{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OUA4ACOIH2MTIEBJG4RF3TGD5O","short_pith_number":"pith:OUA4ACOI","schema_version":"1.0","canonical_sha256":"7501c009c83e9934102937225dccc3ebb8970326a04b242df2b8e9579a8e6a14","source":{"kind":"arxiv","id":"2311.06440","version":1},"attestation_state":"computed","paper":{"title":"Separating the Wheat from the Chaff with BREAD: An open-source benchmark and metrics to detect redundancy in text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Isaac Caswell, Isabel Papadimitriou, Lisa Wang","submitted_at":"2023-11-11T00:11:50Z","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"},"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":"2311.06440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-11T00:11:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0ca007c04f96569429019deffded28a994c7a6cf9adea1016a7c9bd6b87d2e45","abstract_canon_sha256":"0b1a62693b48787463239a1b41cd334557e57b2b747eb556de6698bce84a86c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:40.001866Z","signature_b64":"9Ns1QlVMiswdaEhxP4ZkOmE8hzkQCcck/awy13HFLDUSiGs5pPtQqVIICtSLgqH3zPSaS9pCrWYoB3ArguesAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7501c009c83e9934102937225dccc3ebb8970326a04b242df2b8e9579a8e6a14","last_reissued_at":"2026-07-05T07:11:40.001340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:40.001340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Separating the Wheat from the Chaff with BREAD: An open-source benchmark and metrics to detect redundancy in text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Isaac Caswell, Isabel Papadimitriou, Lisa Wang","submitted_at":"2023-11-11T00:11:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06440","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/2311.06440/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":"2311.06440","created_at":"2026-07-05T07:11:40.001400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06440v1","created_at":"2026-07-05T07:11:40.001400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06440","created_at":"2026-07-05T07:11:40.001400+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUA4ACOIH2MT","created_at":"2026-07-05T07:11:40.001400+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUA4ACOIH2MTIEBJ","created_at":"2026-07-05T07:11:40.001400+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUA4ACOI","created_at":"2026-07-05T07:11:40.001400+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/OUA4ACOIH2MTIEBJG4RF3TGD5O","json":"https://pith.science/pith/OUA4ACOIH2MTIEBJG4RF3TGD5O.json","graph_json":"https://pith.science/api/pith-number/OUA4ACOIH2MTIEBJG4RF3TGD5O/graph.json","events_json":"https://pith.science/api/pith-number/OUA4ACOIH2MTIEBJG4RF3TGD5O/events.json","paper":"https://pith.science/paper/OUA4ACOI"},"agent_actions":{"view_html":"https://pith.science/pith/OUA4ACOIH2MTIEBJG4RF3TGD5O","download_json":"https://pith.science/pith/OUA4ACOIH2MTIEBJG4RF3TGD5O.json","view_paper":"https://pith.science/paper/OUA4ACOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06440&json=true","fetch_graph":"https://pith.science/api/pith-number/OUA4ACOIH2MTIEBJG4RF3TGD5O/graph.json","fetch_events":"https://pith.science/api/pith-number/OUA4ACOIH2MTIEBJG4RF3TGD5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUA4ACOIH2MTIEBJG4RF3TGD5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUA4ACOIH2MTIEBJG4RF3TGD5O/action/storage_attestation","attest_author":"https://pith.science/pith/OUA4ACOIH2MTIEBJG4RF3TGD5O/action/author_attestation","sign_citation":"https://pith.science/pith/OUA4ACOIH2MTIEBJG4RF3TGD5O/action/citation_signature","submit_replication":"https://pith.science/pith/OUA4ACOIH2MTIEBJG4RF3TGD5O/action/replication_record"}},"created_at":"2026-07-05T07:11:40.001400+00:00","updated_at":"2026-07-05T07:11:40.001400+00:00"}