{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HTHHPS3S2AI3BN7SXKFN6TSGCL","short_pith_number":"pith:HTHHPS3S","canonical_record":{"source":{"id":"2403.09029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-03-14T01:40:40Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"399d62ffc0f51c98b135b4d5d23b0239be07e90f16272c7c5cd763b5eea3c3f2","abstract_canon_sha256":"9877dc92f106092978c080a4b015661fbb3cc382f87791842adf5a486e577255"},"schema_version":"1.0"},"canonical_sha256":"3cce77cb72d011b0b7f2ba8adf4e4612dc86eabc85c3bfe9c1e7eef52857c524","source":{"kind":"arxiv","id":"2403.09029","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09029","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09029v1","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09029","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_12","alias_value":"HTHHPS3S2AI3","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_16","alias_value":"HTHHPS3S2AI3BN7S","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_8","alias_value":"HTHHPS3S","created_at":"2026-07-05T07:55:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HTHHPS3S2AI3BN7SXKFN6TSGCL","target":"record","payload":{"canonical_record":{"source":{"id":"2403.09029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-03-14T01:40:40Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"399d62ffc0f51c98b135b4d5d23b0239be07e90f16272c7c5cd763b5eea3c3f2","abstract_canon_sha256":"9877dc92f106092978c080a4b015661fbb3cc382f87791842adf5a486e577255"},"schema_version":"1.0"},"canonical_sha256":"3cce77cb72d011b0b7f2ba8adf4e4612dc86eabc85c3bfe9c1e7eef52857c524","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:50.828124Z","signature_b64":"TP52Fmo7g3Y8PnOiasBasnS9XCme+KTjSL/cZ+AvRoqYy1FnSm2pUnnmFK2fyFVL40vFsj3wXgjwwKBRYme+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cce77cb72d011b0b7f2ba8adf4e4612dc86eabc85c3bfe9c1e7eef52857c524","last_reissued_at":"2026-07-05T07:55:50.827670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:50.827670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.09029","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":"2026-07-05T07:55:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AjUgmshoVHuUPMLmFLzHciPDWvsAmT8Bzp/fZCvug7H5Kp8bZiTG1TkJ/ny7v5w2WHEtn2N7t5CM3GE5tdkqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T15:44:04.810401Z"},"content_sha256":"5b3947b9ae4c5898ecfd55730695568c6eec514efc5fafae5fe537ac7a921da9","schema_version":"1.0","event_id":"sha256:5b3947b9ae4c5898ecfd55730695568c6eec514efc5fafae5fe537ac7a921da9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HTHHPS3S2AI3BN7SXKFN6TSGCL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.HC","authors_text":"Hugo Lauren\\c{c}on, L\\'eo Tronchon, Victor Sanh","submitted_at":"2024-03-14T01:40:40Z","abstract_excerpt":"Using vision-language models (VLMs) in web development presents a promising strategy to increase efficiency and unblock no-code solutions: by providing a screenshot or a sketch of a UI, a VLM could generate the code to reproduce it, for instance in a language like HTML. Despite the advancements in VLMs for various tasks, the specific challenge of converting a screenshot into a corresponding HTML has been minimally explored. We posit that this is mainly due to the absence of a suitable, high-quality dataset. This work introduces WebSight, a synthetic dataset consisting of 2 million pairs of HTM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09029","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/2403.09029/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":"2026-07-05T07:55:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uc5LNpFnmiD37P6DFzU8OR4i6DntEpy9kGFsTPDV2XBqdd7tJSSidhl8R0F49Txnlo49uejUXRDNR45HKJ8cDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T15:44:04.810785Z"},"content_sha256":"ffecc29eb5192a0fe6148c2e873464a9a156fbc38412cad786c61d913ce25d3e","schema_version":"1.0","event_id":"sha256:ffecc29eb5192a0fe6148c2e873464a9a156fbc38412cad786c61d913ce25d3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HTHHPS3S2AI3BN7SXKFN6TSGCL/bundle.json","state_url":"https://pith.science/pith/HTHHPS3S2AI3BN7SXKFN6TSGCL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HTHHPS3S2AI3BN7SXKFN6TSGCL/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":"2026-07-08T15:44:04Z","links":{"resolver":"https://pith.science/pith/HTHHPS3S2AI3BN7SXKFN6TSGCL","bundle":"https://pith.science/pith/HTHHPS3S2AI3BN7SXKFN6TSGCL/bundle.json","state":"https://pith.science/pith/HTHHPS3S2AI3BN7SXKFN6TSGCL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HTHHPS3S2AI3BN7SXKFN6TSGCL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HTHHPS3S2AI3BN7SXKFN6TSGCL","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":"9877dc92f106092978c080a4b015661fbb3cc382f87791842adf5a486e577255","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-03-14T01:40:40Z","title_canon_sha256":"399d62ffc0f51c98b135b4d5d23b0239be07e90f16272c7c5cd763b5eea3c3f2"},"schema_version":"1.0","source":{"id":"2403.09029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09029","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09029v1","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09029","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_12","alias_value":"HTHHPS3S2AI3","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_16","alias_value":"HTHHPS3S2AI3BN7S","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_8","alias_value":"HTHHPS3S","created_at":"2026-07-05T07:55:50Z"}],"graph_snapshots":[{"event_id":"sha256:ffecc29eb5192a0fe6148c2e873464a9a156fbc38412cad786c61d913ce25d3e","target":"graph","created_at":"2026-07-05T07:55:50Z","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/2403.09029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using vision-language models (VLMs) in web development presents a promising strategy to increase efficiency and unblock no-code solutions: by providing a screenshot or a sketch of a UI, a VLM could generate the code to reproduce it, for instance in a language like HTML. Despite the advancements in VLMs for various tasks, the specific challenge of converting a screenshot into a corresponding HTML has been minimally explored. We posit that this is mainly due to the absence of a suitable, high-quality dataset. This work introduces WebSight, a synthetic dataset consisting of 2 million pairs of HTM","authors_text":"Hugo Lauren\\c{c}on, L\\'eo Tronchon, Victor Sanh","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-03-14T01:40:40Z","title":"Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09029","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":"sha256:5b3947b9ae4c5898ecfd55730695568c6eec514efc5fafae5fe537ac7a921da9","target":"record","created_at":"2026-07-05T07:55:50Z","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":"9877dc92f106092978c080a4b015661fbb3cc382f87791842adf5a486e577255","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-03-14T01:40:40Z","title_canon_sha256":"399d62ffc0f51c98b135b4d5d23b0239be07e90f16272c7c5cd763b5eea3c3f2"},"schema_version":"1.0","source":{"id":"2403.09029","kind":"arxiv","version":1}},"canonical_sha256":"3cce77cb72d011b0b7f2ba8adf4e4612dc86eabc85c3bfe9c1e7eef52857c524","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cce77cb72d011b0b7f2ba8adf4e4612dc86eabc85c3bfe9c1e7eef52857c524","first_computed_at":"2026-07-05T07:55:50.827670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:50.827670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TP52Fmo7g3Y8PnOiasBasnS9XCme+KTjSL/cZ+AvRoqYy1FnSm2pUnnmFK2fyFVL40vFsj3wXgjwwKBRYme+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:50.828124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b3947b9ae4c5898ecfd55730695568c6eec514efc5fafae5fe537ac7a921da9","sha256:ffecc29eb5192a0fe6148c2e873464a9a156fbc38412cad786c61d913ce25d3e"],"state_sha256":"a2bebbe36e086d2847ab2de61271f774dab1b84360802c215a5f1344f578c481"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xbz4lpLCL1eYPQaXUaj82A4lQnsjvYQxD6IOHGnd7vzZwuKgmt9afBuCewDM1oB+KBNg4wyelLjmUxMGS3bJCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T15:44:04.812974Z","bundle_sha256":"81419c315ab133016f135eeba717f583fbf7ab14b43802a7634ab8c3a090752e"}}