{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4PAF3LSZYI7L6SRHI46NONRPVP","short_pith_number":"pith:4PAF3LSZ","canonical_record":{"source":{"id":"2412.10840","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T14:30:05Z","cross_cats_sorted":[],"title_canon_sha256":"1599c47ef44a8cfd862447d9107608a745bdfdfd194775519990eb6b607f3bd9","abstract_canon_sha256":"958d4209c4da4a67cb8276eddf6e9887a7dcf1e3108521ad09d2c26974cd40ca"},"schema_version":"1.0"},"canonical_sha256":"e3c05dae59c23ebf4a27473cd7362fabc21720dd748a794357c2cfe21aed827f","source":{"kind":"arxiv","id":"2412.10840","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10840","created_at":"2026-07-05T09:49:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10840v1","created_at":"2026-07-05T09:49:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10840","created_at":"2026-07-05T09:49:23Z"},{"alias_kind":"pith_short_12","alias_value":"4PAF3LSZYI7L","created_at":"2026-07-05T09:49:23Z"},{"alias_kind":"pith_short_16","alias_value":"4PAF3LSZYI7L6SRH","created_at":"2026-07-05T09:49:23Z"},{"alias_kind":"pith_short_8","alias_value":"4PAF3LSZ","created_at":"2026-07-05T09:49:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4PAF3LSZYI7L6SRHI46NONRPVP","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10840","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T14:30:05Z","cross_cats_sorted":[],"title_canon_sha256":"1599c47ef44a8cfd862447d9107608a745bdfdfd194775519990eb6b607f3bd9","abstract_canon_sha256":"958d4209c4da4a67cb8276eddf6e9887a7dcf1e3108521ad09d2c26974cd40ca"},"schema_version":"1.0"},"canonical_sha256":"e3c05dae59c23ebf4a27473cd7362fabc21720dd748a794357c2cfe21aed827f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:23.382728Z","signature_b64":"qmVDTwrW2uZyV3bty0VWdesOxpXQ5bJbcKwlvcVdcCMfjoy82YQaQYrK4RWLnbr8FGEyHlilffEtbXcAq0qJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3c05dae59c23ebf4a27473cd7362fabc21720dd748a794357c2cfe21aed827f","last_reissued_at":"2026-07-05T09:49:23.382273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:23.382273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10840","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":"2026-07-05T09:49:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zquNnDsZgYij12cght3tV07vKwDBrTDbVHuZcpoNQsLiqRMz/nv/eSo9xB1p2WXdJgIwUnHJ7obpeCCTjEkNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T03:50:59.832357Z"},"content_sha256":"93bac5f685f4d9b533277bc5d776d6418e42f0062c0af098ad0ae625b555e08d","schema_version":"1.0","event_id":"sha256:93bac5f685f4d9b533277bc5d776d6418e42f0062c0af098ad0ae625b555e08d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4PAF3LSZYI7L6SRHI46NONRPVP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention-driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models without Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hai-Ming Xu, Lei Wang, Lingqiao Liu, Qi Chen","submitted_at":"2024-12-14T14:30:05Z","abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have generated significant interest in their ability to autonomously interact with and interpret Graphical User Interfaces (GUIs). A major challenge in these systems is grounding-accurately identifying critical GUI components such as text or icons based on a GUI image and a corresponding text query. Traditionally, this task has relied on fine-tuning MLLMs with specialized training data to predict component locations directly. However, in this paper, we propose a novel Tuning-free Attention-driven Grounding (TAG) method that levera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10840","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/2412.10840/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":"2026-07-05T09:49:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6uYFDapx6Qd/y/ZDS0HLMtwqYa4LUq2PkX9j/Na0cFhLaIwXxRKPXfqydcl2aHN4OTmb0vU+e7CIDAKYwmw6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T03:50:59.833319Z"},"content_sha256":"2364e1d069f36750de38e205a4bc440fa0461add8142d57e6e52739cc8b7a4b1","schema_version":"1.0","event_id":"sha256:2364e1d069f36750de38e205a4bc440fa0461add8142d57e6e52739cc8b7a4b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4PAF3LSZYI7L6SRHI46NONRPVP/bundle.json","state_url":"https://pith.science/pith/4PAF3LSZYI7L6SRHI46NONRPVP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4PAF3LSZYI7L6SRHI46NONRPVP/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":"2026-08-12T03:50:59Z","links":{"resolver":"https://pith.science/pith/4PAF3LSZYI7L6SRHI46NONRPVP","bundle":"https://pith.science/pith/4PAF3LSZYI7L6SRHI46NONRPVP/bundle.json","state":"https://pith.science/pith/4PAF3LSZYI7L6SRHI46NONRPVP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4PAF3LSZYI7L6SRHI46NONRPVP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4PAF3LSZYI7L6SRHI46NONRPVP","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":"958d4209c4da4a67cb8276eddf6e9887a7dcf1e3108521ad09d2c26974cd40ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T14:30:05Z","title_canon_sha256":"1599c47ef44a8cfd862447d9107608a745bdfdfd194775519990eb6b607f3bd9"},"schema_version":"1.0","source":{"id":"2412.10840","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10840","created_at":"2026-07-05T09:49:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10840v1","created_at":"2026-07-05T09:49:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10840","created_at":"2026-07-05T09:49:23Z"},{"alias_kind":"pith_short_12","alias_value":"4PAF3LSZYI7L","created_at":"2026-07-05T09:49:23Z"},{"alias_kind":"pith_short_16","alias_value":"4PAF3LSZYI7L6SRH","created_at":"2026-07-05T09:49:23Z"},{"alias_kind":"pith_short_8","alias_value":"4PAF3LSZ","created_at":"2026-07-05T09:49:23Z"}],"graph_snapshots":[{"event_id":"sha256:2364e1d069f36750de38e205a4bc440fa0461add8142d57e6e52739cc8b7a4b1","target":"graph","created_at":"2026-07-05T09:49:23Z","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/2412.10840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Multimodal Large Language Models (MLLMs) have generated significant interest in their ability to autonomously interact with and interpret Graphical User Interfaces (GUIs). A major challenge in these systems is grounding-accurately identifying critical GUI components such as text or icons based on a GUI image and a corresponding text query. Traditionally, this task has relied on fine-tuning MLLMs with specialized training data to predict component locations directly. However, in this paper, we propose a novel Tuning-free Attention-driven Grounding (TAG) method that levera","authors_text":"Hai-Ming Xu, Lei Wang, Lingqiao Liu, Qi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T14:30:05Z","title":"Attention-driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models without Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10840","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":"sha256:93bac5f685f4d9b533277bc5d776d6418e42f0062c0af098ad0ae625b555e08d","target":"record","created_at":"2026-07-05T09:49:23Z","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":"958d4209c4da4a67cb8276eddf6e9887a7dcf1e3108521ad09d2c26974cd40ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T14:30:05Z","title_canon_sha256":"1599c47ef44a8cfd862447d9107608a745bdfdfd194775519990eb6b607f3bd9"},"schema_version":"1.0","source":{"id":"2412.10840","kind":"arxiv","version":1}},"canonical_sha256":"e3c05dae59c23ebf4a27473cd7362fabc21720dd748a794357c2cfe21aed827f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3c05dae59c23ebf4a27473cd7362fabc21720dd748a794357c2cfe21aed827f","first_computed_at":"2026-07-05T09:49:23.382273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:23.382273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qmVDTwrW2uZyV3bty0VWdesOxpXQ5bJbcKwlvcVdcCMfjoy82YQaQYrK4RWLnbr8FGEyHlilffEtbXcAq0qJBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:23.382728Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10840","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93bac5f685f4d9b533277bc5d776d6418e42f0062c0af098ad0ae625b555e08d","sha256:2364e1d069f36750de38e205a4bc440fa0461add8142d57e6e52739cc8b7a4b1"],"state_sha256":"154f7f2d3e927f426489e4568d34831bb7403521b09f791cb65f9a2634d14228"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uPu9c3vQtPiPcN8zndgBc7LTlj4nDuuIUSLVorx9kV02Iurh7Q3SXLk0P6Ip+30PQDtP/XW74RNyYqC9dIpRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T03:50:59.841627Z","bundle_sha256":"bcc56bcc2ecb29a63e689c514818941fa408ea9518215c69a0a56ba0a137ef87"}}