{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H2VE2L3UTFKZLHWE6IIFECNCZ2","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":"837090dd69f3bbad6c7ecb0bca8cb36ea0f17894fc5b8ce504222df832514db4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T06:42:33Z","title_canon_sha256":"2cb658b3a797dc52a8ebbfe8bf578e89d912d240e0df51df57fb3346053dc912"},"schema_version":"1.0","source":{"id":"2402.04615","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04615","created_at":"2026-07-05T08:40:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04615v3","created_at":"2026-07-05T08:40:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04615","created_at":"2026-07-05T08:40:13Z"},{"alias_kind":"pith_short_12","alias_value":"H2VE2L3UTFKZ","created_at":"2026-07-05T08:40:13Z"},{"alias_kind":"pith_short_16","alias_value":"H2VE2L3UTFKZLHWE","created_at":"2026-07-05T08:40:13Z"},{"alias_kind":"pith_short_8","alias_value":"H2VE2L3U","created_at":"2026-07-05T08:40:13Z"}],"graph_snapshots":[{"event_id":"sha256:92dc4e869198e816946ec01766fc1a133f08923ea709eee3e80b82d5cf58a8b9","target":"graph","created_at":"2026-07-05T08:40:13Z","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/2402.04615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Screen user interfaces (UIs) and infographics, sharing similar visual language and design principles, play important roles in human communication and human-machine interaction. We introduce ScreenAI, a vision-language model that specializes in UI and infographics understanding. Our model improves upon the PaLI architecture with the flexible patching strategy of pix2struct and is trained on a unique mixture of datasets. At the heart of this mixture is a novel screen annotation task in which the model has to identify the type and location of UI elements. We use these text annotations to describe","authors_text":"Abhanshu Sharma, Fedir Zubach, Gilles Baechler, Hassan Mansoor, Jason Lin, Jindong Chen, Maria Wang, Srinivas Sunkara, Victor C\\u{a}rbune, Vincent Etter","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T06:42:33Z","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04615","kind":"arxiv","version":3},"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":"sha256:608575a107c779ba0ff9a97acf6e9ea5af6d9968b769334195778260a8808262","target":"record","created_at":"2026-07-05T08:40:13Z","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":"837090dd69f3bbad6c7ecb0bca8cb36ea0f17894fc5b8ce504222df832514db4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T06:42:33Z","title_canon_sha256":"2cb658b3a797dc52a8ebbfe8bf578e89d912d240e0df51df57fb3346053dc912"},"schema_version":"1.0","source":{"id":"2402.04615","kind":"arxiv","version":3}},"canonical_sha256":"3eaa4d2f749955959ec4f2105209a2ce8559e8efa4203329b0a9afeba9d4404c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3eaa4d2f749955959ec4f2105209a2ce8559e8efa4203329b0a9afeba9d4404c","first_computed_at":"2026-07-05T08:40:13.160899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:13.160899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6UVenwscT1ZNw6lUgVdnbPxAGexO8dXf2Nkf/jm97HeqIWPlcR+boDJs3JrJuvUMIJi4EQVTP+4H2JSxQqf0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:13.161553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04615","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:608575a107c779ba0ff9a97acf6e9ea5af6d9968b769334195778260a8808262","sha256:92dc4e869198e816946ec01766fc1a133f08923ea709eee3e80b82d5cf58a8b9"],"state_sha256":"58fe58f3b3d15e5b4350f709cc719fc8a61a4b5a93599f4f3a85779fef83d599"}