{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5WYMZP6NEKZOBTPNHPHZANK435","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":"f603a7fccafe8ca883c38ee07fe7f5b2471cd2cc7cc260cdcc925778663fc08a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T08:47:54Z","title_canon_sha256":"2f759624d881467383ef3af01dcac1a173a90b777a1ca9528eb7d2e73b413d5a"},"schema_version":"1.0","source":{"id":"2409.14818","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14818","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14818v2","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14818","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_12","alias_value":"5WYMZP6NEKZO","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_16","alias_value":"5WYMZP6NEKZOBTPN","created_at":"2026-07-05T09:15:14Z"},{"alias_kind":"pith_short_8","alias_value":"5WYMZP6N","created_at":"2026-07-05T09:15:14Z"}],"graph_snapshots":[{"event_id":"sha256:88acc770d784e6b74218c0dc8523f08c3fd5cfe1684edefffc5081d2aad09ceb","target":"graph","created_at":"2026-07-05T09:15:14Z","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/2409.14818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ang Li, Bin Wang, Jianfeng Liu, Jian Luan, Qinzhuo Wu, Shuo Shang, Tao Tan, Weikai Xu, Wei Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T08:47:54Z","title":"MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14818","kind":"arxiv","version":2},"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":"sha256:2304026ae8ff1bdd80365fc40fed6af2695d6de98fe2fdf9773c9f51914242b9","target":"record","created_at":"2026-07-05T09:15:14Z","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":"f603a7fccafe8ca883c38ee07fe7f5b2471cd2cc7cc260cdcc925778663fc08a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T08:47:54Z","title_canon_sha256":"2f759624d881467383ef3af01dcac1a173a90b777a1ca9528eb7d2e73b413d5a"},"schema_version":"1.0","source":{"id":"2409.14818","kind":"arxiv","version":2}},"canonical_sha256":"edb0ccbfcd22b2e0cded3bcf90355cdf40f4eaa0528e847a5da730b91cc2e890","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edb0ccbfcd22b2e0cded3bcf90355cdf40f4eaa0528e847a5da730b91cc2e890","first_computed_at":"2026-07-05T09:15:14.774324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:14.774324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pnkcI0OM4l90GbpFXqzrTnLbiB5nWqDY2itmZiNGMYS+Tm2Zm7QwJB/OFuv72fii1DnJvGEu6hw7CZXSGuP6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:14.774835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14818","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2304026ae8ff1bdd80365fc40fed6af2695d6de98fe2fdf9773c9f51914242b9","sha256:88acc770d784e6b74218c0dc8523f08c3fd5cfe1684edefffc5081d2aad09ceb"],"state_sha256":"e8d87bce56f14739395e6131558982a88a8a5fc7fc5f82e136ec9987ddd17592"}