{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3ON7B7LS4ITSBS7HENZ55ZOMJG","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":"0584bf084318904f51ba41292f9d4d0a5df4389de74e8644dbd35a3efb06ae34","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T17:14:45Z","title_canon_sha256":"f61ef1b39347cea71104a3da9af74ade7054536d8d8b720f23aaa549587afda2"},"schema_version":"1.0","source":{"id":"2212.10440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10440","created_at":"2026-07-05T05:27:07Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10440v1","created_at":"2026-07-05T05:27:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10440","created_at":"2026-07-05T05:27:07Z"},{"alias_kind":"pith_short_12","alias_value":"3ON7B7LS4ITS","created_at":"2026-07-05T05:27:07Z"},{"alias_kind":"pith_short_16","alias_value":"3ON7B7LS4ITSBS7H","created_at":"2026-07-05T05:27:07Z"},{"alias_kind":"pith_short_8","alias_value":"3ON7B7LS","created_at":"2026-07-05T05:27:07Z"}],"graph_snapshots":[{"event_id":"sha256:dc23951bb313841e38cc6826ca9ae8e637a4c331c923f381a45d773c6a1068e5","target":"graph","created_at":"2026-07-05T05:27:07Z","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/2212.10440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As demand for large corpora increases with the size of current state-of-the-art language models, using web data as the main part of the pre-training corpus for these models has become a ubiquitous practice. This, in turn, has introduced an important challenge for NLP practitioners, as they are now confronted with the task of developing highly optimized models and pipelines for pre-processing large quantities of textual data, which implies, effectively classifying and filtering multilingual, heterogeneous and noisy data, at web scale. One of the main components of this pre-processing step for t","authors_text":"Pedro Ortiz Suarez, Tim Jansen, Victoria Zevallos, Yangling Tong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T17:14:45Z","title":"Perplexed by Quality: A Perplexity-based Method for Adult and Harmful Content Detection in Multilingual Heterogeneous Web Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10440","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:cceac0abbdfc497f0e663236f0ec1a9f6c085e36ecefff3dc668020d629ba1d1","target":"record","created_at":"2026-07-05T05:27:07Z","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":"0584bf084318904f51ba41292f9d4d0a5df4389de74e8644dbd35a3efb06ae34","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T17:14:45Z","title_canon_sha256":"f61ef1b39347cea71104a3da9af74ade7054536d8d8b720f23aaa549587afda2"},"schema_version":"1.0","source":{"id":"2212.10440","kind":"arxiv","version":1}},"canonical_sha256":"db9bf0fd72e22720cbe72373dee5cc49848e8ec3d977e81b80b3989bc25b7812","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db9bf0fd72e22720cbe72373dee5cc49848e8ec3d977e81b80b3989bc25b7812","first_computed_at":"2026-07-05T05:27:07.637094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:27:07.637094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GiXvWbSxVHzBHnWN9RE9RJg0vDz/SzdX9VIBgsszJ68BALT1xNXjGsOXqXRiz4/LfYO9wO2bMQjGSrTr09BdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:27:07.637483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cceac0abbdfc497f0e663236f0ec1a9f6c085e36ecefff3dc668020d629ba1d1","sha256:dc23951bb313841e38cc6826ca9ae8e637a4c331c923f381a45d773c6a1068e5"],"state_sha256":"ace042bf5910fa598537dd6726a4fe54cb8541b09eacf44ddc8a359816435c96"}