{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LS7RRIET76LGPGBT4GQYJANRR4","short_pith_number":"pith:LS7RRIET","schema_version":"1.0","canonical_sha256":"5cbf18a093ff96679833e1a18481b18f23c0ea9310a5237d9ac96dc1ae9d4667","source":{"kind":"arxiv","id":"2406.07822","version":2},"attestation_state":"computed","paper":{"title":"Tell Me What's Next: Textual Foresight for Generic UI Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrea Burns, Bryan A. Plummer, Kate Saenko","submitted_at":"2024-06-12T02:43:19Z","abstract_excerpt":"Mobile app user interfaces (UIs) are rich with action, text, structure, and image content that can be utilized to learn generic UI representations for tasks like automating user commands, summarizing content, and evaluating the accessibility of user interfaces. Prior work has learned strong visual representations with local or global captioning losses, but fails to retain both granularities. To combat this, we propose Textual Foresight, a novel pretraining objective for learning UI screen representations. Textual Foresight generates global text descriptions of future UI states given a current "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.07822","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T02:43:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cbcf2213fbb49e505321d1f7995fdb5be441742a8bf595863693f021972de5e0","abstract_canon_sha256":"87e7cf4c7dd92645511b9e586f4b1c39a74064643bc80956247a893ffec0c0ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:23.070340Z","signature_b64":"Hf3UgClJFDca69sOGktffgF7YeCakFc1/xpQs2yQFX7qFKYaFpEbd1G1ZcxX6GaTxSfZ80IU2MGZlcZNkRyCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cbf18a093ff96679833e1a18481b18f23c0ea9310a5237d9ac96dc1ae9d4667","last_reissued_at":"2026-07-05T08:53:23.069892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:23.069892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tell Me What's Next: Textual Foresight for Generic UI Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Andrea Burns, Bryan A. Plummer, Kate Saenko","submitted_at":"2024-06-12T02:43:19Z","abstract_excerpt":"Mobile app user interfaces (UIs) are rich with action, text, structure, and image content that can be utilized to learn generic UI representations for tasks like automating user commands, summarizing content, and evaluating the accessibility of user interfaces. Prior work has learned strong visual representations with local or global captioning losses, but fails to retain both granularities. To combat this, we propose Textual Foresight, a novel pretraining objective for learning UI screen representations. Textual Foresight generates global text descriptions of future UI states given a current "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07822","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/2406.07822/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.07822","created_at":"2026-07-05T08:53:23.069948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07822v2","created_at":"2026-07-05T08:53:23.069948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07822","created_at":"2026-07-05T08:53:23.069948+00:00"},{"alias_kind":"pith_short_12","alias_value":"LS7RRIET76LG","created_at":"2026-07-05T08:53:23.069948+00:00"},{"alias_kind":"pith_short_16","alias_value":"LS7RRIET76LGPGBT","created_at":"2026-07-05T08:53:23.069948+00:00"},{"alias_kind":"pith_short_8","alias_value":"LS7RRIET","created_at":"2026-07-05T08:53:23.069948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LS7RRIET76LGPGBT4GQYJANRR4","json":"https://pith.science/pith/LS7RRIET76LGPGBT4GQYJANRR4.json","graph_json":"https://pith.science/api/pith-number/LS7RRIET76LGPGBT4GQYJANRR4/graph.json","events_json":"https://pith.science/api/pith-number/LS7RRIET76LGPGBT4GQYJANRR4/events.json","paper":"https://pith.science/paper/LS7RRIET"},"agent_actions":{"view_html":"https://pith.science/pith/LS7RRIET76LGPGBT4GQYJANRR4","download_json":"https://pith.science/pith/LS7RRIET76LGPGBT4GQYJANRR4.json","view_paper":"https://pith.science/paper/LS7RRIET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07822&json=true","fetch_graph":"https://pith.science/api/pith-number/LS7RRIET76LGPGBT4GQYJANRR4/graph.json","fetch_events":"https://pith.science/api/pith-number/LS7RRIET76LGPGBT4GQYJANRR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LS7RRIET76LGPGBT4GQYJANRR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LS7RRIET76LGPGBT4GQYJANRR4/action/storage_attestation","attest_author":"https://pith.science/pith/LS7RRIET76LGPGBT4GQYJANRR4/action/author_attestation","sign_citation":"https://pith.science/pith/LS7RRIET76LGPGBT4GQYJANRR4/action/citation_signature","submit_replication":"https://pith.science/pith/LS7RRIET76LGPGBT4GQYJANRR4/action/replication_record"}},"created_at":"2026-07-05T08:53:23.069948+00:00","updated_at":"2026-07-05T08:53:23.069948+00:00"}