{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ETIEBWJ5OW7JRVDNCC2QTKWLLQ","short_pith_number":"pith:ETIEBWJ5","canonical_record":{"source":{"id":"2305.03668","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-05T16:38:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a59a84d24235e29ebd3a0959af73f4aad5c99997e74cc2839bdf1fa78792ae01","abstract_canon_sha256":"ff64622800ce52a1b5c76cbb7c934d1aeeb6ad4054bae0fd8e633f5968351e46"},"schema_version":"1.0"},"canonical_sha256":"24d040d93d75be98d46d10b509aacb5c3440877288e207203bff62527313fc60","source":{"kind":"arxiv","id":"2305.03668","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03668","created_at":"2026-07-05T07:02:49Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03668v2","created_at":"2026-07-05T07:02:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03668","created_at":"2026-07-05T07:02:49Z"},{"alias_kind":"pith_short_12","alias_value":"ETIEBWJ5OW7J","created_at":"2026-07-05T07:02:49Z"},{"alias_kind":"pith_short_16","alias_value":"ETIEBWJ5OW7JRVDN","created_at":"2026-07-05T07:02:49Z"},{"alias_kind":"pith_short_8","alias_value":"ETIEBWJ5","created_at":"2026-07-05T07:02:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ETIEBWJ5OW7JRVDNCC2QTKWLLQ","target":"record","payload":{"canonical_record":{"source":{"id":"2305.03668","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-05T16:38:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a59a84d24235e29ebd3a0959af73f4aad5c99997e74cc2839bdf1fa78792ae01","abstract_canon_sha256":"ff64622800ce52a1b5c76cbb7c934d1aeeb6ad4054bae0fd8e633f5968351e46"},"schema_version":"1.0"},"canonical_sha256":"24d040d93d75be98d46d10b509aacb5c3440877288e207203bff62527313fc60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:49.699590Z","signature_b64":"LUALDd0pxlKe63spVRSWad65UT5lMXzCcWh/42Bs8rQ7TTjXCr0r25Veoqk+pfN5yznl/qET4jrhu2sgDBtrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24d040d93d75be98d46d10b509aacb5c3440877288e207203bff62527313fc60","last_reissued_at":"2026-07-05T07:02:49.699043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:49.699043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.03668","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:02:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fQMzfMXjS/qhALgLrZVkRhnpFkhuV124eQ+Hgopc7QAQgluiTbrrw6qTxCuvAzJdLK74KmIwTRgaxZvc0y16Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:41:40.826940Z"},"content_sha256":"de2efee6c8342306f366ae6b3c43c2352578ed334f477d776668bf381332d71e","schema_version":"1.0","event_id":"sha256:de2efee6c8342306f366ae6b3c43c2352578ed334f477d776668bf381332d71e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ETIEBWJ5OW7JRVDNCC2QTKWLLQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding","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":"2023-05-05T16:38:05Z","abstract_excerpt":"Webpages have been a rich, scalable resource for vision-language and language only tasks. Yet only pieces of webpages are kept in existing datasets: 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 left underused. To study multimodal webpage understanding, we introduce the Wikipedia Webpage suite (WikiWeb2M) containing 2M pages with all of the associated image, text, and structure data. We verify its utility on three generative tasks: page description generation, section summari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03668","kind":"arxiv","version":2},"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/2305.03668/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":"2026-07-05T07:02:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A020+fBuzoRXp5suVU/bMe4R0lEDCJm1lW/AxYLqJRYF/s2WhEVbccFr2awP9Uy5fNFEaz/DOXqplpO8JKtfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:41:40.827464Z"},"content_sha256":"a0da04f46cdbec12bc146c7deb6348a22a56f3b5814c60cb1a75aa92ac23c1a5","schema_version":"1.0","event_id":"sha256:a0da04f46cdbec12bc146c7deb6348a22a56f3b5814c60cb1a75aa92ac23c1a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ETIEBWJ5OW7JRVDNCC2QTKWLLQ/bundle.json","state_url":"https://pith.science/pith/ETIEBWJ5OW7JRVDNCC2QTKWLLQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ETIEBWJ5OW7JRVDNCC2QTKWLLQ/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":"2026-08-04T12:41:40Z","links":{"resolver":"https://pith.science/pith/ETIEBWJ5OW7JRVDNCC2QTKWLLQ","bundle":"https://pith.science/pith/ETIEBWJ5OW7JRVDNCC2QTKWLLQ/bundle.json","state":"https://pith.science/pith/ETIEBWJ5OW7JRVDNCC2QTKWLLQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ETIEBWJ5OW7JRVDNCC2QTKWLLQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ETIEBWJ5OW7JRVDNCC2QTKWLLQ","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":"ff64622800ce52a1b5c76cbb7c934d1aeeb6ad4054bae0fd8e633f5968351e46","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-05T16:38:05Z","title_canon_sha256":"a59a84d24235e29ebd3a0959af73f4aad5c99997e74cc2839bdf1fa78792ae01"},"schema_version":"1.0","source":{"id":"2305.03668","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03668","created_at":"2026-07-05T07:02:49Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03668v2","created_at":"2026-07-05T07:02:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03668","created_at":"2026-07-05T07:02:49Z"},{"alias_kind":"pith_short_12","alias_value":"ETIEBWJ5OW7J","created_at":"2026-07-05T07:02:49Z"},{"alias_kind":"pith_short_16","alias_value":"ETIEBWJ5OW7JRVDN","created_at":"2026-07-05T07:02:49Z"},{"alias_kind":"pith_short_8","alias_value":"ETIEBWJ5","created_at":"2026-07-05T07:02:49Z"}],"graph_snapshots":[{"event_id":"sha256:a0da04f46cdbec12bc146c7deb6348a22a56f3b5814c60cb1a75aa92ac23c1a5","target":"graph","created_at":"2026-07-05T07:02:49Z","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/2305.03668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Webpages have been a rich, scalable resource for vision-language and language only tasks. Yet only pieces of webpages are kept in existing datasets: 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 left underused. To study multimodal webpage understanding, we introduce the Wikipedia Webpage suite (WikiWeb2M) containing 2M pages with all of the associated image, text, and structure data. We verify its utility on three generative tasks: page description generation, section summari","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":"2023-05-05T16:38:05Z","title":"A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03668","kind":"arxiv","version":2},"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:de2efee6c8342306f366ae6b3c43c2352578ed334f477d776668bf381332d71e","target":"record","created_at":"2026-07-05T07:02:49Z","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":"ff64622800ce52a1b5c76cbb7c934d1aeeb6ad4054bae0fd8e633f5968351e46","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-05T16:38:05Z","title_canon_sha256":"a59a84d24235e29ebd3a0959af73f4aad5c99997e74cc2839bdf1fa78792ae01"},"schema_version":"1.0","source":{"id":"2305.03668","kind":"arxiv","version":2}},"canonical_sha256":"24d040d93d75be98d46d10b509aacb5c3440877288e207203bff62527313fc60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24d040d93d75be98d46d10b509aacb5c3440877288e207203bff62527313fc60","first_computed_at":"2026-07-05T07:02:49.699043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:49.699043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LUALDd0pxlKe63spVRSWad65UT5lMXzCcWh/42Bs8rQ7TTjXCr0r25Veoqk+pfN5yznl/qET4jrhu2sgDBtrDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:49.699590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03668","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de2efee6c8342306f366ae6b3c43c2352578ed334f477d776668bf381332d71e","sha256:a0da04f46cdbec12bc146c7deb6348a22a56f3b5814c60cb1a75aa92ac23c1a5"],"state_sha256":"ef43ce9ed4fb3d5af003f6c434e55937909d39195dd87da9f65c2814af109521"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hEugQhVJdhOt68uHqayAjwUPB7W0Ro2p5wdVTbylMQMePTDk7jMzhdKvsXhKYb3beK50EtE1x3s1FUreP4mRCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:41:40.831166Z","bundle_sha256":"2a0bec494b898bf14762bd54450c759c52f2eae4c8a0c3b334689faf7167606a"}}