{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XNFEBYDP3WWB2GU76YAQ4XRLUN","short_pith_number":"pith:XNFEBYDP","schema_version":"1.0","canonical_sha256":"bb4a40e06fddac1d1a9ff6010e5e2ba3767d3be6fa355155b092944b0025fd2d","source":{"kind":"arxiv","id":"2505.05895","version":3},"attestation_state":"computed","paper":{"title":"Leveraging Vision-Language Models for Visual Grounding and Analysis of Automotive UI","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benjamin Raphael Ernhofer, Daniil Prokhorov, Dominik Bollmann, Jannica Langner","submitted_at":"2025-05-09T09:01:52Z","abstract_excerpt":"Modern automotive infotainment systems necessitate intelligent and adaptive solutions to manage frequent User Interface (UI) updates and diverse design variations. This work introduces a vision-language framework to facilitate the understanding of and interaction with automotive UIs, enabling seamless adaptation across different UI designs. To support research in this field, AutomotiveUI-Bench-4K, an open-source dataset comprising 998 images with 4,208 annotations, is also released. Additionally, a data pipeline for generating training data is presented. A Molmo-7B-based model is fine-tuned us"},"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":"2505.05895","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-09T09:01:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f00a9323e296767313d4dc0527f7bc7f35f7dd411cff494b0862ca2bb08834e0","abstract_canon_sha256":"a1091403bad7751a9e200a3ee8d5feaeae9284c2fe2acbc81764b1a6c1560c92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:49.057251Z","signature_b64":"1lJyc6+/NMG08WzHFH4rhD2in2OrW4Q8OkJFwscy1j4m+sI4ZQFMlEIw93Zd97rhJFPK4kD1mj5K/8LMoPlQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb4a40e06fddac1d1a9ff6010e5e2ba3767d3be6fa355155b092944b0025fd2d","last_reissued_at":"2026-07-05T11:48:49.056630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:49.056630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Vision-Language Models for Visual Grounding and Analysis of Automotive UI","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benjamin Raphael Ernhofer, Daniil Prokhorov, Dominik Bollmann, Jannica Langner","submitted_at":"2025-05-09T09:01:52Z","abstract_excerpt":"Modern automotive infotainment systems necessitate intelligent and adaptive solutions to manage frequent User Interface (UI) updates and diverse design variations. This work introduces a vision-language framework to facilitate the understanding of and interaction with automotive UIs, enabling seamless adaptation across different UI designs. To support research in this field, AutomotiveUI-Bench-4K, an open-source dataset comprising 998 images with 4,208 annotations, is also released. Additionally, a data pipeline for generating training data is presented. A Molmo-7B-based model is fine-tuned us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05895","kind":"arxiv","version":3},"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/2505.05895/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":"2505.05895","created_at":"2026-07-05T11:48:49.056699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05895v3","created_at":"2026-07-05T11:48:49.056699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05895","created_at":"2026-07-05T11:48:49.056699+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNFEBYDP3WWB","created_at":"2026-07-05T11:48:49.056699+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNFEBYDP3WWB2GU7","created_at":"2026-07-05T11:48:49.056699+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNFEBYDP","created_at":"2026-07-05T11:48:49.056699+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/XNFEBYDP3WWB2GU76YAQ4XRLUN","json":"https://pith.science/pith/XNFEBYDP3WWB2GU76YAQ4XRLUN.json","graph_json":"https://pith.science/api/pith-number/XNFEBYDP3WWB2GU76YAQ4XRLUN/graph.json","events_json":"https://pith.science/api/pith-number/XNFEBYDP3WWB2GU76YAQ4XRLUN/events.json","paper":"https://pith.science/paper/XNFEBYDP"},"agent_actions":{"view_html":"https://pith.science/pith/XNFEBYDP3WWB2GU76YAQ4XRLUN","download_json":"https://pith.science/pith/XNFEBYDP3WWB2GU76YAQ4XRLUN.json","view_paper":"https://pith.science/paper/XNFEBYDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05895&json=true","fetch_graph":"https://pith.science/api/pith-number/XNFEBYDP3WWB2GU76YAQ4XRLUN/graph.json","fetch_events":"https://pith.science/api/pith-number/XNFEBYDP3WWB2GU76YAQ4XRLUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNFEBYDP3WWB2GU76YAQ4XRLUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNFEBYDP3WWB2GU76YAQ4XRLUN/action/storage_attestation","attest_author":"https://pith.science/pith/XNFEBYDP3WWB2GU76YAQ4XRLUN/action/author_attestation","sign_citation":"https://pith.science/pith/XNFEBYDP3WWB2GU76YAQ4XRLUN/action/citation_signature","submit_replication":"https://pith.science/pith/XNFEBYDP3WWB2GU76YAQ4XRLUN/action/replication_record"}},"created_at":"2026-07-05T11:48:49.056699+00:00","updated_at":"2026-07-05T11:48:49.056699+00:00"}