{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KXFFNXV4OUTPIKO42QZBSJENRR","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":"9b545aa8529ef19a5b127bbeaefba08f651e8e6c25c56a7058bc9cb3a96776cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:52:42Z","title_canon_sha256":"1d81397ebe8fa6988c75bba727f4c18bbdad9d9b2486e6ed369414afda0fc79b"},"schema_version":"1.0","source":{"id":"2504.16073","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16073","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16073v1","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16073","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"KXFFNXV4OUTP","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_16","alias_value":"KXFFNXV4OUTPIKO4","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_8","alias_value":"KXFFNXV4","created_at":"2026-07-05T10:52:35Z"}],"graph_snapshots":[{"event_id":"sha256:b7b89cfbef5522573126fe6cf7347728350801489f4c3c8b9b482f3c5a21317d","target":"graph","created_at":"2026-07-05T10:52:35Z","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/2504.16073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in visual language models (VLMs) have notably enhanced their capabilities in handling complex Graphical User Interface (GUI) interaction tasks. Despite these improvements, current frameworks often struggle to generate correct actions in challenging GUI environments. State-of-the-art commercial VLMs are black-boxes, and fine-tuning open-source VLMs for GUI tasks requires significant resources. Additionally, existing trajectory-level evaluation and refinement techniques frequently fall short due to delayed feedback and local optimization issues. To address these challenges, w","authors_text":"Anh Tuan Luu, Bo An, Bryan Hooi, See-kiong Ng, Shiyun Xiong, Shuicheng Yan, Yifan Zhang, Zhiyuan Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:52:42Z","title":"Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16073","kind":"arxiv","version":1},"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:a9f704539a5b44d4b4803ecc84093844c95497784301436a2ee6fcae88c36e34","target":"record","created_at":"2026-07-05T10:52:35Z","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":"9b545aa8529ef19a5b127bbeaefba08f651e8e6c25c56a7058bc9cb3a96776cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T17:52:42Z","title_canon_sha256":"1d81397ebe8fa6988c75bba727f4c18bbdad9d9b2486e6ed369414afda0fc79b"},"schema_version":"1.0","source":{"id":"2504.16073","kind":"arxiv","version":1}},"canonical_sha256":"55ca56debc7526f429dcd43219248d8c6147bd915a07abfee1be951588fe3ef3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55ca56debc7526f429dcd43219248d8c6147bd915a07abfee1be951588fe3ef3","first_computed_at":"2026-07-05T10:52:35.086627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:35.086627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uLXm8O4j+SH572Jk3pY4DdBEk9lIaaiABgIHLu5nBr8FccVH0o9wNbBf0CXdxeZeVVowCKcpE7MUnGPusKdXBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:35.087094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16073","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9f704539a5b44d4b4803ecc84093844c95497784301436a2ee6fcae88c36e34","sha256:b7b89cfbef5522573126fe6cf7347728350801489f4c3c8b9b482f3c5a21317d"],"state_sha256":"f38c09863a668bd194cb946008a2ae89d58678aa45b68f1343ec3909a7f80c32"}