{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FV4P57QJ5G4U5VBCSLIEUAVFIL","short_pith_number":"pith:FV4P57QJ","canonical_record":{"source":{"id":"2412.01268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T08:35:31Z","cross_cats_sorted":[],"title_canon_sha256":"a66980e7170e79d4c7607417acf5f4c8e39b1f157b66e8cd365446cc8a86e63d","abstract_canon_sha256":"fa308eb518a4fdaa1636486112cad5cf904c03adde17c2a569fca9891f26d0cf"},"schema_version":"1.0"},"canonical_sha256":"2d78fefe09e9b94ed42292d04a02a542fbc918d6ff9202ba79ceb093cd161c1c","source":{"kind":"arxiv","id":"2412.01268","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01268","created_at":"2026-07-05T09:42:56Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01268v1","created_at":"2026-07-05T09:42:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01268","created_at":"2026-07-05T09:42:56Z"},{"alias_kind":"pith_short_12","alias_value":"FV4P57QJ5G4U","created_at":"2026-07-05T09:42:56Z"},{"alias_kind":"pith_short_16","alias_value":"FV4P57QJ5G4U5VBC","created_at":"2026-07-05T09:42:56Z"},{"alias_kind":"pith_short_8","alias_value":"FV4P57QJ","created_at":"2026-07-05T09:42:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FV4P57QJ5G4U5VBCSLIEUAVFIL","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T08:35:31Z","cross_cats_sorted":[],"title_canon_sha256":"a66980e7170e79d4c7607417acf5f4c8e39b1f157b66e8cd365446cc8a86e63d","abstract_canon_sha256":"fa308eb518a4fdaa1636486112cad5cf904c03adde17c2a569fca9891f26d0cf"},"schema_version":"1.0"},"canonical_sha256":"2d78fefe09e9b94ed42292d04a02a542fbc918d6ff9202ba79ceb093cd161c1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:56.989194Z","signature_b64":"fvwg6sLbKVTxh55qb5TqmQs1XUBPmTPxe0TdJ0gYIo3vOivYEx0e4zxGkkImvmzfPKRsjnf38PmPCm/AEfDRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d78fefe09e9b94ed42292d04a02a542fbc918d6ff9202ba79ceb093cd161c1c","last_reissued_at":"2026-07-05T09:42:56.988710Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:56.988710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01268","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:42:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sRbTlC1KlXHaNW0WE8As4q1bVG/EzLIv5UBgaUeX0pmefcxC3T9I8l6BI4qky7Rv8hykRHXM4Dcx0qh6QqGkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:00:22.149307Z"},"content_sha256":"9dad7ed1ab5d8c826028be873740082c0496fe910ccb9544026a2507ff001c8f","schema_version":"1.0","event_id":"sha256:9dad7ed1ab5d8c826028be873740082c0496fe910ccb9544026a2507ff001c8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FV4P57QJ5G4U5VBCSLIEUAVFIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ponder & Press: Advancing Visual GUI Agent towards General Computer Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoji Zhang, Jingqi Tian, Yansong Tang, Yiqin Wang","submitted_at":"2024-12-02T08:35:31Z","abstract_excerpt":"Most existing GUI agents typically depend on non-vision inputs like HTML source code or accessibility trees, limiting their flexibility across diverse software environments and platforms. Current multimodal large language models (MLLMs), which excel at using vision to ground real-world objects, offer a potential alternative. However, they often struggle with accurately localizing GUI elements -- a critical requirement for effective GUI automation -- due to the semantic gap between real-world objects and GUI elements. In this work, we introduce Ponder & Press, a divide-and-conquer framework for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01268","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/2412.01268/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":"2026-07-05T09:42:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hbfSe8VXBQf0O/YnMi9B5bUnl/vfil4OguPHw62Dta9CI/YHjm9oghTDV+0np4kgOuo94G9yup1YrNUmjX8aCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:00:22.149789Z"},"content_sha256":"bbb6c358b966ba61b5650e2609d2495e887bb56f0574bede3c48bc60b55eabbb","schema_version":"1.0","event_id":"sha256:bbb6c358b966ba61b5650e2609d2495e887bb56f0574bede3c48bc60b55eabbb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FV4P57QJ5G4U5VBCSLIEUAVFIL/bundle.json","state_url":"https://pith.science/pith/FV4P57QJ5G4U5VBCSLIEUAVFIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FV4P57QJ5G4U5VBCSLIEUAVFIL/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":"2026-08-08T07:00:22Z","links":{"resolver":"https://pith.science/pith/FV4P57QJ5G4U5VBCSLIEUAVFIL","bundle":"https://pith.science/pith/FV4P57QJ5G4U5VBCSLIEUAVFIL/bundle.json","state":"https://pith.science/pith/FV4P57QJ5G4U5VBCSLIEUAVFIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FV4P57QJ5G4U5VBCSLIEUAVFIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FV4P57QJ5G4U5VBCSLIEUAVFIL","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":"fa308eb518a4fdaa1636486112cad5cf904c03adde17c2a569fca9891f26d0cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T08:35:31Z","title_canon_sha256":"a66980e7170e79d4c7607417acf5f4c8e39b1f157b66e8cd365446cc8a86e63d"},"schema_version":"1.0","source":{"id":"2412.01268","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01268","created_at":"2026-07-05T09:42:56Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01268v1","created_at":"2026-07-05T09:42:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01268","created_at":"2026-07-05T09:42:56Z"},{"alias_kind":"pith_short_12","alias_value":"FV4P57QJ5G4U","created_at":"2026-07-05T09:42:56Z"},{"alias_kind":"pith_short_16","alias_value":"FV4P57QJ5G4U5VBC","created_at":"2026-07-05T09:42:56Z"},{"alias_kind":"pith_short_8","alias_value":"FV4P57QJ","created_at":"2026-07-05T09:42:56Z"}],"graph_snapshots":[{"event_id":"sha256:bbb6c358b966ba61b5650e2609d2495e887bb56f0574bede3c48bc60b55eabbb","target":"graph","created_at":"2026-07-05T09:42:56Z","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/2412.01268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing GUI agents typically depend on non-vision inputs like HTML source code or accessibility trees, limiting their flexibility across diverse software environments and platforms. Current multimodal large language models (MLLMs), which excel at using vision to ground real-world objects, offer a potential alternative. However, they often struggle with accurately localizing GUI elements -- a critical requirement for effective GUI automation -- due to the semantic gap between real-world objects and GUI elements. In this work, we introduce Ponder & Press, a divide-and-conquer framework for","authors_text":"Haoji Zhang, Jingqi Tian, Yansong Tang, Yiqin Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T08:35:31Z","title":"Ponder & Press: Advancing Visual GUI Agent towards General Computer Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01268","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":"sha256:9dad7ed1ab5d8c826028be873740082c0496fe910ccb9544026a2507ff001c8f","target":"record","created_at":"2026-07-05T09:42:56Z","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":"fa308eb518a4fdaa1636486112cad5cf904c03adde17c2a569fca9891f26d0cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T08:35:31Z","title_canon_sha256":"a66980e7170e79d4c7607417acf5f4c8e39b1f157b66e8cd365446cc8a86e63d"},"schema_version":"1.0","source":{"id":"2412.01268","kind":"arxiv","version":1}},"canonical_sha256":"2d78fefe09e9b94ed42292d04a02a542fbc918d6ff9202ba79ceb093cd161c1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d78fefe09e9b94ed42292d04a02a542fbc918d6ff9202ba79ceb093cd161c1c","first_computed_at":"2026-07-05T09:42:56.988710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:56.988710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fvwg6sLbKVTxh55qb5TqmQs1XUBPmTPxe0TdJ0gYIo3vOivYEx0e4zxGkkImvmzfPKRsjnf38PmPCm/AEfDRBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:56.989194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01268","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dad7ed1ab5d8c826028be873740082c0496fe910ccb9544026a2507ff001c8f","sha256:bbb6c358b966ba61b5650e2609d2495e887bb56f0574bede3c48bc60b55eabbb"],"state_sha256":"efdba07c7a0c548db29824fc76a8f1e6295d8730c700ff10e5ce7799625a5402"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qd6pjsEX2wgaxPsxTEGz1O2CnMYbRhmx7aJoOBSBNgMmXyq33vggpjoy43g/nfSkotKMQ5OVVI8BsdTBgn92AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:00:22.152922Z","bundle_sha256":"a9b19e432de14c2b617c308d6dc7b781a8fc6c5ad855a5c8cc54c5279e52e6ae"}}