{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5WYMZP6NEKZOBTPNHPHZANK435","short_pith_number":"pith:5WYMZP6N","schema_version":"1.0","canonical_sha256":"edb0ccbfcd22b2e0cded3bcf90355cdf40f4eaa0528e847a5da730b91cc2e890","source":{"kind":"arxiv","id":"2409.14818","version":2},"attestation_state":"computed","paper":{"title":"MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ang Li, Bin Wang, Jianfeng Liu, Jian Luan, Qinzhuo Wu, Shuo Shang, Tao Tan, Weikai Xu, Wei Liu","submitted_at":"2024-09-23T08:47:54Z","abstract_excerpt":"Recently, mobile AI agents based on VLMs have been gaining increasing attention. These works typically utilize VLM as a foundation, fine-tuning it with instruction-based mobile datasets. However, these VLMs are typically pre-trained on general-domain data, which often results in a lack of fundamental capabilities specific to the mobile domain. Therefore, they may struggle to recognize specific UI elements and understand intra-UI fine-grained information. In addition, the current fine-tuning task focuses on interacting with the most relevant element for the given instruction. These fine-tuned V"},"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":"2409.14818","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T08:47:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f759624d881467383ef3af01dcac1a173a90b777a1ca9528eb7d2e73b413d5a","abstract_canon_sha256":"f603a7fccafe8ca883c38ee07fe7f5b2471cd2cc7cc260cdcc925778663fc08a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:14.774835Z","signature_b64":"pnkcI0OM4l90GbpFXqzrTnLbiB5nWqDY2itmZiNGMYS+Tm2Zm7QwJB/OFuv72fii1DnJvGEu6hw7CZXSGuP6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edb0ccbfcd22b2e0cded3bcf90355cdf40f4eaa0528e847a5da730b91cc2e890","last_reissued_at":"2026-07-05T09:15:14.774324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:14.774324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ang Li, Bin Wang, Jianfeng Liu, Jian Luan, Qinzhuo Wu, Shuo Shang, Tao Tan, Weikai Xu, Wei Liu","submitted_at":"2024-09-23T08:47:54Z","abstract_excerpt":"Recently, mobile AI agents based on VLMs have been gaining increasing attention. These works typically utilize VLM as a foundation, fine-tuning it with instruction-based mobile datasets. However, these VLMs are typically pre-trained on general-domain data, which often results in a lack of fundamental capabilities specific to the mobile domain. Therefore, they may struggle to recognize specific UI elements and understand intra-UI fine-grained information. In addition, the current fine-tuning task focuses on interacting with the most relevant element for the given instruction. These fine-tuned V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14818","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/2409.14818/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":"2409.14818","created_at":"2026-07-05T09:15:14.774378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14818v2","created_at":"2026-07-05T09:15:14.774378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14818","created_at":"2026-07-05T09:15:14.774378+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WYMZP6NEKZO","created_at":"2026-07-05T09:15:14.774378+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WYMZP6NEKZOBTPN","created_at":"2026-07-05T09:15:14.774378+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WYMZP6N","created_at":"2026-07-05T09:15:14.774378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.12634","citing_title":"MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04579","citing_title":"Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WYMZP6NEKZOBTPNHPHZANK435","json":"https://pith.science/pith/5WYMZP6NEKZOBTPNHPHZANK435.json","graph_json":"https://pith.science/api/pith-number/5WYMZP6NEKZOBTPNHPHZANK435/graph.json","events_json":"https://pith.science/api/pith-number/5WYMZP6NEKZOBTPNHPHZANK435/events.json","paper":"https://pith.science/paper/5WYMZP6N"},"agent_actions":{"view_html":"https://pith.science/pith/5WYMZP6NEKZOBTPNHPHZANK435","download_json":"https://pith.science/pith/5WYMZP6NEKZOBTPNHPHZANK435.json","view_paper":"https://pith.science/paper/5WYMZP6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14818&json=true","fetch_graph":"https://pith.science/api/pith-number/5WYMZP6NEKZOBTPNHPHZANK435/graph.json","fetch_events":"https://pith.science/api/pith-number/5WYMZP6NEKZOBTPNHPHZANK435/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WYMZP6NEKZOBTPNHPHZANK435/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WYMZP6NEKZOBTPNHPHZANK435/action/storage_attestation","attest_author":"https://pith.science/pith/5WYMZP6NEKZOBTPNHPHZANK435/action/author_attestation","sign_citation":"https://pith.science/pith/5WYMZP6NEKZOBTPNHPHZANK435/action/citation_signature","submit_replication":"https://pith.science/pith/5WYMZP6NEKZOBTPNHPHZANK435/action/replication_record"}},"created_at":"2026-07-05T09:15:14.774378+00:00","updated_at":"2026-07-05T09:15:14.774378+00:00"}