{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X6SVZH7BVXRONOIRVQ2P3IEWG3","short_pith_number":"pith:X6SVZH7B","schema_version":"1.0","canonical_sha256":"bfa55c9fe1ade2e6b911ac34fda09636c84c2c19016d85ba7937f5a1d524e06f","source":{"kind":"arxiv","id":"2406.08726","version":3},"attestation_state":"computed","paper":{"title":"Standard Language Ideology in AI-Generated Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eve Fleisig, Genevieve Smith, Ishita Rustagi, Xavier Yin","submitted_at":"2024-06-13T01:08:40Z","abstract_excerpt":"Large language models (LLMs) generate text that reinforces standard language ideology: a bias towards certain language varieties that are granted more prestige, authority, and legitimacy than others. This paper contributes a sociotechnically grounded faceted taxonomy that illustrates how generative AI systems reproduce standard language ideology and its societal implications. We introduce the concept of standard AI-generated language ideology to explain how AI systems confer legitimacy on certain language varieties while marginalizing others, structuring patterns of performance disparity, ster"},"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":"2406.08726","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T01:08:40Z","cross_cats_sorted":[],"title_canon_sha256":"d23b53d185b22eeb490d265f58c263e6627daafec5ada6a618e7054ef7651b4f","abstract_canon_sha256":"a90a2ef6734edca4770ab8f85060cb454b06c011f35696aaa78aed02e992b8a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:55.326769Z","signature_b64":"//S4ZV9jsdpUcDEPq7wWP1r+PugDdBelvIHna/aAD9L+XoRQ/7/ZeIDgHYCxLjE0JN6xGqGVveUSJmES2u+VDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfa55c9fe1ade2e6b911ac34fda09636c84c2c19016d85ba7937f5a1d524e06f","last_reissued_at":"2026-06-10T01:10:55.325581Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:55.325581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Standard Language Ideology in AI-Generated Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eve Fleisig, Genevieve Smith, Ishita Rustagi, Xavier Yin","submitted_at":"2024-06-13T01:08:40Z","abstract_excerpt":"Large language models (LLMs) generate text that reinforces standard language ideology: a bias towards certain language varieties that are granted more prestige, authority, and legitimacy than others. This paper contributes a sociotechnically grounded faceted taxonomy that illustrates how generative AI systems reproduce standard language ideology and its societal implications. We introduce the concept of standard AI-generated language ideology to explain how AI systems confer legitimacy on certain language varieties while marginalizing others, structuring patterns of performance disparity, ster"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08726","kind":"arxiv","version":3},"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/2406.08726/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":"2406.08726","created_at":"2026-06-10T01:10:55.325766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08726v3","created_at":"2026-06-10T01:10:55.325766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08726","created_at":"2026-06-10T01:10:55.325766+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6SVZH7BVXRO","created_at":"2026-06-10T01:10:55.325766+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6SVZH7BVXRONOIR","created_at":"2026-06-10T01:10:55.325766+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6SVZH7B","created_at":"2026-06-10T01:10:55.325766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.27661","citing_title":"Language Ideologies in a Multilingual Society: An LLM-based Analysis of Luxembourgish News Comments","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02080","citing_title":"Cripping AI: Reimagining AI Through Lived Disability Experiences","ref_index":233,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6SVZH7BVXRONOIRVQ2P3IEWG3","json":"https://pith.science/pith/X6SVZH7BVXRONOIRVQ2P3IEWG3.json","graph_json":"https://pith.science/api/pith-number/X6SVZH7BVXRONOIRVQ2P3IEWG3/graph.json","events_json":"https://pith.science/api/pith-number/X6SVZH7BVXRONOIRVQ2P3IEWG3/events.json","paper":"https://pith.science/paper/X6SVZH7B"},"agent_actions":{"view_html":"https://pith.science/pith/X6SVZH7BVXRONOIRVQ2P3IEWG3","download_json":"https://pith.science/pith/X6SVZH7BVXRONOIRVQ2P3IEWG3.json","view_paper":"https://pith.science/paper/X6SVZH7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08726&json=true","fetch_graph":"https://pith.science/api/pith-number/X6SVZH7BVXRONOIRVQ2P3IEWG3/graph.json","fetch_events":"https://pith.science/api/pith-number/X6SVZH7BVXRONOIRVQ2P3IEWG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6SVZH7BVXRONOIRVQ2P3IEWG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6SVZH7BVXRONOIRVQ2P3IEWG3/action/storage_attestation","attest_author":"https://pith.science/pith/X6SVZH7BVXRONOIRVQ2P3IEWG3/action/author_attestation","sign_citation":"https://pith.science/pith/X6SVZH7BVXRONOIRVQ2P3IEWG3/action/citation_signature","submit_replication":"https://pith.science/pith/X6SVZH7BVXRONOIRVQ2P3IEWG3/action/replication_record"}},"created_at":"2026-06-10T01:10:55.325766+00:00","updated_at":"2026-06-10T01:10:55.325766+00:00"}