_state":"computed","paper":{"title":"PAREDA: A Multi-Accent Speech Dataset of Natural Language Processing Research Discussions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Joshi, Dipankar Srirag, Sicheng Jin","submitted_at":"2026-05-18T05:10:26Z","abstract_excerpt":"While modern Automatic Speech Recognition (ASR) systems achieve high accuracy on benchmark corpora, their performance often degrades when there is real-world variability. This work focuses on variability arising due to accented, spontaneous, and domain-specific speech. In particular, we introduce PAper REading DAtaset (PAREDA), a first-of-its-kind multi-accent speech dataset consisting of discussions on academic Natural Language Processing (NLP) papers between speakers with Australian, Indian-English, and Chinese English accents. Each session elicits a spontaneous monologue (a summary of a pap"},"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":"2605.17860","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T05:10:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f08ec4bac83423d469fd17024c542c49d220b71405340389b93d04a299aa52b8","abstract_canon_sha256":"b3e4a984bdf43150f30a7a7e987e6b7f822f4bb0776ab627605302e3aca6b48c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:02.311638Z","signature_b64":"Luce0hzGZYnSBsdzHsfaaalH4gVbz4jOkrOdsO8oC/4hpth+1sr9B7aPrmM+k24n1lsx/xMCiFKVRwDeLjvTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1473b9ce3deacf5fd3e90b386e39b2b08b37c7d7036c286db071373f3c4916db","last_reissued_at":"2026-05-20T00:05:02.310739Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:02.310739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAREDA: A Multi-Accent Speech Dataset of Natural Language Processing Research Discussions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Joshi, Dipankar Srirag, Sicheng Jin","submitted_at":"2026-05-18T05:10:26Z","abstract_excerpt":"While modern Automatic Speech Recognition (ASR) systems achieve high accuracy on benchmark corpora, their performance often degrades when there is real-world variability. This work focuses on variability arising due to accented, spontaneous, and domain-specific speech. In particular, we introduce PAper REading DAtaset (PAREDA), a first-of-its-kind multi-accent speech dataset consisting of discussions on academic Natural Language Processing (NLP) papers between speakers with Australian, Indian-English, and Chinese English accents. Each session elicits a spontaneous monologue (a summary of a pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17860","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/2605.17860/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":"2605.17860","created_at":"2026-05-20T00:05:02.310893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17860v1","created_at":"2026-05-20T00:05:02.310893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17860","created_at":"2026-05-20T00:05:02.310893+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRZ3TTR55LHV","created_at":"2026-05-20T00:05:02.310893+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRZ3TTR55LHV7U7J","created_at":"2026-05-20T00:05:02.310893+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRZ3TTR5","created_at":"2026-05-20T00:05:02.310893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CRZ3TTR55LHV7U7JBM4G4ONSWC","json":"https://pith.science/pith/CRZ3TTR55LHV7U7JBM4G4ONSWC.json","graph_json":"https://pith.science/api/pith-number/CRZ3TTR55LHV7U7JBM4G4ONSWC/graph.json","events_json":"https://pith.science/api/pith-number/CRZ3TTR55LHV7U7JBM4G4ONSWC/events.json","paper":"https://pith.science/paper/CRZ3TTR5"},"agent_actions":{"view_html":"https://pith.science/pith/CRZ3TTR55LHV7U7JBM4G4ONSWC","download_json":"https://pith.science/pith/CRZ3TTR55LHV7U7JBM4G4ONSWC.json","view_paper":"https://pith.science/paper/CRZ3TTR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17860&json=true","fetch_graph":"https://pith.science/api/pith-number/CRZ3TTR55LHV7U7JBM4G4ONSWC/graph.json","fetch_events":"https://pith.science/api/pith-number/CRZ3TTR55LHV7U7JBM4G4ONSWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRZ3TTR55LHV7U7JBM4G4ONSWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRZ3TTR55LHV7U7JBM4G4ONSWC/action/storage_attestation","attest_author":"https://pith.science/pith/CRZ3TTR55LHV7U7JBM4G4ONSWC/action/author_attestation","sign_citation":"https://pith.science/pith/CRZ3TTR55LHV7U7JBM4G4ONSWC/action/citation_signature","submit_replication":"https://pith.science/pith/CRZ3TTR55LHV7U7JBM4G4ONSWC/action/replication_record"}},"created_at":"2026-05-20T00:05:02.310893+00:00","updated_at":"2026-05-20T00:05:02.310893+00:00"}