{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TZ46XIU2YYOPABYY4HWPMS34P7","short_pith_number":"pith:TZ46XIU2","schema_version":"1.0","canonical_sha256":"9e79eba29ac61cf00718e1ecf64b7c7ff33ce1cd8d555a5a8db81203eea9e0f0","source":{"kind":"arxiv","id":"2307.07049","version":1},"attestation_state":"computed","paper":{"title":"MegaWika: Millions of reports and their sources across 50 diverse languages","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Steven White, Alexander Martin, Anqi Liu, Benjamin Van Durme, Jordan Boyd-Graber, Kenton Murray, Mahsa Yarmohammadi, Michelle Yuan, Orion Weller, Samuel Barham, Siddharth Vashishtha, Zhengping Jiang","submitted_at":"2023-07-13T20:04:02Z","abstract_excerpt":"To foster the development of new models for collaborative AI-assisted report generation, we introduce MegaWika, consisting of 13 million Wikipedia articles in 50 diverse languages, along with their 71 million referenced source materials. We process this dataset for a myriad of applications, going beyond the initial Wikipedia citation extraction and web scraping of content, including translating non-English articles for cross-lingual applications and providing FrameNet parses for automated semantic analysis. MegaWika is the largest resource for sentence-level report generation and the only repo"},"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":"2307.07049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-13T20:04:02Z","cross_cats_sorted":[],"title_canon_sha256":"8ce73f028c42fa630301b0eb0aeb496488e2f3352badda684a74e8e11efdf5c1","abstract_canon_sha256":"a932772d023b296f3a7cdcc6168a1d29d982c3cc0243856ec9d4f3bcaf8bc18d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:49.721127Z","signature_b64":"nbKGb52mP3gRZo2qhAyyUBdQxMXcqOxdaqyrf5lglmYlGhORx21QXLk8se6P6KHdLa+98eO0Tdn4Kp10k+gWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e79eba29ac61cf00718e1ecf64b7c7ff33ce1cd8d555a5a8db81203eea9e0f0","last_reissued_at":"2026-07-05T06:30:49.720695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:49.720695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MegaWika: Millions of reports and their sources across 50 diverse languages","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Steven White, Alexander Martin, Anqi Liu, Benjamin Van Durme, Jordan Boyd-Graber, Kenton Murray, Mahsa Yarmohammadi, Michelle Yuan, Orion Weller, Samuel Barham, Siddharth Vashishtha, Zhengping Jiang","submitted_at":"2023-07-13T20:04:02Z","abstract_excerpt":"To foster the development of new models for collaborative AI-assisted report generation, we introduce MegaWika, consisting of 13 million Wikipedia articles in 50 diverse languages, along with their 71 million referenced source materials. We process this dataset for a myriad of applications, going beyond the initial Wikipedia citation extraction and web scraping of content, including translating non-English articles for cross-lingual applications and providing FrameNet parses for automated semantic analysis. MegaWika is the largest resource for sentence-level report generation and the only repo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07049","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/2307.07049/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":"2307.07049","created_at":"2026-07-05T06:30:49.720760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07049v1","created_at":"2026-07-05T06:30:49.720760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07049","created_at":"2026-07-05T06:30:49.720760+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZ46XIU2YYOP","created_at":"2026-07-05T06:30:49.720760+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZ46XIU2YYOPABYY","created_at":"2026-07-05T06:30:49.720760+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZ46XIU2","created_at":"2026-07-05T06:30:49.720760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZ46XIU2YYOPABYY4HWPMS34P7","json":"https://pith.science/pith/TZ46XIU2YYOPABYY4HWPMS34P7.json","graph_json":"https://pith.science/api/pith-number/TZ46XIU2YYOPABYY4HWPMS34P7/graph.json","events_json":"https://pith.science/api/pith-number/TZ46XIU2YYOPABYY4HWPMS34P7/events.json","paper":"https://pith.science/paper/TZ46XIU2"},"agent_actions":{"view_html":"https://pith.science/pith/TZ46XIU2YYOPABYY4HWPMS34P7","download_json":"https://pith.science/pith/TZ46XIU2YYOPABYY4HWPMS34P7.json","view_paper":"https://pith.science/paper/TZ46XIU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07049&json=true","fetch_graph":"https://pith.science/api/pith-number/TZ46XIU2YYOPABYY4HWPMS34P7/graph.json","fetch_events":"https://pith.science/api/pith-number/TZ46XIU2YYOPABYY4HWPMS34P7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZ46XIU2YYOPABYY4HWPMS34P7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZ46XIU2YYOPABYY4HWPMS34P7/action/storage_attestation","attest_author":"https://pith.science/pith/TZ46XIU2YYOPABYY4HWPMS34P7/action/author_attestation","sign_citation":"https://pith.science/pith/TZ46XIU2YYOPABYY4HWPMS34P7/action/citation_signature","submit_replication":"https://pith.science/pith/TZ46XIU2YYOPABYY4HWPMS34P7/action/replication_record"}},"created_at":"2026-07-05T06:30:49.720760+00:00","updated_at":"2026-07-05T06:30:49.720760+00:00"}