{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TZ46XIU2YYOPABYY4HWPMS34P7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a932772d023b296f3a7cdcc6168a1d29d982c3cc0243856ec9d4f3bcaf8bc18d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-13T20:04:02Z","title_canon_sha256":"8ce73f028c42fa630301b0eb0aeb496488e2f3352badda684a74e8e11efdf5c1"},"schema_version":"1.0","source":{"id":"2307.07049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07049","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07049v1","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07049","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"pith_short_12","alias_value":"TZ46XIU2YYOP","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"pith_short_16","alias_value":"TZ46XIU2YYOPABYY","created_at":"2026-07-05T06:30:49Z"},{"alias_kind":"pith_short_8","alias_value":"TZ46XIU2","created_at":"2026-07-05T06:30:49Z"}],"graph_snapshots":[{"event_id":"sha256:dd3dd7bf1f434037fa1a94dd9c738e889e78e3b8b8971356ec8e98046869138e","target":"graph","created_at":"2026-07-05T06:30:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2307.07049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-13T20:04:02Z","title":"MegaWika: Millions of reports and their sources across 50 diverse languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07049","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c2035d88e8b34c27a4cdb53caced9b229a3f006cb807982b3898fe0c5a698b36","target":"record","created_at":"2026-07-05T06:30:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a932772d023b296f3a7cdcc6168a1d29d982c3cc0243856ec9d4f3bcaf8bc18d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-13T20:04:02Z","title_canon_sha256":"8ce73f028c42fa630301b0eb0aeb496488e2f3352badda684a74e8e11efdf5c1"},"schema_version":"1.0","source":{"id":"2307.07049","kind":"arxiv","version":1}},"canonical_sha256":"9e79eba29ac61cf00718e1ecf64b7c7ff33ce1cd8d555a5a8db81203eea9e0f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e79eba29ac61cf00718e1ecf64b7c7ff33ce1cd8d555a5a8db81203eea9e0f0","first_computed_at":"2026-07-05T06:30:49.720695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:30:49.720695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nbKGb52mP3gRZo2qhAyyUBdQxMXcqOxdaqyrf5lglmYlGhORx21QXLk8se6P6KHdLa+98eO0Tdn4Kp10k+gWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:30:49.721127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.07049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2035d88e8b34c27a4cdb53caced9b229a3f006cb807982b3898fe0c5a698b36","sha256:dd3dd7bf1f434037fa1a94dd9c738e889e78e3b8b8971356ec8e98046869138e"],"state_sha256":"28ddc3716a4bee0167bd038749e45f44b8814598816bbf079db67ba30bf3221a"}