{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WTQUPQTOTYX3PEUXQRDIYB7KM7","short_pith_number":"pith:WTQUPQTO","canonical_record":{"source":{"id":"2410.04292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T21:41:49Z","cross_cats_sorted":[],"title_canon_sha256":"46e66df16d7ec68f0aeb580d610ab9ede014cc8537d68d34a8a87e2e5fc5a9e9","abstract_canon_sha256":"92372e0c85df2260dccf72a8edf643aec3da0a8a89cc60e1ff7db969bcfc0656"},"schema_version":"1.0"},"canonical_sha256":"b4e147c26e9e2fb7929784468c07ea67ef05abb2129e74d690c8027e59b3d2cd","source":{"kind":"arxiv","id":"2410.04292","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04292","created_at":"2026-07-05T09:16:32Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04292v1","created_at":"2026-07-05T09:16:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04292","created_at":"2026-07-05T09:16:32Z"},{"alias_kind":"pith_short_12","alias_value":"WTQUPQTOTYX3","created_at":"2026-07-05T09:16:32Z"},{"alias_kind":"pith_short_16","alias_value":"WTQUPQTOTYX3PEUX","created_at":"2026-07-05T09:16:32Z"},{"alias_kind":"pith_short_8","alias_value":"WTQUPQTO","created_at":"2026-07-05T09:16:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WTQUPQTOTYX3PEUXQRDIYB7KM7","target":"record","payload":{"canonical_record":{"source":{"id":"2410.04292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T21:41:49Z","cross_cats_sorted":[],"title_canon_sha256":"46e66df16d7ec68f0aeb580d610ab9ede014cc8537d68d34a8a87e2e5fc5a9e9","abstract_canon_sha256":"92372e0c85df2260dccf72a8edf643aec3da0a8a89cc60e1ff7db969bcfc0656"},"schema_version":"1.0"},"canonical_sha256":"b4e147c26e9e2fb7929784468c07ea67ef05abb2129e74d690c8027e59b3d2cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:32.487424Z","signature_b64":"S//pqkMBhI5yt7Va0ymK1PBWwKmavXewkJQnmJDK3gx5Wu6pw0SpHxmEk0KUH2dDiT5t+iC3m3+9bgmZEx4xDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4e147c26e9e2fb7929784468c07ea67ef05abb2129e74d690c8027e59b3d2cd","last_reissued_at":"2026-07-05T09:16:32.487061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:32.487061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.04292","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":"2026-07-05T09:16:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ZYdPVOqjjXdLx7Q8pq2mDV5onAcJTPAMvfqCDM5vp6mm5DBxoc0sCIXZJDaa6bSEzJfkU2XXMyeyhDyP7mAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:10:09.483560Z"},"content_sha256":"3cbd84a7ecf872ec173b36056659cdbfaea9319263630d9535c9d251bab4af24","schema_version":"1.0","event_id":"sha256:3cbd84a7ecf872ec173b36056659cdbfaea9319263630d9535c9d251bab4af24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WTQUPQTOTYX3PEUXQRDIYB7KM7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficiently Identifying Low-Quality Language Subsets in Multilingual Datasets: A Case Study on a Large-Scale Multilingual Audio Dataset","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emily P. Ahn, Farhan Samir, Jian Zhu, M\\'arton Soskuthy, Shreya Prakash, Vered Shwartz","submitted_at":"2024-10-05T21:41:49Z","abstract_excerpt":"Curating datasets that span multiple languages is challenging. To make the collection more scalable, researchers often incorporate one or more imperfect classifiers in the process, like language identification models. These models, however, are prone to failure, resulting in some language subsets being unreliable for downstream tasks. We introduce a statistical test, the Preference Proportion Test, for identifying such unreliable subsets. By annotating only 20 samples for a language subset, we're able to identify systematic transcription errors for 10 language subsets in a recent large multili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04292","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/2410.04292/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":"2026-07-05T09:16:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6nCqDeFalEAA+ceP0pDiz9SHTy8k2WGMBUgpGTNJxUWg12I/FP7LZ1uyfZSmKBt0/3sXGCWE+MFjeUa/esT0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:10:09.484073Z"},"content_sha256":"35e62c487f80c30e924016587d70ee6fe1c51f11347621316471b17abac7c89a","schema_version":"1.0","event_id":"sha256:35e62c487f80c30e924016587d70ee6fe1c51f11347621316471b17abac7c89a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTQUPQTOTYX3PEUXQRDIYB7KM7/bundle.json","state_url":"https://pith.science/pith/WTQUPQTOTYX3PEUXQRDIYB7KM7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTQUPQTOTYX3PEUXQRDIYB7KM7/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":"2026-08-08T03:10:09Z","links":{"resolver":"https://pith.science/pith/WTQUPQTOTYX3PEUXQRDIYB7KM7","bundle":"https://pith.science/pith/WTQUPQTOTYX3PEUXQRDIYB7KM7/bundle.json","state":"https://pith.science/pith/WTQUPQTOTYX3PEUXQRDIYB7KM7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTQUPQTOTYX3PEUXQRDIYB7KM7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WTQUPQTOTYX3PEUXQRDIYB7KM7","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":"92372e0c85df2260dccf72a8edf643aec3da0a8a89cc60e1ff7db969bcfc0656","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T21:41:49Z","title_canon_sha256":"46e66df16d7ec68f0aeb580d610ab9ede014cc8537d68d34a8a87e2e5fc5a9e9"},"schema_version":"1.0","source":{"id":"2410.04292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04292","created_at":"2026-07-05T09:16:32Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04292v1","created_at":"2026-07-05T09:16:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04292","created_at":"2026-07-05T09:16:32Z"},{"alias_kind":"pith_short_12","alias_value":"WTQUPQTOTYX3","created_at":"2026-07-05T09:16:32Z"},{"alias_kind":"pith_short_16","alias_value":"WTQUPQTOTYX3PEUX","created_at":"2026-07-05T09:16:32Z"},{"alias_kind":"pith_short_8","alias_value":"WTQUPQTO","created_at":"2026-07-05T09:16:32Z"}],"graph_snapshots":[{"event_id":"sha256:35e62c487f80c30e924016587d70ee6fe1c51f11347621316471b17abac7c89a","target":"graph","created_at":"2026-07-05T09:16:32Z","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/2410.04292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Curating datasets that span multiple languages is challenging. To make the collection more scalable, researchers often incorporate one or more imperfect classifiers in the process, like language identification models. These models, however, are prone to failure, resulting in some language subsets being unreliable for downstream tasks. We introduce a statistical test, the Preference Proportion Test, for identifying such unreliable subsets. By annotating only 20 samples for a language subset, we're able to identify systematic transcription errors for 10 language subsets in a recent large multili","authors_text":"Emily P. Ahn, Farhan Samir, Jian Zhu, M\\'arton Soskuthy, Shreya Prakash, Vered Shwartz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T21:41:49Z","title":"Efficiently Identifying Low-Quality Language Subsets in Multilingual Datasets: A Case Study on a Large-Scale Multilingual Audio Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04292","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":"sha256:3cbd84a7ecf872ec173b36056659cdbfaea9319263630d9535c9d251bab4af24","target":"record","created_at":"2026-07-05T09:16:32Z","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":"92372e0c85df2260dccf72a8edf643aec3da0a8a89cc60e1ff7db969bcfc0656","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-05T21:41:49Z","title_canon_sha256":"46e66df16d7ec68f0aeb580d610ab9ede014cc8537d68d34a8a87e2e5fc5a9e9"},"schema_version":"1.0","source":{"id":"2410.04292","kind":"arxiv","version":1}},"canonical_sha256":"b4e147c26e9e2fb7929784468c07ea67ef05abb2129e74d690c8027e59b3d2cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4e147c26e9e2fb7929784468c07ea67ef05abb2129e74d690c8027e59b3d2cd","first_computed_at":"2026-07-05T09:16:32.487061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:32.487061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S//pqkMBhI5yt7Va0ymK1PBWwKmavXewkJQnmJDK3gx5Wu6pw0SpHxmEk0KUH2dDiT5t+iC3m3+9bgmZEx4xDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:32.487424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cbd84a7ecf872ec173b36056659cdbfaea9319263630d9535c9d251bab4af24","sha256:35e62c487f80c30e924016587d70ee6fe1c51f11347621316471b17abac7c89a"],"state_sha256":"42882b52923e4c3a65ad99424f3e02cd94500f7cd52c76a13a72ed4ba32520d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ldutnyxpxTbiiD/Sn9tA37vw7s5ks/UmQxwvZCSej13GA8vzDIjfg8NIuQOaobmoSv9DErcYAAbDJw3XcFf4Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:10:09.488592Z","bundle_sha256":"ed55f9c52ba78c2b54a28522b1882ea5fa14c8686d82cb33b86164a41b659c06"}}