{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:23SCZN7DCZYAIGPFGTWFQO7CI2","short_pith_number":"pith:23SCZN7D","canonical_record":{"source":{"id":"2410.22456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T18:44:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e9d3d0c2f0ce08e9135dfae58ba39ed7476ad2d0ceaa1809f51e7253d238b61","abstract_canon_sha256":"5988f78d21e0628ac0e59c13574ca0c2882f18ae4c086bcccc92d906c80245e5"},"schema_version":"1.0"},"canonical_sha256":"d6e42cb7e316700419e534ec583be246b9cdb88992063f7c45d0afc721cf2e98","source":{"kind":"arxiv","id":"2410.22456","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22456","created_at":"2026-07-05T09:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22456v1","created_at":"2026-07-05T09:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22456","created_at":"2026-07-05T09:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"23SCZN7DCZYA","created_at":"2026-07-05T09:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"23SCZN7DCZYAIGPF","created_at":"2026-07-05T09:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"23SCZN7D","created_at":"2026-07-05T09:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:23SCZN7DCZYAIGPFGTWFQO7CI2","target":"record","payload":{"canonical_record":{"source":{"id":"2410.22456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T18:44:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e9d3d0c2f0ce08e9135dfae58ba39ed7476ad2d0ceaa1809f51e7253d238b61","abstract_canon_sha256":"5988f78d21e0628ac0e59c13574ca0c2882f18ae4c086bcccc92d906c80245e5"},"schema_version":"1.0"},"canonical_sha256":"d6e42cb7e316700419e534ec583be246b9cdb88992063f7c45d0afc721cf2e98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:16.758612Z","signature_b64":"YQW/pT92yKjkPIBuzfeE7j8ocsVSN3yyI84YB+BCgGd/JCbrZ9vrFqIEGI3Fts55aVcHafJE+EcEzGx1kjKMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6e42cb7e316700419e534ec583be246b9cdb88992063f7c45d0afc721cf2e98","last_reissued_at":"2026-07-05T09:28:16.758139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:16.758139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.22456","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":"2026-07-05T09:28:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"78m9ZX5kKp34229ozwEcz+Ng5yrK6sGpKP5yUOWCni6LR0ByjFwJpthnWU9vKAroE+KudKkYbPmcDZNSw8LVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:50:13.645659Z"},"content_sha256":"fb2d415cd4d7d0000fdff17e80088f231b51c33fade6a4d8c031ef345a5925c8","schema_version":"1.0","event_id":"sha256:fb2d415cd4d7d0000fdff17e80088f231b51c33fade6a4d8c031ef345a5925c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:23SCZN7DCZYAIGPFGTWFQO7CI2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image2Struct: Benchmarking Structure Extraction for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chi Heem Wong, Josselin Somerville Roberts, Michihiro Yasunaga, Percy Liang, Tony Lee, Yifan Mai","submitted_at":"2024-10-29T18:44:59Z","abstract_excerpt":"We introduce Image2Struct, a benchmark to evaluate vision-language models (VLMs) on extracting structure from images. Our benchmark 1) captures real-world use cases, 2) is fully automatic and does not require human judgment, and 3) is based on a renewable stream of fresh data. In Image2Struct, VLMs are prompted to generate the underlying structure (e.g., LaTeX code or HTML) from an input image (e.g., webpage screenshot). The structure is then rendered to produce an output image (e.g., rendered webpage), which is compared against the input image to produce a similarity score. This round-trip ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22456","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/2410.22456/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":"2026-07-05T09:28:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4bfnXUOGn1x+VV/Sj7jhNIxWtgqLdpPFTbcEbxHgyY0mK/ypCrJol20dEX1/mPPkDMM/OxAgEQeZf6pc6fAyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:50:13.646482Z"},"content_sha256":"3d3f6a32c1da32a30e24b393a97b1dd2663bd30d31bc2416a14fd8c390583741","schema_version":"1.0","event_id":"sha256:3d3f6a32c1da32a30e24b393a97b1dd2663bd30d31bc2416a14fd8c390583741"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/23SCZN7DCZYAIGPFGTWFQO7CI2/bundle.json","state_url":"https://pith.science/pith/23SCZN7DCZYAIGPFGTWFQO7CI2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/23SCZN7DCZYAIGPFGTWFQO7CI2/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":"2026-08-05T18:50:13Z","links":{"resolver":"https://pith.science/pith/23SCZN7DCZYAIGPFGTWFQO7CI2","bundle":"https://pith.science/pith/23SCZN7DCZYAIGPFGTWFQO7CI2/bundle.json","state":"https://pith.science/pith/23SCZN7DCZYAIGPFGTWFQO7CI2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/23SCZN7DCZYAIGPFGTWFQO7CI2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:23SCZN7DCZYAIGPFGTWFQO7CI2","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":"5988f78d21e0628ac0e59c13574ca0c2882f18ae4c086bcccc92d906c80245e5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T18:44:59Z","title_canon_sha256":"0e9d3d0c2f0ce08e9135dfae58ba39ed7476ad2d0ceaa1809f51e7253d238b61"},"schema_version":"1.0","source":{"id":"2410.22456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22456","created_at":"2026-07-05T09:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22456v1","created_at":"2026-07-05T09:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22456","created_at":"2026-07-05T09:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"23SCZN7DCZYA","created_at":"2026-07-05T09:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"23SCZN7DCZYAIGPF","created_at":"2026-07-05T09:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"23SCZN7D","created_at":"2026-07-05T09:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:3d3f6a32c1da32a30e24b393a97b1dd2663bd30d31bc2416a14fd8c390583741","target":"graph","created_at":"2026-07-05T09:28:16Z","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/2410.22456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Image2Struct, a benchmark to evaluate vision-language models (VLMs) on extracting structure from images. Our benchmark 1) captures real-world use cases, 2) is fully automatic and does not require human judgment, and 3) is based on a renewable stream of fresh data. In Image2Struct, VLMs are prompted to generate the underlying structure (e.g., LaTeX code or HTML) from an input image (e.g., webpage screenshot). The structure is then rendered to produce an output image (e.g., rendered webpage), which is compared against the input image to produce a similarity score. This round-trip ev","authors_text":"Chi Heem Wong, Josselin Somerville Roberts, Michihiro Yasunaga, Percy Liang, Tony Lee, Yifan Mai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T18:44:59Z","title":"Image2Struct: Benchmarking Structure Extraction for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22456","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:fb2d415cd4d7d0000fdff17e80088f231b51c33fade6a4d8c031ef345a5925c8","target":"record","created_at":"2026-07-05T09:28:16Z","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":"5988f78d21e0628ac0e59c13574ca0c2882f18ae4c086bcccc92d906c80245e5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T18:44:59Z","title_canon_sha256":"0e9d3d0c2f0ce08e9135dfae58ba39ed7476ad2d0ceaa1809f51e7253d238b61"},"schema_version":"1.0","source":{"id":"2410.22456","kind":"arxiv","version":1}},"canonical_sha256":"d6e42cb7e316700419e534ec583be246b9cdb88992063f7c45d0afc721cf2e98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6e42cb7e316700419e534ec583be246b9cdb88992063f7c45d0afc721cf2e98","first_computed_at":"2026-07-05T09:28:16.758139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:16.758139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YQW/pT92yKjkPIBuzfeE7j8ocsVSN3yyI84YB+BCgGd/JCbrZ9vrFqIEGI3Fts55aVcHafJE+EcEzGx1kjKMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:16.758612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb2d415cd4d7d0000fdff17e80088f231b51c33fade6a4d8c031ef345a5925c8","sha256:3d3f6a32c1da32a30e24b393a97b1dd2663bd30d31bc2416a14fd8c390583741"],"state_sha256":"72fe98a42962e4048a8a03fb4dc62d05a5f47ecc46db83e0e7cefe3c40fd4f9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"okxx9YqUMtYc4qBU4b12qov2M1IwmLXhDaVIz/z9u+W2Zp9LTDDTtvGBqFaGZjMRONGICfYiW/9Lsq2pVjrTBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:50:13.657397Z","bundle_sha256":"21e5307797d67b4d82a3a5938acef00ec17f20b99aa7b79854e5987d6c041509"}}