{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C4SQJYVOMGNXN6S5QZUNDDRXOK","short_pith_number":"pith:C4SQJYVO","schema_version":"1.0","canonical_sha256":"172504e2ae619b76fa5d8668d18e37729263cb3f73339df7fd77bf05b74b1832","source":{"kind":"arxiv","id":"2307.13405","version":1},"attestation_state":"computed","paper":{"title":"Towards Bridging the Digital Language Divide","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fausto Giunchiglia, G\\'abor Bella, Gertraud Koch, Paula Helm","submitted_at":"2023-07-25T10:53:20Z","abstract_excerpt":"It is a well-known fact that current AI-based language technology -- language models, machine translation systems, multilingual dictionaries and corpora -- focuses on the world's 2-3% most widely spoken languages. Recent research efforts have attempted to expand the coverage of AI technology to `under-resourced languages.' The goal of our paper is to bring attention to a phenomenon that we call linguistic bias: multilingual language processing systems often exhibit a hardwired, yet usually involuntary and hidden representational preference towards certain languages. Linguistic bias is manifest"},"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":"2307.13405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-25T10:53:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"051637faa759380813cb3691cb1eef69756923f3dc4994453b6e538f83e57e6d","abstract_canon_sha256":"91cff66985c93a8a57658bad45b4b327cd68b89be78da688837874b1c7027344"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:13.849238Z","signature_b64":"20SR2o7iWLKw+BK31CYGtkCHhse+Ev+hXnpOsB/h7t3VWUAbejDfvKldL9jdZQ8PrkWJ2GDv7YWUYeDY7gzjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"172504e2ae619b76fa5d8668d18e37729263cb3f73339df7fd77bf05b74b1832","last_reissued_at":"2026-07-05T06:34:13.848726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:13.848726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Bridging the Digital Language Divide","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fausto Giunchiglia, G\\'abor Bella, Gertraud Koch, Paula Helm","submitted_at":"2023-07-25T10:53:20Z","abstract_excerpt":"It is a well-known fact that current AI-based language technology -- language models, machine translation systems, multilingual dictionaries and corpora -- focuses on the world's 2-3% most widely spoken languages. Recent research efforts have attempted to expand the coverage of AI technology to `under-resourced languages.' The goal of our paper is to bring attention to a phenomenon that we call linguistic bias: multilingual language processing systems often exhibit a hardwired, yet usually involuntary and hidden representational preference towards certain languages. Linguistic bias is manifest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13405","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/2307.13405/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":"2307.13405","created_at":"2026-07-05T06:34:13.848791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.13405v1","created_at":"2026-07-05T06:34:13.848791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13405","created_at":"2026-07-05T06:34:13.848791+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4SQJYVOMGNX","created_at":"2026-07-05T06:34:13.848791+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4SQJYVOMGNXN6S5","created_at":"2026-07-05T06:34:13.848791+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4SQJYVO","created_at":"2026-07-05T06:34:13.848791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18942","citing_title":"Disparities In Negation Understanding Across Languages In Vision-Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02608","citing_title":"Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C4SQJYVOMGNXN6S5QZUNDDRXOK","json":"https://pith.science/pith/C4SQJYVOMGNXN6S5QZUNDDRXOK.json","graph_json":"https://pith.science/api/pith-number/C4SQJYVOMGNXN6S5QZUNDDRXOK/graph.json","events_json":"https://pith.science/api/pith-number/C4SQJYVOMGNXN6S5QZUNDDRXOK/events.json","paper":"https://pith.science/paper/C4SQJYVO"},"agent_actions":{"view_html":"https://pith.science/pith/C4SQJYVOMGNXN6S5QZUNDDRXOK","download_json":"https://pith.science/pith/C4SQJYVOMGNXN6S5QZUNDDRXOK.json","view_paper":"https://pith.science/paper/C4SQJYVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.13405&json=true","fetch_graph":"https://pith.science/api/pith-number/C4SQJYVOMGNXN6S5QZUNDDRXOK/graph.json","fetch_events":"https://pith.science/api/pith-number/C4SQJYVOMGNXN6S5QZUNDDRXOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4SQJYVOMGNXN6S5QZUNDDRXOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4SQJYVOMGNXN6S5QZUNDDRXOK/action/storage_attestation","attest_author":"https://pith.science/pith/C4SQJYVOMGNXN6S5QZUNDDRXOK/action/author_attestation","sign_citation":"https://pith.science/pith/C4SQJYVOMGNXN6S5QZUNDDRXOK/action/citation_signature","submit_replication":"https://pith.science/pith/C4SQJYVOMGNXN6S5QZUNDDRXOK/action/replication_record"}},"created_at":"2026-07-05T06:34:13.848791+00:00","updated_at":"2026-07-05T06:34:13.848791+00:00"}