{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BJRGZ7FEYD65YKUN6WZG6IC7EY","short_pith_number":"pith:BJRGZ7FE","schema_version":"1.0","canonical_sha256":"0a626cfca4c0fddc2a8df5b26f205f2626d92c789d14fc37fbe862ef29d3fec5","source":{"kind":"arxiv","id":"2505.23170","version":1},"attestation_state":"computed","paper":{"title":"ZIPA: A family of efficient models for multilingual phone recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"David R. Mortensen, Eleanor Chodroff, Farhan Samir, Jian Zhu","submitted_at":"2025-05-29T07:08:23Z","abstract_excerpt":"We present ZIPA, a family of efficient speech models that advances the state-of-the-art performance of crosslinguistic phone recognition. We first curated IPAPack++, a large-scale multilingual speech corpus with 17,132 hours of normalized phone transcriptions and a novel evaluation set capturing unseen languages and sociophonetic variation. With the large-scale training data, ZIPA, including transducer (ZIPA-T) and CTC-based (ZIPA-CR) variants, leverage the efficient Zipformer backbones and outperform existing phone recognition systems with much fewer parameters. Further scaling via noisy stud"},"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":"2505.23170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T07:08:23Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"f16b3613a3bacfaadc8a7d23235898580353b19cef6cd2594952b0540dfd3743","abstract_canon_sha256":"c44639431b4796101648ea14f1bc7bad2181a187ca0afbcd996e9f53bf1c7bd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:11.997416Z","signature_b64":"iUvNuQg9/o76skORQv0HYqi+9GiTzsGHcvo3rUAaV7dkFvffQ3CY4xSwbk3gp/KZcwt2g+IASa5PYGWFvbjaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a626cfca4c0fddc2a8df5b26f205f2626d92c789d14fc37fbe862ef29d3fec5","last_reissued_at":"2026-07-05T11:12:11.996946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:11.996946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZIPA: A family of efficient models for multilingual phone recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"David R. Mortensen, Eleanor Chodroff, Farhan Samir, Jian Zhu","submitted_at":"2025-05-29T07:08:23Z","abstract_excerpt":"We present ZIPA, a family of efficient speech models that advances the state-of-the-art performance of crosslinguistic phone recognition. We first curated IPAPack++, a large-scale multilingual speech corpus with 17,132 hours of normalized phone transcriptions and a novel evaluation set capturing unseen languages and sociophonetic variation. With the large-scale training data, ZIPA, including transducer (ZIPA-T) and CTC-based (ZIPA-CR) variants, leverage the efficient Zipformer backbones and outperform existing phone recognition systems with much fewer parameters. Further scaling via noisy stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23170","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/2505.23170/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":"2505.23170","created_at":"2026-07-05T11:12:11.996998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23170v1","created_at":"2026-07-05T11:12:11.996998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23170","created_at":"2026-07-05T11:12:11.996998+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJRGZ7FEYD65","created_at":"2026-07-05T11:12:11.996998+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJRGZ7FEYD65YKUN","created_at":"2026-07-05T11:12:11.996998+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJRGZ7FE","created_at":"2026-07-05T11:12:11.996998+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/BJRGZ7FEYD65YKUN6WZG6IC7EY","json":"https://pith.science/pith/BJRGZ7FEYD65YKUN6WZG6IC7EY.json","graph_json":"https://pith.science/api/pith-number/BJRGZ7FEYD65YKUN6WZG6IC7EY/graph.json","events_json":"https://pith.science/api/pith-number/BJRGZ7FEYD65YKUN6WZG6IC7EY/events.json","paper":"https://pith.science/paper/BJRGZ7FE"},"agent_actions":{"view_html":"https://pith.science/pith/BJRGZ7FEYD65YKUN6WZG6IC7EY","download_json":"https://pith.science/pith/BJRGZ7FEYD65YKUN6WZG6IC7EY.json","view_paper":"https://pith.science/paper/BJRGZ7FE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23170&json=true","fetch_graph":"https://pith.science/api/pith-number/BJRGZ7FEYD65YKUN6WZG6IC7EY/graph.json","fetch_events":"https://pith.science/api/pith-number/BJRGZ7FEYD65YKUN6WZG6IC7EY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJRGZ7FEYD65YKUN6WZG6IC7EY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJRGZ7FEYD65YKUN6WZG6IC7EY/action/storage_attestation","attest_author":"https://pith.science/pith/BJRGZ7FEYD65YKUN6WZG6IC7EY/action/author_attestation","sign_citation":"https://pith.science/pith/BJRGZ7FEYD65YKUN6WZG6IC7EY/action/citation_signature","submit_replication":"https://pith.science/pith/BJRGZ7FEYD65YKUN6WZG6IC7EY/action/replication_record"}},"created_at":"2026-07-05T11:12:11.996998+00:00","updated_at":"2026-07-05T11:12:11.996998+00:00"}