{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U6GPLRI4XIZPVA4CJINHGEWNTP","short_pith_number":"pith:U6GPLRI4","schema_version":"1.0","canonical_sha256":"a78cf5c51cba32fa83824a1a7312cd9bd1f5f29fb0c8f9342a775ddd8d03d7c1","source":{"kind":"arxiv","id":"2411.03477","version":2},"attestation_state":"computed","paper":{"title":"CrowdGenUI: Aligning LLM-Based UI Generation with Crowdsourced User Preferences","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Chang Xiao, Misha Sra, Yimeng Liu","submitted_at":"2024-11-05T20:01:20Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable potential across various design domains, including user interface (UI) generation. However, current LLMs for UI generation tend to offer generic solutions that lack a nuanced understanding of task context and user preferences. We present CrowdGenUI, a framework that enhances LLM-based UI generation with crowdsourced user preferences. This framework addresses the limitations by guiding LLM reasoning with real user preferences, enabling the generation of UI widgets that reflect user needs and task-specific requirements. We evaluate our fr"},"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":"2411.03477","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2024-11-05T20:01:20Z","cross_cats_sorted":[],"title_canon_sha256":"febb458f56b18073079a118a4371c8b08967ec0332e1b4bd99b1fbe3e97b53a4","abstract_canon_sha256":"6cd9b38a6e7b8127546b5da0f70afad69cc39fe855b72b228a68a0416bef9acf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:27.982015Z","signature_b64":"zCq2PUegyP2JFmr6rI16LWzZWvySQ9JZojWyn0yQ0d3fLlCdJ9f/xgWkeVcpTJll29ai+nYd/ET/o43QIK8RBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a78cf5c51cba32fa83824a1a7312cd9bd1f5f29fb0c8f9342a775ddd8d03d7c1","last_reissued_at":"2026-07-05T10:51:27.981512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:27.981512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrowdGenUI: Aligning LLM-Based UI Generation with Crowdsourced User Preferences","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Chang Xiao, Misha Sra, Yimeng Liu","submitted_at":"2024-11-05T20:01:20Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable potential across various design domains, including user interface (UI) generation. However, current LLMs for UI generation tend to offer generic solutions that lack a nuanced understanding of task context and user preferences. We present CrowdGenUI, a framework that enhances LLM-based UI generation with crowdsourced user preferences. This framework addresses the limitations by guiding LLM reasoning with real user preferences, enabling the generation of UI widgets that reflect user needs and task-specific requirements. We evaluate our fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03477","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/2411.03477/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":"2411.03477","created_at":"2026-07-05T10:51:27.981573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03477v2","created_at":"2026-07-05T10:51:27.981573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03477","created_at":"2026-07-05T10:51:27.981573+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6GPLRI4XIZP","created_at":"2026-07-05T10:51:27.981573+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6GPLRI4XIZPVA4C","created_at":"2026-07-05T10:51:27.981573+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6GPLRI4","created_at":"2026-07-05T10:51:27.981573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.23379","citing_title":"TaskLens: Generating Task-Conditioned Scaffolded Interfaces for Learning Professional Creative Software","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6GPLRI4XIZPVA4CJINHGEWNTP","json":"https://pith.science/pith/U6GPLRI4XIZPVA4CJINHGEWNTP.json","graph_json":"https://pith.science/api/pith-number/U6GPLRI4XIZPVA4CJINHGEWNTP/graph.json","events_json":"https://pith.science/api/pith-number/U6GPLRI4XIZPVA4CJINHGEWNTP/events.json","paper":"https://pith.science/paper/U6GPLRI4"},"agent_actions":{"view_html":"https://pith.science/pith/U6GPLRI4XIZPVA4CJINHGEWNTP","download_json":"https://pith.science/pith/U6GPLRI4XIZPVA4CJINHGEWNTP.json","view_paper":"https://pith.science/paper/U6GPLRI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03477&json=true","fetch_graph":"https://pith.science/api/pith-number/U6GPLRI4XIZPVA4CJINHGEWNTP/graph.json","fetch_events":"https://pith.science/api/pith-number/U6GPLRI4XIZPVA4CJINHGEWNTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6GPLRI4XIZPVA4CJINHGEWNTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6GPLRI4XIZPVA4CJINHGEWNTP/action/storage_attestation","attest_author":"https://pith.science/pith/U6GPLRI4XIZPVA4CJINHGEWNTP/action/author_attestation","sign_citation":"https://pith.science/pith/U6GPLRI4XIZPVA4CJINHGEWNTP/action/citation_signature","submit_replication":"https://pith.science/pith/U6GPLRI4XIZPVA4CJINHGEWNTP/action/replication_record"}},"created_at":"2026-07-05T10:51:27.981573+00:00","updated_at":"2026-07-05T10:51:27.981573+00:00"}