{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CIYIJVKQ3V6P23EMVEOZWLIE4G","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":"497fd1732e4903c3602805f0d173cfab9f3ec24a67ed0abd75e720107b1da8bb","cross_cats_sorted":["cs.AI","cs.CV","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-01T08:29:59Z","title_canon_sha256":"a78f103bfb46632e1184228d1b9a75990894db43a560830418ad1c91c1a8571a"},"schema_version":"1.0","source":{"id":"2503.00401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00401","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00401v2","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00401","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"CIYIJVKQ3V6P","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"pith_short_16","alias_value":"CIYIJVKQ3V6P23EM","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"pith_short_8","alias_value":"CIYIJVKQ","created_at":"2026-07-05T10:24:03Z"}],"graph_snapshots":[{"event_id":"sha256:35cbfca2b1998513ada31250d0c4e7912ff57948743567765dd72a22eff8b49f","target":"graph","created_at":"2026-07-05T10:24:03Z","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/2503.00401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Perception-enhanced pre-training, particularly through grounding techniques, is widely adopted to enhance the performance of graphical user interface (GUI) agents. However, in resource-constrained scenarios, the format discrepancy between coordinate-oriented grounding and action-oriented reasoning limits the effectiveness of grounding for reasoning tasks. To address this challenge, we propose a query-oriented pivot approach called query inference, which serves as a bridge between GUI grounding and reasoning. By inferring potential user queries from a screenshot and its associated element coord","authors_text":"Gongshen Liu, Pengzhou Cheng, Tianjie Ju, Zheng Wu, Zhuosheng Zhang, Zongru Wu","cross_cats":["cs.AI","cs.CV","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-01T08:29:59Z","title":"Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00401","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":"sha256:2b4aac9e88dd384358f44d4835dc4e35e28914e3dd33430087786553c377e313","target":"record","created_at":"2026-07-05T10:24:03Z","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":"497fd1732e4903c3602805f0d173cfab9f3ec24a67ed0abd75e720107b1da8bb","cross_cats_sorted":["cs.AI","cs.CV","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-01T08:29:59Z","title_canon_sha256":"a78f103bfb46632e1184228d1b9a75990894db43a560830418ad1c91c1a8571a"},"schema_version":"1.0","source":{"id":"2503.00401","kind":"arxiv","version":2}},"canonical_sha256":"123084d550dd7cfd6c8ca91d9b2d04e19073c4e85e57ea44ab0c193d3e9c6c07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"123084d550dd7cfd6c8ca91d9b2d04e19073c4e85e57ea44ab0c193d3e9c6c07","first_computed_at":"2026-07-05T10:24:03.345809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:03.345809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/HlrTgAj+PycqYvMDQIO2EeYsI+VmQD8EkCuLT+XZWN4YdRLT9jAQL+BXAXA+ApFIxy75GO+oblezG6zo+XeDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:03.346300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.00401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b4aac9e88dd384358f44d4835dc4e35e28914e3dd33430087786553c377e313","sha256:35cbfca2b1998513ada31250d0c4e7912ff57948743567765dd72a22eff8b49f"],"state_sha256":"94059a22614c7a40edc6e227b5326b8011450abf539ddb58258997fde80e7fcf"}