{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HVECE47JBPAVOJQN3NKWFUUNYT","short_pith_number":"pith:HVECE47J","schema_version":"1.0","canonical_sha256":"3d482273e90bc157260ddb5562d28dc4c98f3f93d9a991e8908e1c09fc1c3895","source":{"kind":"arxiv","id":"2503.03743","version":1},"attestation_state":"computed","paper":{"title":"CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jun Xu, Qinglin Jia, Shuai Wang, Sunhao Dai, Yuqi Zhou, Zhaocheng Du, Zhenhua Dong","submitted_at":"2025-03-05T18:56:16Z","abstract_excerpt":"The advancement of visual language models (VLMs) has enhanced mobile device operations, allowing simulated human-like actions to address user requirements. Current VLM-based mobile operating assistants can be structured into three levels: task, subtask, and action. The subtask level, linking high-level goals with low-level executable actions, is crucial for task completion but faces two challenges: ineffective subtasks that lower-level agent cannot execute and inefficient subtasks that fail to contribute to the completion of the higher-level task. These challenges stem from VLM's lack of exper"},"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":"2503.03743","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-05T18:56:16Z","cross_cats_sorted":[],"title_canon_sha256":"b15c16a450ca8f65f8f1a1039f9fd6dedc50cc578c393d70e8e3eba9a6d2b0d8","abstract_canon_sha256":"b185d06a9c3068a31ec08ac5221bf227eb1de910ecf80acd82eadf7c8f292bf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:59.791794Z","signature_b64":"EIF5sjO4VhnYchNEu4AF0zi3p8qtzxf1Fv4ydKj8tmTP3GyfOQLFg2/8wNWzvQP65kDjYEx3fzL4jKIHHc89AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d482273e90bc157260ddb5562d28dc4c98f3f93d9a991e8908e1c09fc1c3895","last_reissued_at":"2026-07-05T10:24:59.790992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:59.790992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHOP: Mobile Operating Assistant with Constrained High-frequency Optimized Subtask Planning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jun Xu, Qinglin Jia, Shuai Wang, Sunhao Dai, Yuqi Zhou, Zhaocheng Du, Zhenhua Dong","submitted_at":"2025-03-05T18:56:16Z","abstract_excerpt":"The advancement of visual language models (VLMs) has enhanced mobile device operations, allowing simulated human-like actions to address user requirements. Current VLM-based mobile operating assistants can be structured into three levels: task, subtask, and action. The subtask level, linking high-level goals with low-level executable actions, is crucial for task completion but faces two challenges: ineffective subtasks that lower-level agent cannot execute and inefficient subtasks that fail to contribute to the completion of the higher-level task. These challenges stem from VLM's lack of exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03743","kind":"arxiv","version":1},"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/2503.03743/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":"2503.03743","created_at":"2026-07-05T10:24:59.791064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03743v1","created_at":"2026-07-05T10:24:59.791064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03743","created_at":"2026-07-05T10:24:59.791064+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVECE47JBPAV","created_at":"2026-07-05T10:24:59.791064+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVECE47JBPAVOJQN","created_at":"2026-07-05T10:24:59.791064+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVECE47J","created_at":"2026-07-05T10:24:59.791064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04025","citing_title":"Uncertainty-Aware GUI Agent: Adaptive Perception through Component Recommendation and Human-in-the-Loop Refinement","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVECE47JBPAVOJQN3NKWFUUNYT","json":"https://pith.science/pith/HVECE47JBPAVOJQN3NKWFUUNYT.json","graph_json":"https://pith.science/api/pith-number/HVECE47JBPAVOJQN3NKWFUUNYT/graph.json","events_json":"https://pith.science/api/pith-number/HVECE47JBPAVOJQN3NKWFUUNYT/events.json","paper":"https://pith.science/paper/HVECE47J"},"agent_actions":{"view_html":"https://pith.science/pith/HVECE47JBPAVOJQN3NKWFUUNYT","download_json":"https://pith.science/pith/HVECE47JBPAVOJQN3NKWFUUNYT.json","view_paper":"https://pith.science/paper/HVECE47J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03743&json=true","fetch_graph":"https://pith.science/api/pith-number/HVECE47JBPAVOJQN3NKWFUUNYT/graph.json","fetch_events":"https://pith.science/api/pith-number/HVECE47JBPAVOJQN3NKWFUUNYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVECE47JBPAVOJQN3NKWFUUNYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVECE47JBPAVOJQN3NKWFUUNYT/action/storage_attestation","attest_author":"https://pith.science/pith/HVECE47JBPAVOJQN3NKWFUUNYT/action/author_attestation","sign_citation":"https://pith.science/pith/HVECE47JBPAVOJQN3NKWFUUNYT/action/citation_signature","submit_replication":"https://pith.science/pith/HVECE47JBPAVOJQN3NKWFUUNYT/action/replication_record"}},"created_at":"2026-07-05T10:24:59.791064+00:00","updated_at":"2026-07-05T10:24:59.791064+00:00"}