{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:N5E3NQBCNBGJEX74MJPM5ZRMN6","short_pith_number":"pith:N5E3NQBC","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"},"canonical_sha256":"6f49b6c022684c925ffc625ecee62c6f923839f41d924071d7f8baff4544955e","source":{"kind":"arxiv","id":"2005.13962","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.13962","created_at":"2026-07-05T01:06:27Z"},{"alias_kind":"arxiv_version","alias_value":"2005.13962v1","created_at":"2026-07-05T01:06:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.13962","created_at":"2026-07-05T01:06:27Z"},{"alias_kind":"pith_short_12","alias_value":"N5E3NQBCNBGJ","created_at":"2026-07-05T01:06:27Z"},{"alias_kind":"pith_short_16","alias_value":"N5E3NQBCNBGJEX74","created_at":"2026-07-05T01:06:27Z"},{"alias_kind":"pith_short_8","alias_value":"N5E3NQBC","created_at":"2026-07-05T01:06:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:N5E3NQBCNBGJEX74MJPM5ZRMN6","target":"record","payload":{"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"},"canonical_sha256":"6f49b6c022684c925ffc625ecee62c6f923839f41d924071d7f8baff4544955e","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"},"source_kind":"arxiv","source_id":"2005.13962","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:06:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cbrbkbXbRDQbRN1GH5dUKeLaU/3NVgSL0s3XpXYCp0VfRl0e/+PEZsYyvocZay2mUZbxPqWPKD9JRE0z0HKuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:33:11.246864Z"},"content_sha256":"22ddffd7e777624362cd049207b3050eb41419d11b3a0e9bda63b678a3ed748d","schema_version":"1.0","event_id":"sha256:22ddffd7e777624362cd049207b3050eb41419d11b3a0e9bda63b678a3ed748d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:N5E3NQBCNBGJEX74MJPM5ZRMN6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:06:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vwb0nDPeYW7CxL4tVUL/rbwVblRJZjO/E7tuIfXCBOkRHp/6EukAFtUE66vuDnZyJD1TF7kigKdO0GWTbhD1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:33:11.247739Z"},"content_sha256":"b1187296c345a064a5da298b6b74c5d068c63bed975813ea91f18966612bf4e4","schema_version":"1.0","event_id":"sha256:b1187296c345a064a5da298b6b74c5d068c63bed975813ea91f18966612bf4e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6/bundle.json","state_url":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T18:33:11Z","links":{"resolver":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6","bundle":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6/bundle.json","state":"https://pith.science/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N5E3NQBCNBGJEX74MJPM5ZRMN6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:N5E3NQBCNBGJEX74MJPM5ZRMN6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"156c38c814a6c1ea992c7a5e2f847631d7fc831c471c3ca1540d8937ef6b0226","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-28T13:03:51Z","title_canon_sha256":"6d758e16a833466efcd43c6b25ff1cd3075de59affd34b6f79f21509e5d00813"},"schema_version":"1.0","source":{"id":"2005.13962","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.13962","created_at":"2026-07-05T01:06:27Z"},{"alias_kind":"arxiv_version","alias_value":"2005.13962v1","created_at":"2026-07-05T01:06:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.13962","created_at":"2026-07-05T01:06:27Z"},{"alias_kind":"pith_short_12","alias_value":"N5E3NQBCNBGJ","created_at":"2026-07-05T01:06:27Z"},{"alias_kind":"pith_short_16","alias_value":"N5E3NQBCNBGJEX74","created_at":"2026-07-05T01:06:27Z"},{"alias_kind":"pith_short_8","alias_value":"N5E3NQBC","created_at":"2026-07-05T01:06:27Z"}],"graph_snapshots":[{"event_id":"sha256:b1187296c345a064a5da298b6b74c5d068c63bed975813ea91f18966612bf4e4","target":"graph","created_at":"2026-07-05T01:06:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2005.13962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Alan W Black, Eleanor Chodroff, Elizabeth Salesky, Jason Eisner, Matthew Wiesner, Ryan Cotterell, Tiago Pimentel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-28T13:03:51Z","title":"A Corpus for Large-Scale Phonetic Typology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.13962","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:22ddffd7e777624362cd049207b3050eb41419d11b3a0e9bda63b678a3ed748d","target":"record","created_at":"2026-07-05T01:06:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"156c38c814a6c1ea992c7a5e2f847631d7fc831c471c3ca1540d8937ef6b0226","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-28T13:03:51Z","title_canon_sha256":"6d758e16a833466efcd43c6b25ff1cd3075de59affd34b6f79f21509e5d00813"},"schema_version":"1.0","source":{"id":"2005.13962","kind":"arxiv","version":1}},"canonical_sha256":"6f49b6c022684c925ffc625ecee62c6f923839f41d924071d7f8baff4544955e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f49b6c022684c925ffc625ecee62c6f923839f41d924071d7f8baff4544955e","first_computed_at":"2026-07-05T01:06:27.053779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:06:27.053779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p7izqB3isMeXtipgvlRkywSUUUCJzbUyWRmPZffn0oWx8RhdL2In4Rv7mriOFbO6bkXnUnNB38IU2ekix/7kCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:06:27.054264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.13962","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22ddffd7e777624362cd049207b3050eb41419d11b3a0e9bda63b678a3ed748d","sha256:b1187296c345a064a5da298b6b74c5d068c63bed975813ea91f18966612bf4e4"],"state_sha256":"ed43ec36c0fa80da4e00194ecf494b9e5018ede36908d00c533b9e39bf689edf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L78sbucwtccuy3oyzF3X/JS6XvHzKI4J8efpij/kl91+g0fJxBXIIqP6p6KKh0O1eHPR5iVXeu12XTnXHD9mAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:33:11.252716Z","bundle_sha256":"75dd95675b2b0fee06d770d404592a83135063509183cd2bff0ef1fd2d7bbd7c"}}