{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MCVVB6EDKEPDJD3G7E52ZOBYDN","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":"99acd2b9705f56e8eecdd51656c9a86a0d91018209e27449b8d5d19da2e159ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-10T13:09:23Z","title_canon_sha256":"3f68ac168d794718115e7c26e7b2b727aabaef7f6830a0f9291eeff1ff8ed410"},"schema_version":"1.0","source":{"id":"2407.07630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07630","created_at":"2026-07-05T08:42:15Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07630v1","created_at":"2026-07-05T08:42:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07630","created_at":"2026-07-05T08:42:15Z"},{"alias_kind":"pith_short_12","alias_value":"MCVVB6EDKEPD","created_at":"2026-07-05T08:42:15Z"},{"alias_kind":"pith_short_16","alias_value":"MCVVB6EDKEPDJD3G","created_at":"2026-07-05T08:42:15Z"},{"alias_kind":"pith_short_8","alias_value":"MCVVB6ED","created_at":"2026-07-05T08:42:15Z"}],"graph_snapshots":[{"event_id":"sha256:d98c92969499e4fe2a43f4a7b29423089b523d7cbb2b991cfe36a95a9535b60c","target":"graph","created_at":"2026-07-05T08:42:15Z","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/2407.07630/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This article presents a comprehensive review of the challenges associated with using massive web-mined corpora for the pre-training of large language models (LLMs). This review identifies key challenges in this domain, including challenges such as noise (irrelevant or misleading information), duplication of content, the presence of low-quality or incorrect information, biases, and the inclusion of sensitive or personal information in web-mined corpora. Addressing these issues is crucial for the development of accurate, reliable, and ethically responsible language models. Through an examination","authors_text":"Micha{\\l} Pere{\\l}kiewicz, Rafa{\\l} Po\\'swiata","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-10T13:09:23Z","title":"A Review of the Challenges with Massive Web-mined Corpora Used in Large Language Models Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07630","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":"sha256:8649c4e99df0e0c1b89db47211a44915a03324b6160a46958e021afdf2cc6cdb","target":"record","created_at":"2026-07-05T08:42:15Z","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":"99acd2b9705f56e8eecdd51656c9a86a0d91018209e27449b8d5d19da2e159ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-10T13:09:23Z","title_canon_sha256":"3f68ac168d794718115e7c26e7b2b727aabaef7f6830a0f9291eeff1ff8ed410"},"schema_version":"1.0","source":{"id":"2407.07630","kind":"arxiv","version":1}},"canonical_sha256":"60ab50f883511e348f66f93bacb8381b4b309a5dba8f4bef1db70acca257aab4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60ab50f883511e348f66f93bacb8381b4b309a5dba8f4bef1db70acca257aab4","first_computed_at":"2026-07-05T08:42:15.175415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:15.175415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4gbUMdld34ViVTtqOYJdB34MinGLmYbZXuztkN1CrhnDMZv2Q9nOE0OQRMRqN8SKSivS1Y/b3Tkt4LcrSMW0DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:15.175881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8649c4e99df0e0c1b89db47211a44915a03324b6160a46958e021afdf2cc6cdb","sha256:d98c92969499e4fe2a43f4a7b29423089b523d7cbb2b991cfe36a95a9535b60c"],"state_sha256":"0ddc19e839114d720315e20dec0fa39ffa5e11a39d4fe98a79291d6cfd54d8a4"}