{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QMTCI3JRGZN3EYBCB242EOC6PG","short_pith_number":"pith:QMTCI3JR","schema_version":"1.0","canonical_sha256":"8326246d31365bb260220eb9a2385e7991dc2c0cbfa6a3717e8e8f9165bc79f7","source":{"kind":"arxiv","id":"2305.05432","version":1},"attestation_state":"computed","paper":{"title":"WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Andrea Burns, Bryan A. Plummer, Geoff Brown, Jianmo Ni, Joshua Ainslie, Kate Saenko, Krishna Srinivasan, Mandy Guo","submitted_at":"2023-05-09T13:20:59Z","abstract_excerpt":"Webpages have been a rich resource for language and vision-language tasks. Yet only pieces of webpages are kept: image-caption pairs, long text articles, or raw HTML, never all in one place. Webpage tasks have resultingly received little attention and structured image-text data underused. To study multimodal webpage understanding, we introduce the Wikipedia Webpage 2M (WikiWeb2M) suite; the first to retain the full set of images, text, and structure data available in a page. WikiWeb2M can be used for tasks like page description generation, section summarization, and contextual image captioning"},"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":"2305.05432","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T13:20:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"814a0fc2bb004a9aa37b7abae84d5a4f83d77ad6c68c8272ae4e5a00a75f95d6","abstract_canon_sha256":"b23f6348720551ebe12c2e1a1aa314de012b44c40c56c578acb915ab2b97ffbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:34.700197Z","signature_b64":"iMf/Ra2QKlEKRkqPsbqDV1iasAI9sR6MeE10X3Q4r/lnuQrVx2sCJ/8mcdrPJyvSKh3sJ+1sl4Bc5YE4iVbUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8326246d31365bb260220eb9a2385e7991dc2c0cbfa6a3717e8e8f9165bc79f7","last_reissued_at":"2026-07-05T06:08:34.699839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:34.699839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Andrea Burns, Bryan A. Plummer, Geoff Brown, Jianmo Ni, Joshua Ainslie, Kate Saenko, Krishna Srinivasan, Mandy Guo","submitted_at":"2023-05-09T13:20:59Z","abstract_excerpt":"Webpages have been a rich resource for language and vision-language tasks. Yet only pieces of webpages are kept: image-caption pairs, long text articles, or raw HTML, never all in one place. Webpage tasks have resultingly received little attention and structured image-text data underused. To study multimodal webpage understanding, we introduce the Wikipedia Webpage 2M (WikiWeb2M) suite; the first to retain the full set of images, text, and structure data available in a page. WikiWeb2M can be used for tasks like page description generation, section summarization, and contextual image captioning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05432","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/2305.05432/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":"2305.05432","created_at":"2026-07-05T06:08:34.699902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05432v1","created_at":"2026-07-05T06:08:34.699902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05432","created_at":"2026-07-05T06:08:34.699902+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMTCI3JRGZN3","created_at":"2026-07-05T06:08:34.699902+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMTCI3JRGZN3EYBC","created_at":"2026-07-05T06:08:34.699902+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMTCI3JR","created_at":"2026-07-05T06:08:34.699902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04176","citing_title":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QMTCI3JRGZN3EYBCB242EOC6PG","json":"https://pith.science/pith/QMTCI3JRGZN3EYBCB242EOC6PG.json","graph_json":"https://pith.science/api/pith-number/QMTCI3JRGZN3EYBCB242EOC6PG/graph.json","events_json":"https://pith.science/api/pith-number/QMTCI3JRGZN3EYBCB242EOC6PG/events.json","paper":"https://pith.science/paper/QMTCI3JR"},"agent_actions":{"view_html":"https://pith.science/pith/QMTCI3JRGZN3EYBCB242EOC6PG","download_json":"https://pith.science/pith/QMTCI3JRGZN3EYBCB242EOC6PG.json","view_paper":"https://pith.science/paper/QMTCI3JR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05432&json=true","fetch_graph":"https://pith.science/api/pith-number/QMTCI3JRGZN3EYBCB242EOC6PG/graph.json","fetch_events":"https://pith.science/api/pith-number/QMTCI3JRGZN3EYBCB242EOC6PG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMTCI3JRGZN3EYBCB242EOC6PG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMTCI3JRGZN3EYBCB242EOC6PG/action/storage_attestation","attest_author":"https://pith.science/pith/QMTCI3JRGZN3EYBCB242EOC6PG/action/author_attestation","sign_citation":"https://pith.science/pith/QMTCI3JRGZN3EYBCB242EOC6PG/action/citation_signature","submit_replication":"https://pith.science/pith/QMTCI3JRGZN3EYBCB242EOC6PG/action/replication_record"}},"created_at":"2026-07-05T06:08:34.699902+00:00","updated_at":"2026-07-05T06:08:34.699902+00:00"}