{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:N5E3NQBCNBGJEX74MJPM5ZRMN6","short_pith_number":"pith:N5E3NQBC","schema_version":"1.0","canonical_sha256":"6f49b6c022684c925ffc625ecee62c6f923839f41d924071d7f8baff4544955e","source":{"kind":"arxiv","id":"2005.13962","version":1},"attestation_state":"computed","paper":{"title":"A Corpus for Large-Scale Phonetic Typology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan W Black, Eleanor Chodroff, Elizabeth Salesky, Jason Eisner, Matthew Wiesner, Ryan Cotterell, Tiago Pimentel","submitted_at":"2020-05-28T13:03:51Z","abstract_excerpt":"A major hurdle in data-driven research on typology is having sufficient data in many languages to draw meaningful conclusions. We present VoxClamantis v1.0, the first large-scale corpus for phonetic typology, with aligned segments and estimated phoneme-level labels in 690 readings spanning 635 languages, along with acoustic-phonetic measures of vowels and sibilants. Access to such data can greatly facilitate investigation of phonetic typology at a large scale and across many languages. However, it is non-trivial and computationally intensive to obtain such alignments for hundreds of languages,"},"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":"2005.13962","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-28T13:03:51Z","cross_cats_sorted":[],"title_canon_sha256":"6d758e16a833466efcd43c6b25ff1cd3075de59affd34b6f79f21509e5d00813","abstract_canon_sha256":"156c38c814a6c1ea992c7a5e2f847631d7fc831c471c3ca1540d8937ef6b0226"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:27.054264Z","signature_b64":"p7izqB3isMeXtipgvlRkywSUUUCJzbUyWRmPZffn0oWx8RhdL2In4Rv7mriOFbO6bkXnUnNB38IU2ekix/7kCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f49b6c022684c925ffc625ecee62c6f923839f41d924071d7f8baff4544955e","last_reissued_at":"2026-07-05T01:06:27.053779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:27.053779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Corpus for Large-Scale Phonetic Typology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan W Black, Eleanor Chodroff, Elizabeth Salesky, Jason Eisner, Matthew Wiesner, Ryan Cotterell, Tiago Pimentel","submitted_at":"2020-05-28T13:03:51Z","abstract_excerpt":"A major hurdle in data-driven research on typology is having sufficient data in many languages to draw meaningful conclusions. We present VoxClamantis v1.0, the first large-scale corpus for phonetic typology, with aligned segments and estimated phoneme-level labels in 690 readings spanning 635 languages, along with acoustic-phonetic measures of vowels and sibilants. Access to such data can greatly facilitate investigation of phonetic typology at a large scale and across many languages. However, it is non-trivial and computationally intensive to obtain such alignments for hundreds of languages,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.13962","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/2005.13962/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":"2005.13962","created_at":"2026-07-05T01:06:27.053835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.13962v1","created_at":"2026-07-05T01:06:27.053835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.13962","created_at":"2026-07-05T01:06:27.053835+00:00"},{"alias_kind":"pith_short_12","alias_value":"N5E3NQBCNBGJ","created_at":"2026-07-05T01:06:27.053835+00:00"},{"alias_kind":"pith_short_16","alias_value":"N5E3NQBCNBGJEX74","created_at":"2026-07-05T01:06:27.053835+00:00"},{"alias_kind":"pith_short_8","alias_value":"N5E3NQBC","created_at":"2026-07-05T01:06:27.053835+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/N5E3NQBCNBGJEX74MJPM5ZRMN6","json":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6.json","graph_json":"https://pith.science/api/pith-number/N5E3NQBCNBGJEX74MJPM5ZRMN6/graph.json","events_json":"https://pith.science/api/pith-number/N5E3NQBCNBGJEX74MJPM5ZRMN6/events.json","paper":"https://pith.science/paper/N5E3NQBC"},"agent_actions":{"view_html":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6","download_json":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6.json","view_paper":"https://pith.science/paper/N5E3NQBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.13962&json=true","fetch_graph":"https://pith.science/api/pith-number/N5E3NQBCNBGJEX74MJPM5ZRMN6/graph.json","fetch_events":"https://pith.science/api/pith-number/N5E3NQBCNBGJEX74MJPM5ZRMN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6/action/storage_attestation","attest_author":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6/action/author_attestation","sign_citation":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6/action/citation_signature","submit_replication":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6/action/replication_record"}},"created_at":"2026-07-05T01:06:27.053835+00:00","updated_at":"2026-07-05T01:06:27.053835+00:00"}