{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OUA4ACOIH2MTIEBJG4RF3TGD5O","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":"0b1a62693b48787463239a1b41cd334557e57b2b747eb556de6698bce84a86c1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-11T00:11:50Z","title_canon_sha256":"0ca007c04f96569429019deffded28a994c7a6cf9adea1016a7c9bd6b87d2e45"},"schema_version":"1.0","source":{"id":"2311.06440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06440","created_at":"2026-07-05T07:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06440v1","created_at":"2026-07-05T07:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06440","created_at":"2026-07-05T07:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"OUA4ACOIH2MT","created_at":"2026-07-05T07:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"OUA4ACOIH2MTIEBJ","created_at":"2026-07-05T07:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"OUA4ACOI","created_at":"2026-07-05T07:11:40Z"}],"graph_snapshots":[{"event_id":"sha256:e425ec07f091f77410c187d3872126b9881ed24158cdb23a6d95e83709a527b5","target":"graph","created_at":"2026-07-05T07:11:40Z","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/2311.06440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data quality is a problem that perpetually resurfaces throughout the field of NLP, regardless of task, domain, or architecture, and remains especially severe for lower-resource languages. A typical and insidious issue, affecting both training data and model output, is data that is repetitive and dominated by linguistically uninteresting boilerplate, such as price catalogs or computer-generated log files. Though this problem permeates many web-scraped corpora, there has yet to be a benchmark to test against, or a systematic study to find simple metrics that generalize across languages and agree","authors_text":"Isaac Caswell, Isabel Papadimitriou, Lisa Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-11T00:11:50Z","title":"Separating the Wheat from the Chaff with BREAD: An open-source benchmark and metrics to detect redundancy in text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06440","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":"sha256:3a65a9e0a61b66f3a332761c76b5be82dc329cb19998e181a6f13787d140ae20","target":"record","created_at":"2026-07-05T07:11:40Z","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":"0b1a62693b48787463239a1b41cd334557e57b2b747eb556de6698bce84a86c1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-11T00:11:50Z","title_canon_sha256":"0ca007c04f96569429019deffded28a994c7a6cf9adea1016a7c9bd6b87d2e45"},"schema_version":"1.0","source":{"id":"2311.06440","kind":"arxiv","version":1}},"canonical_sha256":"7501c009c83e9934102937225dccc3ebb8970326a04b242df2b8e9579a8e6a14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7501c009c83e9934102937225dccc3ebb8970326a04b242df2b8e9579a8e6a14","first_computed_at":"2026-07-05T07:11:40.001340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:40.001340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Ns1QlVMiswdaEhxP4ZkOmE8hzkQCcck/awy13HFLDUSiGs5pPtQqVIICtSLgqH3zPSaS9pCrWYoB3ArguesAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:40.001866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.06440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a65a9e0a61b66f3a332761c76b5be82dc329cb19998e181a6f13787d140ae20","sha256:e425ec07f091f77410c187d3872126b9881ed24158cdb23a6d95e83709a527b5"],"state_sha256":"1cca29b2865fabfa33b07e880f1623c28d215a4ad4c418d57e655aaf124f3f12"}