{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MVCDPI2XHPFWHIWFOZ3CCHPKAX","short_pith_number":"pith:MVCDPI2X","schema_version":"1.0","canonical_sha256":"654437a3573bcb63a2c57676211dea05fb17ff1cf3c586951e0aa38f5b136349","source":{"kind":"arxiv","id":"2606.30084","version":1},"attestation_state":"computed","paper":{"title":"One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenglin Cai, Chen Liu, Hanzhang Zhou, Liangyu Chen, Ling Chen, Steven Hoi, Xin Yu, Yue Wang","submitted_at":"2026-06-29T10:20:39Z","abstract_excerpt":"MLLM-based GUI grounding methods commonly formulate target localization as autoregressive coordinate generation, enabling models to leverage the strong instruction-following and semantic understanding capabilities of MLLMs. However, this formulation requires the model to retain region-level target evidence while decoding coordinate tokens with the spatial precision demanded by GUI clicking. Our diagnostic analysis reveals that target-region awareness emerges in intermediate decoder layers but is neither retained nor translated into the final coordinate prediction. Existing ZoomIn-style methods"},"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":"2606.30084","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T10:20:39Z","cross_cats_sorted":[],"title_canon_sha256":"1f94bd0035b1ef4e8ef54315db5557e4e8df0834e904214e06b443a1beefb178","abstract_canon_sha256":"3bcbaa063fb160a3d945eeb007f598dc883a9f9af870ebb17909775ae3a67f6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:48.886385Z","signature_b64":"NiPTodn4P/0MLo4UjGO5KC4VpTC2+tq4QGKu07DbGprhugeFq7VZYziaAWuemgDZ+YG+R9wke4O/SqLan1X/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"654437a3573bcb63a2c57676211dea05fb17ff1cf3c586951e0aa38f5b136349","last_reissued_at":"2026-06-30T02:17:48.885678Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:48.885678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenglin Cai, Chen Liu, Hanzhang Zhou, Liangyu Chen, Ling Chen, Steven Hoi, Xin Yu, Yue Wang","submitted_at":"2026-06-29T10:20:39Z","abstract_excerpt":"MLLM-based GUI grounding methods commonly formulate target localization as autoregressive coordinate generation, enabling models to leverage the strong instruction-following and semantic understanding capabilities of MLLMs. However, this formulation requires the model to retain region-level target evidence while decoding coordinate tokens with the spatial precision demanded by GUI clicking. Our diagnostic analysis reveals that target-region awareness emerges in intermediate decoder layers but is neither retained nor translated into the final coordinate prediction. Existing ZoomIn-style methods"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30084","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/2606.30084/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":"2606.30084","created_at":"2026-06-30T02:17:48.885789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30084v1","created_at":"2026-06-30T02:17:48.885789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30084","created_at":"2026-06-30T02:17:48.885789+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVCDPI2XHPFW","created_at":"2026-06-30T02:17:48.885789+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVCDPI2XHPFWHIWF","created_at":"2026-06-30T02:17:48.885789+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVCDPI2X","created_at":"2026-06-30T02:17:48.885789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVCDPI2XHPFWHIWFOZ3CCHPKAX","json":"https://pith.science/pith/MVCDPI2XHPFWHIWFOZ3CCHPKAX.json","graph_json":"https://pith.science/api/pith-number/MVCDPI2XHPFWHIWFOZ3CCHPKAX/graph.json","events_json":"https://pith.science/api/pith-number/MVCDPI2XHPFWHIWFOZ3CCHPKAX/events.json","paper":"https://pith.science/paper/MVCDPI2X"},"agent_actions":{"view_html":"https://pith.science/pith/MVCDPI2XHPFWHIWFOZ3CCHPKAX","download_json":"https://pith.science/pith/MVCDPI2XHPFWHIWFOZ3CCHPKAX.json","view_paper":"https://pith.science/paper/MVCDPI2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30084&json=true","fetch_graph":"https://pith.science/api/pith-number/MVCDPI2XHPFWHIWFOZ3CCHPKAX/graph.json","fetch_events":"https://pith.science/api/pith-number/MVCDPI2XHPFWHIWFOZ3CCHPKAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVCDPI2XHPFWHIWFOZ3CCHPKAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVCDPI2XHPFWHIWFOZ3CCHPKAX/action/storage_attestation","attest_author":"https://pith.science/pith/MVCDPI2XHPFWHIWFOZ3CCHPKAX/action/author_attestation","sign_citation":"https://pith.science/pith/MVCDPI2XHPFWHIWFOZ3CCHPKAX/action/citation_signature","submit_replication":"https://pith.science/pith/MVCDPI2XHPFWHIWFOZ3CCHPKAX/action/replication_record"}},"created_at":"2026-06-30T02:17:48.885789+00:00","updated_at":"2026-06-30T02:17:48.885789+00:00"}