{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FNFSF2DYPSORWJRDRNE4CDIHZU","short_pith_number":"pith:FNFSF2DY","canonical_record":{"source":{"id":"2506.03143","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T17:59:08Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"25d0f9eeb0ab44111c578d06d95378387673092f383acd075023cbe5b1ce9049","abstract_canon_sha256":"97ce6041a1b2d9fb9d6b4b29700398d4e562ebcbec0123ad4afbcfbdba166564"},"schema_version":"1.0"},"canonical_sha256":"2b4b22e8787c9d1b26238b49c10d07cd132f6f8f870590612fc647b47888ac2e","source":{"kind":"arxiv","id":"2506.03143","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03143","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03143v1","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03143","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_12","alias_value":"FNFSF2DYPSOR","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_16","alias_value":"FNFSF2DYPSORWJRD","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_8","alias_value":"FNFSF2DY","created_at":"2026-07-05T11:15:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FNFSF2DYPSORWJRDRNE4CDIHZU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03143","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T17:59:08Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"25d0f9eeb0ab44111c578d06d95378387673092f383acd075023cbe5b1ce9049","abstract_canon_sha256":"97ce6041a1b2d9fb9d6b4b29700398d4e562ebcbec0123ad4afbcfbdba166564"},"schema_version":"1.0"},"canonical_sha256":"2b4b22e8787c9d1b26238b49c10d07cd132f6f8f870590612fc647b47888ac2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:15.676523Z","signature_b64":"FZP03/Ra4h0Wzr2UKbZVciUulSM2cBHmATQ2ADeZPR+XfokKohkJkJGGh7j4T5McnqmFp/SwYFtTsnVpY1oaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b4b22e8787c9d1b26238b49c10d07cd132f6f8f870590612fc647b47888ac2e","last_reissued_at":"2026-07-05T11:15:15.676015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:15.676015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03143","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":"2026-07-05T11:15:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PaTHEpfneS0l1Vr/aVAjFv+8ykIRrfbzAyVv4KF5EkODltDP2pjtlAai6ieyz2+069T/y+iXqcOncBnbaLTkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:11:16.461754Z"},"content_sha256":"2dba6d9050b14e4bcd0eee4df76aacbec4d49524b7fcc9dd050c0a1b90170eaf","schema_version":"1.0","event_id":"sha256:2dba6d9050b14e4bcd0eee4df76aacbec4d49524b7fcc9dd050c0a1b90170eaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FNFSF2DYPSORWJRDRNE4CDIHZU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Bo Qiao, Chaoyun Zhang, Dongmei Zhang, Huan Zhang, Huiqiang Jiang, Jianbing Zhang, Jianfeng Gao, Jian Mu, Jianwei Yang, Kanzhi Cheng, Lars Liden, Qianhui Wu, Qingwei Lin, Reuben Tan, Rui Yang, Si Qin, Tong Zhang","submitted_at":"2025-06-03T17:59:08Z","abstract_excerpt":"One of the principal challenges in building VLM-powered GUI agents is visual grounding, i.e., localizing the appropriate screen region for action execution based on both the visual content and the textual plans. Most existing work formulates this as a text-based coordinate generation task. However, these approaches suffer from several limitations: weak spatial-semantic alignment, inability to handle ambiguous supervision targets, and a mismatch between the dense nature of screen coordinates and the coarse, patch-level granularity of visual features extracted by models like Vision Transformers."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03143","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/2506.03143/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":"2026-07-05T11:15:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tr2Y/kHN4u+j7EyGHxa5W8HSFZ4UOZXDWWnrz7c6yn+ij59do3X1JAbOc0345Td1D7gso3IG32zmtN5tNW5aCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:11:16.462400Z"},"content_sha256":"254003fb09f327e7da1350956f2ced969b9fe6986cb62a1d5c30e23538493b4c","schema_version":"1.0","event_id":"sha256:254003fb09f327e7da1350956f2ced969b9fe6986cb62a1d5c30e23538493b4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FNFSF2DYPSORWJRDRNE4CDIHZU/bundle.json","state_url":"https://pith.science/pith/FNFSF2DYPSORWJRDRNE4CDIHZU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FNFSF2DYPSORWJRDRNE4CDIHZU/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":"2026-08-05T11:11:16Z","links":{"resolver":"https://pith.science/pith/FNFSF2DYPSORWJRDRNE4CDIHZU","bundle":"https://pith.science/pith/FNFSF2DYPSORWJRDRNE4CDIHZU/bundle.json","state":"https://pith.science/pith/FNFSF2DYPSORWJRDRNE4CDIHZU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FNFSF2DYPSORWJRDRNE4CDIHZU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FNFSF2DYPSORWJRDRNE4CDIHZU","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":"97ce6041a1b2d9fb9d6b4b29700398d4e562ebcbec0123ad4afbcfbdba166564","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T17:59:08Z","title_canon_sha256":"25d0f9eeb0ab44111c578d06d95378387673092f383acd075023cbe5b1ce9049"},"schema_version":"1.0","source":{"id":"2506.03143","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03143","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03143v1","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03143","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_12","alias_value":"FNFSF2DYPSOR","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_16","alias_value":"FNFSF2DYPSORWJRD","created_at":"2026-07-05T11:15:15Z"},{"alias_kind":"pith_short_8","alias_value":"FNFSF2DY","created_at":"2026-07-05T11:15:15Z"}],"graph_snapshots":[{"event_id":"sha256:254003fb09f327e7da1350956f2ced969b9fe6986cb62a1d5c30e23538493b4c","target":"graph","created_at":"2026-07-05T11:15:15Z","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/2506.03143/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the principal challenges in building VLM-powered GUI agents is visual grounding, i.e., localizing the appropriate screen region for action execution based on both the visual content and the textual plans. Most existing work formulates this as a text-based coordinate generation task. However, these approaches suffer from several limitations: weak spatial-semantic alignment, inability to handle ambiguous supervision targets, and a mismatch between the dense nature of screen coordinates and the coarse, patch-level granularity of visual features extracted by models like Vision Transformers.","authors_text":"Baolin Peng, Bo Qiao, Chaoyun Zhang, Dongmei Zhang, Huan Zhang, Huiqiang Jiang, Jianbing Zhang, Jianfeng Gao, Jian Mu, Jianwei Yang, Kanzhi Cheng, Lars Liden, Qianhui Wu, Qingwei Lin, Reuben Tan, Rui Yang, Si Qin, Tong Zhang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T17:59:08Z","title":"GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03143","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":"sha256:2dba6d9050b14e4bcd0eee4df76aacbec4d49524b7fcc9dd050c0a1b90170eaf","target":"record","created_at":"2026-07-05T11:15:15Z","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":"97ce6041a1b2d9fb9d6b4b29700398d4e562ebcbec0123ad4afbcfbdba166564","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T17:59:08Z","title_canon_sha256":"25d0f9eeb0ab44111c578d06d95378387673092f383acd075023cbe5b1ce9049"},"schema_version":"1.0","source":{"id":"2506.03143","kind":"arxiv","version":1}},"canonical_sha256":"2b4b22e8787c9d1b26238b49c10d07cd132f6f8f870590612fc647b47888ac2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b4b22e8787c9d1b26238b49c10d07cd132f6f8f870590612fc647b47888ac2e","first_computed_at":"2026-07-05T11:15:15.676015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:15.676015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FZP03/Ra4h0Wzr2UKbZVciUulSM2cBHmATQ2ADeZPR+XfokKohkJkJGGh7j4T5McnqmFp/SwYFtTsnVpY1oaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:15.676523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03143","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dba6d9050b14e4bcd0eee4df76aacbec4d49524b7fcc9dd050c0a1b90170eaf","sha256:254003fb09f327e7da1350956f2ced969b9fe6986cb62a1d5c30e23538493b4c"],"state_sha256":"4fff0e29528b5900c156f27bd69d96d395a330e8a424b923382466a8c945db86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"STdX8y29gOR9SQ0K1rr9WdoucEFcJV4FVJQHqVUjNiEBRRJa+JHafFu5Kh7ERiaCWEnnWW+S87ZnP1/NsA63Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:11:16.467594Z","bundle_sha256":"a2d149604c9137fd97c6629d4d5b1a9fd4aa704ef76655c376e3a6646ab0d26c"}}