{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GP3TJKOF55PNFTDDHVIMKJF34K","short_pith_number":"pith:GP3TJKOF","schema_version":"1.0","canonical_sha256":"33f734a9c5ef5ed2cc633d50c524bbe282993dcf9f32b0ee97faec7cca0a4eb7","source":{"kind":"arxiv","id":"2501.13836","version":3},"attestation_state":"computed","paper":{"title":"Think Outside the Data: Colonial Biases and Systemic Issues in Automated Moderation Pipelines for Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Aditya Vashistha, Farhana Shahid, Mona Elswah","submitted_at":"2025-01-23T17:01:53Z","abstract_excerpt":"Most social media users come from the Global South, where harmful content usually appears in local languages. Yet, AI-driven moderation systems struggle with low-resource languages spoken in these regions. Through semi-structured interviews with 22 AI experts working on harmful content detection in four low-resource languages: Tamil (South Asia), Swahili (East Africa), Maghrebi Arabic (North Africa), and Quechua (South America)--we examine systemic issues in building automated moderation tools for these languages. Our findings reveal that beyond data scarcity, socio-political factors such as t"},"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":"2501.13836","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T17:01:53Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"6126a131d17e01ab3694479401a969f52eacd9c7745b80c7402debdce078f01e","abstract_canon_sha256":"ba8e7f3380b4331b8d0a9edeb077d8724ced745441316543b6e44fd51d36f1f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:47.256505Z","signature_b64":"pmFBo7n6GSsZSXWJKt+sbzpUGql1BYmxpkOhPieTT/N466g9W7q9VHq58B89lE7QRa1UXI0e6ZdWTgJhxHTJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33f734a9c5ef5ed2cc633d50c524bbe282993dcf9f32b0ee97faec7cca0a4eb7","last_reissued_at":"2026-07-05T11:48:47.256019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:47.256019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think Outside the Data: Colonial Biases and Systemic Issues in Automated Moderation Pipelines for Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Aditya Vashistha, Farhana Shahid, Mona Elswah","submitted_at":"2025-01-23T17:01:53Z","abstract_excerpt":"Most social media users come from the Global South, where harmful content usually appears in local languages. Yet, AI-driven moderation systems struggle with low-resource languages spoken in these regions. Through semi-structured interviews with 22 AI experts working on harmful content detection in four low-resource languages: Tamil (South Asia), Swahili (East Africa), Maghrebi Arabic (North Africa), and Quechua (South America)--we examine systemic issues in building automated moderation tools for these languages. Our findings reveal that beyond data scarcity, socio-political factors such as t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13836","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/2501.13836/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":"2501.13836","created_at":"2026-07-05T11:48:47.256083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13836v3","created_at":"2026-07-05T11:48:47.256083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13836","created_at":"2026-07-05T11:48:47.256083+00:00"},{"alias_kind":"pith_short_12","alias_value":"GP3TJKOF55PN","created_at":"2026-07-05T11:48:47.256083+00:00"},{"alias_kind":"pith_short_16","alias_value":"GP3TJKOF55PNFTDD","created_at":"2026-07-05T11:48:47.256083+00:00"},{"alias_kind":"pith_short_8","alias_value":"GP3TJKOF","created_at":"2026-07-05T11:48:47.256083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19190","citing_title":"Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12613","citing_title":"Creating Group Rules with AI: Human-AI Collaboration in WhatsApp Moderation","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GP3TJKOF55PNFTDDHVIMKJF34K","json":"https://pith.science/pith/GP3TJKOF55PNFTDDHVIMKJF34K.json","graph_json":"https://pith.science/api/pith-number/GP3TJKOF55PNFTDDHVIMKJF34K/graph.json","events_json":"https://pith.science/api/pith-number/GP3TJKOF55PNFTDDHVIMKJF34K/events.json","paper":"https://pith.science/paper/GP3TJKOF"},"agent_actions":{"view_html":"https://pith.science/pith/GP3TJKOF55PNFTDDHVIMKJF34K","download_json":"https://pith.science/pith/GP3TJKOF55PNFTDDHVIMKJF34K.json","view_paper":"https://pith.science/paper/GP3TJKOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13836&json=true","fetch_graph":"https://pith.science/api/pith-number/GP3TJKOF55PNFTDDHVIMKJF34K/graph.json","fetch_events":"https://pith.science/api/pith-number/GP3TJKOF55PNFTDDHVIMKJF34K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GP3TJKOF55PNFTDDHVIMKJF34K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GP3TJKOF55PNFTDDHVIMKJF34K/action/storage_attestation","attest_author":"https://pith.science/pith/GP3TJKOF55PNFTDDHVIMKJF34K/action/author_attestation","sign_citation":"https://pith.science/pith/GP3TJKOF55PNFTDDHVIMKJF34K/action/citation_signature","submit_replication":"https://pith.science/pith/GP3TJKOF55PNFTDDHVIMKJF34K/action/replication_record"}},"created_at":"2026-07-05T11:48:47.256083+00:00","updated_at":"2026-07-05T11:48:47.256083+00:00"}