{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QMTCI3JRGZN3EYBCB242EOC6PG","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":"b23f6348720551ebe12c2e1a1aa314de012b44c40c56c578acb915ab2b97ffbb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T13:20:59Z","title_canon_sha256":"814a0fc2bb004a9aa37b7abae84d5a4f83d77ad6c68c8272ae4e5a00a75f95d6"},"schema_version":"1.0","source":{"id":"2305.05432","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05432","created_at":"2026-07-05T06:08:34Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05432v1","created_at":"2026-07-05T06:08:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05432","created_at":"2026-07-05T06:08:34Z"},{"alias_kind":"pith_short_12","alias_value":"QMTCI3JRGZN3","created_at":"2026-07-05T06:08:34Z"},{"alias_kind":"pith_short_16","alias_value":"QMTCI3JRGZN3EYBC","created_at":"2026-07-05T06:08:34Z"},{"alias_kind":"pith_short_8","alias_value":"QMTCI3JR","created_at":"2026-07-05T06:08:34Z"}],"graph_snapshots":[{"event_id":"sha256:105b50466192daad65a3c956c680e4a744abce39e67c2e08df52965a30352ade","target":"graph","created_at":"2026-07-05T06:08:34Z","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/2305.05432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andrea Burns, Bryan A. Plummer, Geoff Brown, Jianmo Ni, Joshua Ainslie, Kate Saenko, Krishna Srinivasan, Mandy Guo","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T13:20:59Z","title":"WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05432","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":"sha256:7be6ea9693c03d38f49a22f71b2afd3b986677eb17afd10be536b4c161c1da04","target":"record","created_at":"2026-07-05T06:08:34Z","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":"b23f6348720551ebe12c2e1a1aa314de012b44c40c56c578acb915ab2b97ffbb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T13:20:59Z","title_canon_sha256":"814a0fc2bb004a9aa37b7abae84d5a4f83d77ad6c68c8272ae4e5a00a75f95d6"},"schema_version":"1.0","source":{"id":"2305.05432","kind":"arxiv","version":1}},"canonical_sha256":"8326246d31365bb260220eb9a2385e7991dc2c0cbfa6a3717e8e8f9165bc79f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8326246d31365bb260220eb9a2385e7991dc2c0cbfa6a3717e8e8f9165bc79f7","first_computed_at":"2026-07-05T06:08:34.699839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:34.699839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iMf/Ra2QKlEKRkqPsbqDV1iasAI9sR6MeE10X3Q4r/lnuQrVx2sCJ/8mcdrPJyvSKh3sJ+1sl4Bc5YE4iVbUDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:34.700197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.05432","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7be6ea9693c03d38f49a22f71b2afd3b986677eb17afd10be536b4c161c1da04","sha256:105b50466192daad65a3c956c680e4a744abce39e67c2e08df52965a30352ade"],"state_sha256":"faaf9f40a047d06ba0bf5df64159c6f1767e75609ae988abc5954475c7410118"}