{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D4I5YYS6RF2M7UVC7BEDLSGZVA","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":"5e080b6ddb3ba1b95c38445996721d0b46491d2fe87c34fc97976d45cd6983b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T16:20:14Z","title_canon_sha256":"15252a5c709307b8566c67b3624bb713e007697ece955e04496c18fa4f27064a"},"schema_version":"1.0","source":{"id":"2606.06349","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06349","created_at":"2026-06-05T01:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06349v1","created_at":"2026-06-05T01:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06349","created_at":"2026-06-05T01:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"D4I5YYS6RF2M","created_at":"2026-06-05T01:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"D4I5YYS6RF2M7UVC","created_at":"2026-06-05T01:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"D4I5YYS6","created_at":"2026-06-05T01:15:42Z"}],"graph_snapshots":[{"event_id":"sha256:b0317be6ce771cc8a32f9293f0d2920ac3b79b5b370be91d9cf0871c43939439","target":"graph","created_at":"2026-06-05T01:15:42Z","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/2606.06349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Several of the world's languages are still under-resourced in terms of Natural Language Processing (NLP) tools. This is mostly due to the lack of high-quality datasets to train, develop, and evaluate systems and models for several tasks, such as Machine Translation (MT). We conduct a manual audit of the parallel and monolingual corpora available for Lombard, an under-resourced language continuum from Italy. Our analysis reveals that the perceived abundance of web-scraped data is an illusion, with massive datasets plagued by severe language misidentification, boilerplate text, and non-linguisti","authors_text":"Edoardo Signoroni, Pavel Rychl\\'y","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T16:20:14Z","title":"\"Chi nas dal soch el sent de legn\" -- Auditing Text Corpora for Lombard"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06349","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":"sha256:154b96fd432a464df00167fde870a77b1b7aef6bf58962cfdd89a860bf23e9af","target":"record","created_at":"2026-06-05T01:15:42Z","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":"5e080b6ddb3ba1b95c38445996721d0b46491d2fe87c34fc97976d45cd6983b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T16:20:14Z","title_canon_sha256":"15252a5c709307b8566c67b3624bb713e007697ece955e04496c18fa4f27064a"},"schema_version":"1.0","source":{"id":"2606.06349","kind":"arxiv","version":1}},"canonical_sha256":"1f11dc625e8974cfd2a2f84835c8d9a81c817d726f667d2264a23b31c9548cfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f11dc625e8974cfd2a2f84835c8d9a81c817d726f667d2264a23b31c9548cfb","first_computed_at":"2026-06-05T01:15:42.437522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:42.437522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WSgR55SMp6Nvx8PZSzcOldG1moJ41BqnH94IAvukfeE6iVye1gVRt6mSQ4QTsemn/CXNvvfcSSMl6pSSrz/ZCA==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:42.437907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06349","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:154b96fd432a464df00167fde870a77b1b7aef6bf58962cfdd89a860bf23e9af","sha256:b0317be6ce771cc8a32f9293f0d2920ac3b79b5b370be91d9cf0871c43939439"],"state_sha256":"cbc8ea82355f251e5d477e8e1e587513abac1a1268e630ff7e26a2af729663f2"}