{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JNRUFTLCZD24QNBOJW2OJQ74KP","short_pith_number":"pith:JNRUFTLC","schema_version":"1.0","canonical_sha256":"4b6342cd62c8f5c8342e4db4e4c3fc53e5ba205cd2359880002de5383a4ecc90","source":{"kind":"arxiv","id":"2503.16788","version":1},"attestation_state":"computed","paper":{"title":"Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Li Zhang, Longxi Gao, Mengwei Xu","submitted_at":"2025-03-21T01:52:43Z","abstract_excerpt":"Reasoning capabilities have significantly improved the performance of vision-language models (VLMs) in domains such as mathematical problem-solving, coding, and visual question-answering. However, their impact on real-world applications remains unclear. This paper presents the first empirical study on the effectiveness of reasoning-enabled VLMs in mobile GUI agents, a domain that requires interpreting complex screen layouts, understanding user instructions, and executing multi-turn interactions. We evaluate two pairs of commercial models--Gemini 2.0 Flash and Claude 3.7 Sonnet--comparing their"},"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":"2503.16788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-21T01:52:43Z","cross_cats_sorted":[],"title_canon_sha256":"c30cd6112236db067ed7633cd33c7b5b7b28157349a449f3de71f783fb2ddbc6","abstract_canon_sha256":"c973ddeb1b27498aa33f1c95b126cae40e7647f21a66e7c88c86d419b8512891"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:49.949587Z","signature_b64":"cWuq0I03KQlBmn8iaxQ7GY7HvAa66itv8LkDzJ36/EuLLLBpFWJ33PhaVeJ7soxE9jwhRhyGoLXTMm+35aufAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b6342cd62c8f5c8342e4db4e4c3fc53e5ba205cd2359880002de5383a4ecc90","last_reissued_at":"2026-07-05T10:36:49.949080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:49.949080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Li Zhang, Longxi Gao, Mengwei Xu","submitted_at":"2025-03-21T01:52:43Z","abstract_excerpt":"Reasoning capabilities have significantly improved the performance of vision-language models (VLMs) in domains such as mathematical problem-solving, coding, and visual question-answering. However, their impact on real-world applications remains unclear. This paper presents the first empirical study on the effectiveness of reasoning-enabled VLMs in mobile GUI agents, a domain that requires interpreting complex screen layouts, understanding user instructions, and executing multi-turn interactions. We evaluate two pairs of commercial models--Gemini 2.0 Flash and Claude 3.7 Sonnet--comparing their"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16788","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/2503.16788/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":"2503.16788","created_at":"2026-07-05T10:36:49.949139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16788v1","created_at":"2026-07-05T10:36:49.949139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16788","created_at":"2026-07-05T10:36:49.949139+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNRUFTLCZD24","created_at":"2026-07-05T10:36:49.949139+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNRUFTLCZD24QNBO","created_at":"2026-07-05T10:36:49.949139+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNRUFTLC","created_at":"2026-07-05T10:36:49.949139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06664","citing_title":"BAMI: Training-Free Bias Mitigation in GUI Grounding","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JNRUFTLCZD24QNBOJW2OJQ74KP","json":"https://pith.science/pith/JNRUFTLCZD24QNBOJW2OJQ74KP.json","graph_json":"https://pith.science/api/pith-number/JNRUFTLCZD24QNBOJW2OJQ74KP/graph.json","events_json":"https://pith.science/api/pith-number/JNRUFTLCZD24QNBOJW2OJQ74KP/events.json","paper":"https://pith.science/paper/JNRUFTLC"},"agent_actions":{"view_html":"https://pith.science/pith/JNRUFTLCZD24QNBOJW2OJQ74KP","download_json":"https://pith.science/pith/JNRUFTLCZD24QNBOJW2OJQ74KP.json","view_paper":"https://pith.science/paper/JNRUFTLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16788&json=true","fetch_graph":"https://pith.science/api/pith-number/JNRUFTLCZD24QNBOJW2OJQ74KP/graph.json","fetch_events":"https://pith.science/api/pith-number/JNRUFTLCZD24QNBOJW2OJQ74KP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNRUFTLCZD24QNBOJW2OJQ74KP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNRUFTLCZD24QNBOJW2OJQ74KP/action/storage_attestation","attest_author":"https://pith.science/pith/JNRUFTLCZD24QNBOJW2OJQ74KP/action/author_attestation","sign_citation":"https://pith.science/pith/JNRUFTLCZD24QNBOJW2OJQ74KP/action/citation_signature","submit_replication":"https://pith.science/pith/JNRUFTLCZD24QNBOJW2OJQ74KP/action/replication_record"}},"created_at":"2026-07-05T10:36:49.949139+00:00","updated_at":"2026-07-05T10:36:49.949139+00:00"}