{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NBCCBTFSS53GPZQ2WGTDMRTKQK","short_pith_number":"pith:NBCCBTFS","canonical_record":{"source":{"id":"2407.01558","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2024-05-05T19:10:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fea542e83b1e43a716327b3a5e5f158929f62d55fc3bff55b1768f6f5b742ca1","abstract_canon_sha256":"c723ffb7696df9c0bd258ba2a78cc2ae4e2e6812aa55e3a779f4f4c41d33f6a7"},"schema_version":"1.0"},"canonical_sha256":"684420ccb2977667e61ab1a636466a8283961977f30159c6f7db65c5d69db4eb","source":{"kind":"arxiv","id":"2407.01558","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01558","created_at":"2026-07-05T11:39:03Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01558v3","created_at":"2026-07-05T11:39:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01558","created_at":"2026-07-05T11:39:03Z"},{"alias_kind":"pith_short_12","alias_value":"NBCCBTFSS53G","created_at":"2026-07-05T11:39:03Z"},{"alias_kind":"pith_short_16","alias_value":"NBCCBTFSS53GPZQ2","created_at":"2026-07-05T11:39:03Z"},{"alias_kind":"pith_short_8","alias_value":"NBCCBTFS","created_at":"2026-07-05T11:39:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NBCCBTFSS53GPZQ2WGTDMRTKQK","target":"record","payload":{"canonical_record":{"source":{"id":"2407.01558","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2024-05-05T19:10:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fea542e83b1e43a716327b3a5e5f158929f62d55fc3bff55b1768f6f5b742ca1","abstract_canon_sha256":"c723ffb7696df9c0bd258ba2a78cc2ae4e2e6812aa55e3a779f4f4c41d33f6a7"},"schema_version":"1.0"},"canonical_sha256":"684420ccb2977667e61ab1a636466a8283961977f30159c6f7db65c5d69db4eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:03.505833Z","signature_b64":"KADj68A5/XyG8RPWdHTBymxCp1Sk1i4neqTf63e6dqzVw4DqSCrjzOJuWaTfI4tF6beklhCpICRdnux55cLsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"684420ccb2977667e61ab1a636466a8283961977f30159c6f7db65c5d69db4eb","last_reissued_at":"2026-07-05T11:39:03.505396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:03.505396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.01558","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:39:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EX0r9ovEsMcgqMLlC0F+zKMgXRe4Cl+Hmhxtg7rAiyv7kJLFvxdvhX0mbOWwFfDO/sWT1MIiNPrr/5yY4JqVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:46:10.712277Z"},"content_sha256":"5a4b8a23e404886582df751913c2ab0f47f29d9b74c599c5c57f18d0771fe6f0","schema_version":"1.0","event_id":"sha256:5a4b8a23e404886582df751913c2ab0f47f29d9b74c599c5c57f18d0771fe6f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NBCCBTFSS53GPZQ2WGTDMRTKQK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Grounding Methods for Efficient Interaction with Desktop Graphical User Interfaces","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"El Hassane Ettifouri, Jessica L\\'opez Espejel, Laura Minkova, Tassnim Dardouri, Walid Dahhane","submitted_at":"2024-05-05T19:10:19Z","abstract_excerpt":"Most visual grounding solutions primarily focus on realistic images. However, applications involving synthetic images, such as Graphical User Interfaces (GUIs), remain limited. This restricts the development of autonomous computer vision-powered artificial intelligence (AI) agents for automatic application interaction. Enabling AI to effectively understand and interact with GUIs is crucial to advancing automation in software testing, accessibility, and human-computer interaction. In this work, we explore Instruction Visual Grounding (IVG), a multi-modal approach to object identification within"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01558","kind":"arxiv","version":3},"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/2407.01558/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":"2026-07-05T11:39:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mSo32dbw4VnAHxjVib8yi6G6SE4ErGO9uXAB+8v0AG9yee0HASYvIONw3FbKrtLFhHV+6QdkvJFv+O8OUWOhDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:46:10.712773Z"},"content_sha256":"c85a4ee5b302efd9905beafcf4e7ff113ed08e0e289f039aa31ac92209ac6328","schema_version":"1.0","event_id":"sha256:c85a4ee5b302efd9905beafcf4e7ff113ed08e0e289f039aa31ac92209ac6328"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NBCCBTFSS53GPZQ2WGTDMRTKQK/bundle.json","state_url":"https://pith.science/pith/NBCCBTFSS53GPZQ2WGTDMRTKQK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NBCCBTFSS53GPZQ2WGTDMRTKQK/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":"2026-08-04T10:46:10Z","links":{"resolver":"https://pith.science/pith/NBCCBTFSS53GPZQ2WGTDMRTKQK","bundle":"https://pith.science/pith/NBCCBTFSS53GPZQ2WGTDMRTKQK/bundle.json","state":"https://pith.science/pith/NBCCBTFSS53GPZQ2WGTDMRTKQK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NBCCBTFSS53GPZQ2WGTDMRTKQK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NBCCBTFSS53GPZQ2WGTDMRTKQK","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":"c723ffb7696df9c0bd258ba2a78cc2ae4e2e6812aa55e3a779f4f4c41d33f6a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2024-05-05T19:10:19Z","title_canon_sha256":"fea542e83b1e43a716327b3a5e5f158929f62d55fc3bff55b1768f6f5b742ca1"},"schema_version":"1.0","source":{"id":"2407.01558","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01558","created_at":"2026-07-05T11:39:03Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01558v3","created_at":"2026-07-05T11:39:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01558","created_at":"2026-07-05T11:39:03Z"},{"alias_kind":"pith_short_12","alias_value":"NBCCBTFSS53G","created_at":"2026-07-05T11:39:03Z"},{"alias_kind":"pith_short_16","alias_value":"NBCCBTFSS53GPZQ2","created_at":"2026-07-05T11:39:03Z"},{"alias_kind":"pith_short_8","alias_value":"NBCCBTFS","created_at":"2026-07-05T11:39:03Z"}],"graph_snapshots":[{"event_id":"sha256:c85a4ee5b302efd9905beafcf4e7ff113ed08e0e289f039aa31ac92209ac6328","target":"graph","created_at":"2026-07-05T11:39:03Z","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/2407.01558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most visual grounding solutions primarily focus on realistic images. However, applications involving synthetic images, such as Graphical User Interfaces (GUIs), remain limited. This restricts the development of autonomous computer vision-powered artificial intelligence (AI) agents for automatic application interaction. Enabling AI to effectively understand and interact with GUIs is crucial to advancing automation in software testing, accessibility, and human-computer interaction. In this work, we explore Instruction Visual Grounding (IVG), a multi-modal approach to object identification within","authors_text":"El Hassane Ettifouri, Jessica L\\'opez Espejel, Laura Minkova, Tassnim Dardouri, Walid Dahhane","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2024-05-05T19:10:19Z","title":"Visual Grounding Methods for Efficient Interaction with Desktop Graphical User Interfaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01558","kind":"arxiv","version":3},"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":"sha256:5a4b8a23e404886582df751913c2ab0f47f29d9b74c599c5c57f18d0771fe6f0","target":"record","created_at":"2026-07-05T11:39:03Z","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":"c723ffb7696df9c0bd258ba2a78cc2ae4e2e6812aa55e3a779f4f4c41d33f6a7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2024-05-05T19:10:19Z","title_canon_sha256":"fea542e83b1e43a716327b3a5e5f158929f62d55fc3bff55b1768f6f5b742ca1"},"schema_version":"1.0","source":{"id":"2407.01558","kind":"arxiv","version":3}},"canonical_sha256":"684420ccb2977667e61ab1a636466a8283961977f30159c6f7db65c5d69db4eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"684420ccb2977667e61ab1a636466a8283961977f30159c6f7db65c5d69db4eb","first_computed_at":"2026-07-05T11:39:03.505396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:03.505396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KADj68A5/XyG8RPWdHTBymxCp1Sk1i4neqTf63e6dqzVw4DqSCrjzOJuWaTfI4tF6beklhCpICRdnux55cLsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:03.505833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01558","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a4b8a23e404886582df751913c2ab0f47f29d9b74c599c5c57f18d0771fe6f0","sha256:c85a4ee5b302efd9905beafcf4e7ff113ed08e0e289f039aa31ac92209ac6328"],"state_sha256":"cf31289b732bd4727aeb0cae1c0d2fe06aebe7dff0b4f1fd2c908f8586e16876"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IlKBzyZviEqK/X5eD4gg+rfwwsGDYKKDwctugVpswd+z7xoYzPIsSHb4A+Gw8w7BWJErcGNUULomkkPRu1x9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:46:10.717511Z","bundle_sha256":"e9eef77cfd36ca03f95aaf58b5592aeef9b8e7d765e99cd1affd60b6f6472cf7"}}