{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YNHEUHXW5HDLWCZKFEOTXYK6BX","short_pith_number":"pith:YNHEUHXW","schema_version":"1.0","canonical_sha256":"c34e4a1ef6e9c6bb0b2a291d3be15e0df89a136abf9e05687070fc3103684625","source":{"kind":"arxiv","id":"2502.17110","version":3},"attestation_state":"computed","paper":{"title":"Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Haiyang Xu, Jitao Sang, Ji Zhang, Junyang Wang, Ming Yan, Xi Zhang","submitted_at":"2025-02-24T12:51:23Z","abstract_excerpt":"The exponential rise in mobile device usage necessitates streamlined automation for effective task management, yet many AI frameworks fall short due to inadequate operational expertise. While manually written knowledge can bridge this gap, it is often burdensome and inefficient. We introduce Mobile-Agent-V, an innovative framework that utilizes video as a guiding tool to effortlessly and efficiently inject operational knowledge into mobile automation processes. By deriving knowledge directly from video content, Mobile-Agent-V eliminates manual intervention, significantly reducing the effort an"},"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":"2502.17110","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T12:51:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cd91d09bf432807a125b03a4884f9d112edf798e3f0dd9b2116c5f83ce91e2d7","abstract_canon_sha256":"6b9122edbc42ee5f024039e23af48753a604e34bb54fe978bd519674eca6c1fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:54.284824Z","signature_b64":"pReeYEEjS911md2a0mYEJYe7AudOpoU9sYH6E/9DxEKNruWP3S+ZUnwKaUwpHN8whex4njDaUjBlGgDRBdJPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c34e4a1ef6e9c6bb0b2a291d3be15e0df89a136abf9e05687070fc3103684625","last_reissued_at":"2026-07-05T11:14:54.284336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:54.284336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Haiyang Xu, Jitao Sang, Ji Zhang, Junyang Wang, Ming Yan, Xi Zhang","submitted_at":"2025-02-24T12:51:23Z","abstract_excerpt":"The exponential rise in mobile device usage necessitates streamlined automation for effective task management, yet many AI frameworks fall short due to inadequate operational expertise. While manually written knowledge can bridge this gap, it is often burdensome and inefficient. We introduce Mobile-Agent-V, an innovative framework that utilizes video as a guiding tool to effortlessly and efficiently inject operational knowledge into mobile automation processes. By deriving knowledge directly from video content, Mobile-Agent-V eliminates manual intervention, significantly reducing the effort an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17110","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/2502.17110/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":"2502.17110","created_at":"2026-07-05T11:14:54.284401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17110v3","created_at":"2026-07-05T11:14:54.284401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17110","created_at":"2026-07-05T11:14:54.284401+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNHEUHXW5HDL","created_at":"2026-07-05T11:14:54.284401+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNHEUHXW5HDLWCZK","created_at":"2026-07-05T11:14:54.284401+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNHEUHXW","created_at":"2026-07-05T11:14:54.284401+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29445","citing_title":"Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YNHEUHXW5HDLWCZKFEOTXYK6BX","json":"https://pith.science/pith/YNHEUHXW5HDLWCZKFEOTXYK6BX.json","graph_json":"https://pith.science/api/pith-number/YNHEUHXW5HDLWCZKFEOTXYK6BX/graph.json","events_json":"https://pith.science/api/pith-number/YNHEUHXW5HDLWCZKFEOTXYK6BX/events.json","paper":"https://pith.science/paper/YNHEUHXW"},"agent_actions":{"view_html":"https://pith.science/pith/YNHEUHXW5HDLWCZKFEOTXYK6BX","download_json":"https://pith.science/pith/YNHEUHXW5HDLWCZKFEOTXYK6BX.json","view_paper":"https://pith.science/paper/YNHEUHXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17110&json=true","fetch_graph":"https://pith.science/api/pith-number/YNHEUHXW5HDLWCZKFEOTXYK6BX/graph.json","fetch_events":"https://pith.science/api/pith-number/YNHEUHXW5HDLWCZKFEOTXYK6BX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNHEUHXW5HDLWCZKFEOTXYK6BX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNHEUHXW5HDLWCZKFEOTXYK6BX/action/storage_attestation","attest_author":"https://pith.science/pith/YNHEUHXW5HDLWCZKFEOTXYK6BX/action/author_attestation","sign_citation":"https://pith.science/pith/YNHEUHXW5HDLWCZKFEOTXYK6BX/action/citation_signature","submit_replication":"https://pith.science/pith/YNHEUHXW5HDLWCZKFEOTXYK6BX/action/replication_record"}},"created_at":"2026-07-05T11:14:54.284401+00:00","updated_at":"2026-07-05T11:14:54.284401+00:00"}