{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IT3SX3IN2QXVYDUCGM7QVEBLIH","short_pith_number":"pith:IT3SX3IN","canonical_record":{"source":{"id":"2508.03828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2025-08-05T18:18:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ee00235369695b24bde59ea623758b37aa8445978ba50ab1239e6b31e33c080a","abstract_canon_sha256":"a637fb582e89aa68951c69f0e584a263f502114558a62ccd8a52e271f863018b"},"schema_version":"1.0"},"canonical_sha256":"44f72bed0dd42f5c0e82333f0a902b41f85a0b2f77df905635536b9e0b950d19","source":{"kind":"arxiv","id":"2508.03828","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03828","created_at":"2026-07-05T11:49:15Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03828v1","created_at":"2026-07-05T11:49:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03828","created_at":"2026-07-05T11:49:15Z"},{"alias_kind":"pith_short_12","alias_value":"IT3SX3IN2QXV","created_at":"2026-07-05T11:49:15Z"},{"alias_kind":"pith_short_16","alias_value":"IT3SX3IN2QXVYDUC","created_at":"2026-07-05T11:49:15Z"},{"alias_kind":"pith_short_8","alias_value":"IT3SX3IN","created_at":"2026-07-05T11:49:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IT3SX3IN2QXVYDUCGM7QVEBLIH","target":"record","payload":{"canonical_record":{"source":{"id":"2508.03828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2025-08-05T18:18:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ee00235369695b24bde59ea623758b37aa8445978ba50ab1239e6b31e33c080a","abstract_canon_sha256":"a637fb582e89aa68951c69f0e584a263f502114558a62ccd8a52e271f863018b"},"schema_version":"1.0"},"canonical_sha256":"44f72bed0dd42f5c0e82333f0a902b41f85a0b2f77df905635536b9e0b950d19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:15.958051Z","signature_b64":"kD0CA0VJRRWajLsgI29+ORWR4PxgAIrQ8iPy5jCw2HW4YpGbRUSLncxE7WoO+Lxti9QhVWT8BbB8UV1p2X2dAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44f72bed0dd42f5c0e82333f0a902b41f85a0b2f77df905635536b9e0b950d19","last_reissued_at":"2026-07-05T11:49:15.957594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:15.957594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.03828","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vJQilFQugnr6tXIQXiSxnVmNZ36bVSPbygdeTac/V5DW948GO88H0y6xsvNV2+6jk1C91AuyLRiswyp9QhsoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:53:37.636618Z"},"content_sha256":"61af8361ded39e6015791bcf0aaa0ccbcdff845c923bd613b443d8234eaa6069","schema_version":"1.0","event_id":"sha256:61af8361ded39e6015791bcf0aaa0ccbcdff845c923bd613b443d8234eaa6069"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IT3SX3IN2QXVYDUCGM7QVEBLIH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MegaWika 2: A More Comprehensive Multilingual Collection of Articles and their Sources","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DL","authors_text":"Benjamin Van Durme, Chandler May, Samuel Barham","submitted_at":"2025-08-05T18:18:17Z","abstract_excerpt":"We introduce MegaWika 2, a large, multilingual dataset of Wikipedia articles with their citations and scraped web sources; articles are represented in a rich data structure, and scraped source texts are stored inline with precise character offsets of their citations in the article text. MegaWika 2 is a major upgrade from the original MegaWika, spanning six times as many articles and twice as many fully scraped citations. Both MegaWika and MegaWika 2 support report generation research ; whereas MegaWika also focused on supporting question answering and retrieval applications, MegaWika 2 is desi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03828","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/2508.03828/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j2jsvKGmFOgNTH3Hcv0XrlcwIeZIVCo3z3JT43SwKACn8r4RDLoPHcyyElMGKwCSpqacLgTWklr+Ko4nli9zAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:53:37.637138Z"},"content_sha256":"24673c0f29ccd692504a94cf8d563958f86b088a7ef5beca97686110ce5de92e","schema_version":"1.0","event_id":"sha256:24673c0f29ccd692504a94cf8d563958f86b088a7ef5beca97686110ce5de92e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IT3SX3IN2QXVYDUCGM7QVEBLIH/bundle.json","state_url":"https://pith.science/pith/IT3SX3IN2QXVYDUCGM7QVEBLIH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IT3SX3IN2QXVYDUCGM7QVEBLIH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T19:53:37Z","links":{"resolver":"https://pith.science/pith/IT3SX3IN2QXVYDUCGM7QVEBLIH","bundle":"https://pith.science/pith/IT3SX3IN2QXVYDUCGM7QVEBLIH/bundle.json","state":"https://pith.science/pith/IT3SX3IN2QXVYDUCGM7QVEBLIH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IT3SX3IN2QXVYDUCGM7QVEBLIH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IT3SX3IN2QXVYDUCGM7QVEBLIH","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":"a637fb582e89aa68951c69f0e584a263f502114558a62ccd8a52e271f863018b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2025-08-05T18:18:17Z","title_canon_sha256":"ee00235369695b24bde59ea623758b37aa8445978ba50ab1239e6b31e33c080a"},"schema_version":"1.0","source":{"id":"2508.03828","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03828","created_at":"2026-07-05T11:49:15Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03828v1","created_at":"2026-07-05T11:49:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03828","created_at":"2026-07-05T11:49:15Z"},{"alias_kind":"pith_short_12","alias_value":"IT3SX3IN2QXV","created_at":"2026-07-05T11:49:15Z"},{"alias_kind":"pith_short_16","alias_value":"IT3SX3IN2QXVYDUC","created_at":"2026-07-05T11:49:15Z"},{"alias_kind":"pith_short_8","alias_value":"IT3SX3IN","created_at":"2026-07-05T11:49:15Z"}],"graph_snapshots":[{"event_id":"sha256:24673c0f29ccd692504a94cf8d563958f86b088a7ef5beca97686110ce5de92e","target":"graph","created_at":"2026-07-05T11:49:15Z","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/2508.03828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce MegaWika 2, a large, multilingual dataset of Wikipedia articles with their citations and scraped web sources; articles are represented in a rich data structure, and scraped source texts are stored inline with precise character offsets of their citations in the article text. MegaWika 2 is a major upgrade from the original MegaWika, spanning six times as many articles and twice as many fully scraped citations. Both MegaWika and MegaWika 2 support report generation research ; whereas MegaWika also focused on supporting question answering and retrieval applications, MegaWika 2 is desi","authors_text":"Benjamin Van Durme, Chandler May, Samuel Barham","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2025-08-05T18:18:17Z","title":"MegaWika 2: A More Comprehensive Multilingual Collection of Articles and their Sources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03828","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":"sha256:61af8361ded39e6015791bcf0aaa0ccbcdff845c923bd613b443d8234eaa6069","target":"record","created_at":"2026-07-05T11:49:15Z","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":"a637fb582e89aa68951c69f0e584a263f502114558a62ccd8a52e271f863018b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2025-08-05T18:18:17Z","title_canon_sha256":"ee00235369695b24bde59ea623758b37aa8445978ba50ab1239e6b31e33c080a"},"schema_version":"1.0","source":{"id":"2508.03828","kind":"arxiv","version":1}},"canonical_sha256":"44f72bed0dd42f5c0e82333f0a902b41f85a0b2f77df905635536b9e0b950d19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44f72bed0dd42f5c0e82333f0a902b41f85a0b2f77df905635536b9e0b950d19","first_computed_at":"2026-07-05T11:49:15.957594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:15.957594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kD0CA0VJRRWajLsgI29+ORWR4PxgAIrQ8iPy5jCw2HW4YpGbRUSLncxE7WoO+Lxti9QhVWT8BbB8UV1p2X2dAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:15.958051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.03828","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61af8361ded39e6015791bcf0aaa0ccbcdff845c923bd613b443d8234eaa6069","sha256:24673c0f29ccd692504a94cf8d563958f86b088a7ef5beca97686110ce5de92e"],"state_sha256":"12f0ffd3c6861fe5e2fc45c3435c35fffc53b080faf6dc8d81425e34d0d1e907"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1sbSahMsUolFBD8WG9jv7WxU/JAgp0eTl7jKzgDRH1s+JFp0dZgXz6P6cZuQmkldt/Cbf1ian9yJMpVP5sAEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T19:53:37.640847Z","bundle_sha256":"ee5dc8a0d23e61bc02d98a08877abe1159360f400439c030dc51a5271f9e1e37"}}