{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5SBL4BL4WOB2JVZVQQ3LLXONNZ","short_pith_number":"pith:5SBL4BL4","canonical_record":{"source":{"id":"2505.00684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T17:45:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"76d6707d763cf5996fdbe603d28510cc8c0722659166e06d50580c87f0f37de6","abstract_canon_sha256":"134017e47fce4b99ae63e13a0a0e6cc136c660c5ecb6b05c15f2a929150799d3"},"schema_version":"1.0"},"canonical_sha256":"ec82be057cb383a4d7358436b5ddcd6e68b8890272a5ea2667f519298d2fd099","source":{"kind":"arxiv","id":"2505.00684","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00684","created_at":"2026-07-05T11:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00684v2","created_at":"2026-07-05T11:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00684","created_at":"2026-07-05T11:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"5SBL4BL4WOB2","created_at":"2026-07-05T11:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"5SBL4BL4WOB2JVZV","created_at":"2026-07-05T11:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"5SBL4BL4","created_at":"2026-07-05T11:36:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5SBL4BL4WOB2JVZVQQ3LLXONNZ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.00684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T17:45:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"76d6707d763cf5996fdbe603d28510cc8c0722659166e06d50580c87f0f37de6","abstract_canon_sha256":"134017e47fce4b99ae63e13a0a0e6cc136c660c5ecb6b05c15f2a929150799d3"},"schema_version":"1.0"},"canonical_sha256":"ec82be057cb383a4d7358436b5ddcd6e68b8890272a5ea2667f519298d2fd099","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:31.373654Z","signature_b64":"c0G0JUfpHqLPqB/6iSHVniJAfs56WRZISQygPhCd0NOhwr9wbZSIHsPBbtGx7AJ/DySOKC+UmnPyg75dLkvoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec82be057cb383a4d7358436b5ddcd6e68b8890272a5ea2667f519298d2fd099","last_reissued_at":"2026-07-05T11:36:31.373099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:31.373099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.00684","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OjPH3znez+Z9pyVl93NWsv+LvBHtdmymrW8RdN0nyXzRuBu30e2YL0lV5eNtHXkTHReQEpye23aKGRE3WWJmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:17:03.423586Z"},"content_sha256":"b93974a1f639e77c898df6f9a157992a1ecf807da3e71c280454ce07d95fb424","schema_version":"1.0","event_id":"sha256:b93974a1f639e77c898df6f9a157992a1ecf807da3e71c280454ce07d95fb424"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5SBL4BL4WOB2JVZVQQ3LLXONNZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Test-time Scaling for GUI Agent Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Honglak Lee, Justin Johnson, Lajanugen Logeswaran, Tiange Luo","submitted_at":"2025-05-01T17:45:59Z","abstract_excerpt":"We introduce RegionFocus, a visual test-time scaling approach for Vision Language Model Agents. Understanding webpages is challenging due to the visual complexity of GUI images and the large number of interface elements, making accurate action selection difficult. Our approach dynamically zooms in on relevant regions, reducing background clutter and improving grounding accuracy. To support this process, we propose an image-as-map mechanism that visualizes key landmarks at each step, providing a transparent action record and enables the agent to effectively choose among action candidates. Even "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00684","kind":"arxiv","version":2},"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/2505.00684/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:36:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9XYsngX4R52h65s+r+886e5/3bGEIypkP200gTNmDQFzFnYXf5b3RO9b33idyIeL+pgSurWfGgvxBTPsNNifCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:17:03.423919Z"},"content_sha256":"0915c659e1f342130e44e7cc0f9fdc9378b1036ce18c971a7f65609f16e94013","schema_version":"1.0","event_id":"sha256:0915c659e1f342130e44e7cc0f9fdc9378b1036ce18c971a7f65609f16e94013"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5SBL4BL4WOB2JVZVQQ3LLXONNZ/bundle.json","state_url":"https://pith.science/pith/5SBL4BL4WOB2JVZVQQ3LLXONNZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5SBL4BL4WOB2JVZVQQ3LLXONNZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T12:17:03Z","links":{"resolver":"https://pith.science/pith/5SBL4BL4WOB2JVZVQQ3LLXONNZ","bundle":"https://pith.science/pith/5SBL4BL4WOB2JVZVQQ3LLXONNZ/bundle.json","state":"https://pith.science/pith/5SBL4BL4WOB2JVZVQQ3LLXONNZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5SBL4BL4WOB2JVZVQQ3LLXONNZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5SBL4BL4WOB2JVZVQQ3LLXONNZ","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":"134017e47fce4b99ae63e13a0a0e6cc136c660c5ecb6b05c15f2a929150799d3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T17:45:59Z","title_canon_sha256":"76d6707d763cf5996fdbe603d28510cc8c0722659166e06d50580c87f0f37de6"},"schema_version":"1.0","source":{"id":"2505.00684","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00684","created_at":"2026-07-05T11:36:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00684v2","created_at":"2026-07-05T11:36:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00684","created_at":"2026-07-05T11:36:31Z"},{"alias_kind":"pith_short_12","alias_value":"5SBL4BL4WOB2","created_at":"2026-07-05T11:36:31Z"},{"alias_kind":"pith_short_16","alias_value":"5SBL4BL4WOB2JVZV","created_at":"2026-07-05T11:36:31Z"},{"alias_kind":"pith_short_8","alias_value":"5SBL4BL4","created_at":"2026-07-05T11:36:31Z"}],"graph_snapshots":[{"event_id":"sha256:0915c659e1f342130e44e7cc0f9fdc9378b1036ce18c971a7f65609f16e94013","target":"graph","created_at":"2026-07-05T11:36:31Z","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/2505.00684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce RegionFocus, a visual test-time scaling approach for Vision Language Model Agents. Understanding webpages is challenging due to the visual complexity of GUI images and the large number of interface elements, making accurate action selection difficult. Our approach dynamically zooms in on relevant regions, reducing background clutter and improving grounding accuracy. To support this process, we propose an image-as-map mechanism that visualizes key landmarks at each step, providing a transparent action record and enables the agent to effectively choose among action candidates. Even ","authors_text":"Honglak Lee, Justin Johnson, Lajanugen Logeswaran, Tiange Luo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T17:45:59Z","title":"Visual Test-time Scaling for GUI Agent Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00684","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:b93974a1f639e77c898df6f9a157992a1ecf807da3e71c280454ce07d95fb424","target":"record","created_at":"2026-07-05T11:36:31Z","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":"134017e47fce4b99ae63e13a0a0e6cc136c660c5ecb6b05c15f2a929150799d3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T17:45:59Z","title_canon_sha256":"76d6707d763cf5996fdbe603d28510cc8c0722659166e06d50580c87f0f37de6"},"schema_version":"1.0","source":{"id":"2505.00684","kind":"arxiv","version":2}},"canonical_sha256":"ec82be057cb383a4d7358436b5ddcd6e68b8890272a5ea2667f519298d2fd099","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec82be057cb383a4d7358436b5ddcd6e68b8890272a5ea2667f519298d2fd099","first_computed_at":"2026-07-05T11:36:31.373099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:31.373099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c0G0JUfpHqLPqB/6iSHVniJAfs56WRZISQygPhCd0NOhwr9wbZSIHsPBbtGx7AJ/DySOKC+UmnPyg75dLkvoDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:31.373654Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00684","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b93974a1f639e77c898df6f9a157992a1ecf807da3e71c280454ce07d95fb424","sha256:0915c659e1f342130e44e7cc0f9fdc9378b1036ce18c971a7f65609f16e94013"],"state_sha256":"56ed9f5a39cb2226cb92eabd99ac2d9482d3a52752386134b0fac8c1bbbf4e19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7X/aJnVHk8TaYxYmmKIS9wjUtLdeUx7uw8qUA6K4YnKORtZ3LqQcNMRzuDc9bXEj1LVwNqka5ltuJsKInDNxDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:17:03.426818Z","bundle_sha256":"c0c2d4495bbc24a1777836018396e925984361717c4de243122d840602ab095e"}}