{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:55IY4NRO7SNEX4CV3ZBBRGUI32","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":"2280b09d4de7d9f49382d6d6e8571fe58d86ad170b772425bd9e9d816284c4e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T14:46:26Z","title_canon_sha256":"24ee8392fbb08011ef3c4413b4c5a4b82f94299d71ef4aefee8e9b7bf619cba2"},"schema_version":"1.0","source":{"id":"2507.01764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01764","created_at":"2026-07-05T11:30:54Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01764v1","created_at":"2026-07-05T11:30:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01764","created_at":"2026-07-05T11:30:54Z"},{"alias_kind":"pith_short_12","alias_value":"55IY4NRO7SNE","created_at":"2026-07-05T11:30:54Z"},{"alias_kind":"pith_short_16","alias_value":"55IY4NRO7SNEX4CV","created_at":"2026-07-05T11:30:54Z"},{"alias_kind":"pith_short_8","alias_value":"55IY4NRO","created_at":"2026-07-05T11:30:54Z"}],"graph_snapshots":[{"event_id":"sha256:9a686424ac165a8434acdc532b0067fdf3b2582e7767f418f6b5c4cd7793f26d","target":"graph","created_at":"2026-07-05T11:30:54Z","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/2507.01764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenisation - \"the process of splitting text into atomic parts\" (Brezina & Timperley, 2017: 1) - is a crucial step for corpus linguistics, as it provides the basis for any applicable quantitative method (e.g. collocations) while ensuring the reliability of qualitative approaches. This paper examines how discrepancies in tokenisation affect the representation of language data and the validity of analytical findings: investigating the challenges posed by emojis and homoglyphs, the study highlights the necessity of preprocessing these elements to maintain corpus fidelity to the source data. The ","authors_text":"Matteo Di Cristofaro","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T14:46:26Z","title":"Data interference: emojis, homoglyphs, and issues of data fidelity in corpora and their results"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01764","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":"sha256:94cce56efb579d46d726adf6083fd455823179a875be629ddcff0df1c1f8465e","target":"record","created_at":"2026-07-05T11:30:54Z","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":"2280b09d4de7d9f49382d6d6e8571fe58d86ad170b772425bd9e9d816284c4e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T14:46:26Z","title_canon_sha256":"24ee8392fbb08011ef3c4413b4c5a4b82f94299d71ef4aefee8e9b7bf619cba2"},"schema_version":"1.0","source":{"id":"2507.01764","kind":"arxiv","version":1}},"canonical_sha256":"ef518e362efc9a4bf055de42189a88deb5c2a69ebc0ee0056ca5ce1cbead3b0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef518e362efc9a4bf055de42189a88deb5c2a69ebc0ee0056ca5ce1cbead3b0b","first_computed_at":"2026-07-05T11:30:54.747935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:54.747935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vHql4rUVLPHpo+6MzhaybLb3FdTAlHDpmJEnr79KBpA0NoYOu2jN1n98YLGhEoHwI79ypEIBTzOX73+bxuFRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:54.748479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94cce56efb579d46d726adf6083fd455823179a875be629ddcff0df1c1f8465e","sha256:9a686424ac165a8434acdc532b0067fdf3b2582e7767f418f6b5c4cd7793f26d"],"state_sha256":"d8de097ae6fcf36e67959b1cdd49fc192a36a1bedba007d46e992f97ddb4f845"}