{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FAZDVGYQM3RSAIEESFJDHAB5KQ","short_pith_number":"pith:FAZDVGYQ","canonical_record":{"source":{"id":"2406.19263","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T15:34:16Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ed8e478c616b03031c3ee6a629f123809d5390d5db65c9b95c92cba518b317d4","abstract_canon_sha256":"a1c31601e7b99d5ee9cdf00abc1448aa6ccf75689e0096237ca8d3e8662609bb"},"schema_version":"1.0"},"canonical_sha256":"28323a9b1066e3202084915233803d5422fd012e59b69a1bec4261608b323964","source":{"kind":"arxiv","id":"2406.19263","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19263","created_at":"2026-07-05T09:26:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19263v2","created_at":"2026-07-05T09:26:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19263","created_at":"2026-07-05T09:26:28Z"},{"alias_kind":"pith_short_12","alias_value":"FAZDVGYQM3RS","created_at":"2026-07-05T09:26:28Z"},{"alias_kind":"pith_short_16","alias_value":"FAZDVGYQM3RSAIEE","created_at":"2026-07-05T09:26:28Z"},{"alias_kind":"pith_short_8","alias_value":"FAZDVGYQ","created_at":"2026-07-05T09:26:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FAZDVGYQM3RSAIEESFJDHAB5KQ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.19263","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T15:34:16Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ed8e478c616b03031c3ee6a629f123809d5390d5db65c9b95c92cba518b317d4","abstract_canon_sha256":"a1c31601e7b99d5ee9cdf00abc1448aa6ccf75689e0096237ca8d3e8662609bb"},"schema_version":"1.0"},"canonical_sha256":"28323a9b1066e3202084915233803d5422fd012e59b69a1bec4261608b323964","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:28.711734Z","signature_b64":"iFzQ/M1piBVbqBW7LVURQy11UzXcK2lWuA16nHN1/WgFi4B3Qh67Ffc5HdhA22hjsPMhTBbu5fXwxM330TJIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28323a9b1066e3202084915233803d5422fd012e59b69a1bec4261608b323964","last_reissued_at":"2026-07-05T09:26:28.711265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:28.711265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.19263","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":"2026-07-05T09:26:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bmDIRpsrb2tkupIoxqnH7rV44laDQ9TciEqQVEkPdUrW0dg+e1eqm/CrSItd6eAKCf/LBj//EE+TZ2AWR6bECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:38:31.800590Z"},"content_sha256":"a928f47ab8437f223378625be96f6e71df131ce5b2066878baaf1958f341bcc1","schema_version":"1.0","event_id":"sha256:a928f47ab8437f223378625be96f6e71df131ce5b2066878baaf1958f341bcc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FAZDVGYQM3RSAIEESFJDHAB5KQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Ching-Chen Kuo, Jie Yang, Lei Ding, Shan Jiang, Xin Eric Wang, Xinze Guan, Yang Zhao, Yi Zhang, Yue Fan","submitted_at":"2024-06-27T15:34:16Z","abstract_excerpt":"Graphical User Interfaces (GUIs) are central to our interaction with digital devices and growing efforts have been made to build models for various GUI understanding tasks. However, these efforts largely overlook an important GUI-referring task: screen reading based on user-indicated points, which we name the Screen Point-and-Read (ScreenPR) task. Currently, this task is predominantly handled by rigid accessible screen reading tools, in great need of new models driven by advancements in Multimodal Large Language Models (MLLMs). In this paper, we propose a Tree-of-Lens (ToL) agent, utilizing a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19263","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/2406.19263/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":"2026-07-05T09:26:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VYiyIhYUXkUr7pU40KUwpZfRq6ciKjBWyh97ZZUXwv8FVc3TYeWaVVwHRUthDW3FdL+ZLV2bBrJJ5wrn4kcBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:38:31.801119Z"},"content_sha256":"0c60a2755e4347aa207423015ca79dc0cfaef8ee81f85d6389033b45a776fbce","schema_version":"1.0","event_id":"sha256:0c60a2755e4347aa207423015ca79dc0cfaef8ee81f85d6389033b45a776fbce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAZDVGYQM3RSAIEESFJDHAB5KQ/bundle.json","state_url":"https://pith.science/pith/FAZDVGYQM3RSAIEESFJDHAB5KQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAZDVGYQM3RSAIEESFJDHAB5KQ/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":"2026-08-08T20:38:31Z","links":{"resolver":"https://pith.science/pith/FAZDVGYQM3RSAIEESFJDHAB5KQ","bundle":"https://pith.science/pith/FAZDVGYQM3RSAIEESFJDHAB5KQ/bundle.json","state":"https://pith.science/pith/FAZDVGYQM3RSAIEESFJDHAB5KQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAZDVGYQM3RSAIEESFJDHAB5KQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FAZDVGYQM3RSAIEESFJDHAB5KQ","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":"a1c31601e7b99d5ee9cdf00abc1448aa6ccf75689e0096237ca8d3e8662609bb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T15:34:16Z","title_canon_sha256":"ed8e478c616b03031c3ee6a629f123809d5390d5db65c9b95c92cba518b317d4"},"schema_version":"1.0","source":{"id":"2406.19263","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19263","created_at":"2026-07-05T09:26:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19263v2","created_at":"2026-07-05T09:26:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19263","created_at":"2026-07-05T09:26:28Z"},{"alias_kind":"pith_short_12","alias_value":"FAZDVGYQM3RS","created_at":"2026-07-05T09:26:28Z"},{"alias_kind":"pith_short_16","alias_value":"FAZDVGYQM3RSAIEE","created_at":"2026-07-05T09:26:28Z"},{"alias_kind":"pith_short_8","alias_value":"FAZDVGYQ","created_at":"2026-07-05T09:26:28Z"}],"graph_snapshots":[{"event_id":"sha256:0c60a2755e4347aa207423015ca79dc0cfaef8ee81f85d6389033b45a776fbce","target":"graph","created_at":"2026-07-05T09:26:28Z","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/2406.19263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graphical User Interfaces (GUIs) are central to our interaction with digital devices and growing efforts have been made to build models for various GUI understanding tasks. However, these efforts largely overlook an important GUI-referring task: screen reading based on user-indicated points, which we name the Screen Point-and-Read (ScreenPR) task. Currently, this task is predominantly handled by rigid accessible screen reading tools, in great need of new models driven by advancements in Multimodal Large Language Models (MLLMs). In this paper, we propose a Tree-of-Lens (ToL) agent, utilizing a ","authors_text":"Ching-Chen Kuo, Jie Yang, Lei Ding, Shan Jiang, Xin Eric Wang, Xinze Guan, Yang Zhao, Yi Zhang, Yue Fan","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T15:34:16Z","title":"Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19263","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:a928f47ab8437f223378625be96f6e71df131ce5b2066878baaf1958f341bcc1","target":"record","created_at":"2026-07-05T09:26:28Z","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":"a1c31601e7b99d5ee9cdf00abc1448aa6ccf75689e0096237ca8d3e8662609bb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T15:34:16Z","title_canon_sha256":"ed8e478c616b03031c3ee6a629f123809d5390d5db65c9b95c92cba518b317d4"},"schema_version":"1.0","source":{"id":"2406.19263","kind":"arxiv","version":2}},"canonical_sha256":"28323a9b1066e3202084915233803d5422fd012e59b69a1bec4261608b323964","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28323a9b1066e3202084915233803d5422fd012e59b69a1bec4261608b323964","first_computed_at":"2026-07-05T09:26:28.711265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:28.711265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iFzQ/M1piBVbqBW7LVURQy11UzXcK2lWuA16nHN1/WgFi4B3Qh67Ffc5HdhA22hjsPMhTBbu5fXwxM330TJIBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:28.711734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19263","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a928f47ab8437f223378625be96f6e71df131ce5b2066878baaf1958f341bcc1","sha256:0c60a2755e4347aa207423015ca79dc0cfaef8ee81f85d6389033b45a776fbce"],"state_sha256":"a8cc1b971fdb6b93438e3a2055b303339f6e37b853a98d89f7ebcb48b5456061"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zn7Ud936DrpyyARY/6FbnMvtTN98gSQ9XhQOnM0/y3C+9E0RId20/NRdFn3mzTljEmYuWfNVYLpo3sy+XifHCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:38:31.806086Z","bundle_sha256":"b6521e60b0bb45f061d0630e3a3bd39060d488165f28a4d11909ecfd46270f3a"}}