{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JLRX7SWY52JWBBWHJPOB3H67MJ","short_pith_number":"pith:JLRX7SWY","schema_version":"1.0","canonical_sha256":"4ae37fcad8ee936086c74bdc1d9fdf624673c6f04b5629af5ce368e013a0e45f","source":{"kind":"arxiv","id":"2501.01056","version":1},"attestation_state":"computed","paper":{"title":"Risks of Cultural Erasure in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aida M. Davani, Kevin Robinson, Rida Qadri, Vinodkumar Prabhakaran","submitted_at":"2025-01-02T04:57:50Z","abstract_excerpt":"Large language models are increasingly being integrated into applications that shape the production and discovery of societal knowledge such as search, online education, and travel planning. As a result, language models will shape how people learn about, perceive and interact with global cultures making it important to consider whose knowledge systems and perspectives are represented in models. Recognizing this importance, increasingly work in Machine Learning and NLP has focused on evaluating gaps in global cultural representational distribution within outputs. However, more work is needed on"},"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":"2501.01056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T04:57:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bedd207594b471bb1dff3b9993c4ea83e57d52d1f0942954476574539ad17351","abstract_canon_sha256":"426b5652aa2821a942ddfe0d987411171c44ed570f5bc4dcab64242ad4a24e42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:13.657991Z","signature_b64":"l7cs2psIS434nJr1ZLrWWm+sS66ZBI2mx2JjAS0j5fG7k7k+l2ZZtUzMzwD7EjmjAtHN6P/lzOQjly8ixfriCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ae37fcad8ee936086c74bdc1d9fdf624673c6f04b5629af5ce368e013a0e45f","last_reissued_at":"2026-07-05T09:56:13.657554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:13.657554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risks of Cultural Erasure in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aida M. Davani, Kevin Robinson, Rida Qadri, Vinodkumar Prabhakaran","submitted_at":"2025-01-02T04:57:50Z","abstract_excerpt":"Large language models are increasingly being integrated into applications that shape the production and discovery of societal knowledge such as search, online education, and travel planning. As a result, language models will shape how people learn about, perceive and interact with global cultures making it important to consider whose knowledge systems and perspectives are represented in models. Recognizing this importance, increasingly work in Machine Learning and NLP has focused on evaluating gaps in global cultural representational distribution within outputs. However, more work is needed on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01056","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/2501.01056/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":"2501.01056","created_at":"2026-07-05T09:56:13.657610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01056v1","created_at":"2026-07-05T09:56:13.657610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01056","created_at":"2026-07-05T09:56:13.657610+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLRX7SWY52JW","created_at":"2026-07-05T09:56:13.657610+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLRX7SWY52JWBBWH","created_at":"2026-07-05T09:56:13.657610+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLRX7SWY","created_at":"2026-07-05T09:56:13.657610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20048","citing_title":"Culturally uneven urban perception in large language models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05936","citing_title":"Epistemic Injustice in Language Models: An Audit of Pretraining Filters and Guardrails","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28343","citing_title":"The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2512.05929","citing_title":"LLM Harms: A Taxonomy and Discussion","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03493","citing_title":"Cultural Authenticity: Comparing LLM Cultural Representations to Native Human Expectations","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20048","citing_title":"Culturally uneven urban perception in large language models","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLRX7SWY52JWBBWHJPOB3H67MJ","json":"https://pith.science/pith/JLRX7SWY52JWBBWHJPOB3H67MJ.json","graph_json":"https://pith.science/api/pith-number/JLRX7SWY52JWBBWHJPOB3H67MJ/graph.json","events_json":"https://pith.science/api/pith-number/JLRX7SWY52JWBBWHJPOB3H67MJ/events.json","paper":"https://pith.science/paper/JLRX7SWY"},"agent_actions":{"view_html":"https://pith.science/pith/JLRX7SWY52JWBBWHJPOB3H67MJ","download_json":"https://pith.science/pith/JLRX7SWY52JWBBWHJPOB3H67MJ.json","view_paper":"https://pith.science/paper/JLRX7SWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01056&json=true","fetch_graph":"https://pith.science/api/pith-number/JLRX7SWY52JWBBWHJPOB3H67MJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JLRX7SWY52JWBBWHJPOB3H67MJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLRX7SWY52JWBBWHJPOB3H67MJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLRX7SWY52JWBBWHJPOB3H67MJ/action/storage_attestation","attest_author":"https://pith.science/pith/JLRX7SWY52JWBBWHJPOB3H67MJ/action/author_attestation","sign_citation":"https://pith.science/pith/JLRX7SWY52JWBBWHJPOB3H67MJ/action/citation_signature","submit_replication":"https://pith.science/pith/JLRX7SWY52JWBBWHJPOB3H67MJ/action/replication_record"}},"created_at":"2026-07-05T09:56:13.657610+00:00","updated_at":"2026-07-05T09:56:13.657610+00:00"}