{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:X7CQ6R4UB2H6XTDT5KQF736DDF","short_pith_number":"pith:X7CQ6R4U","canonical_record":{"source":{"id":"2509.04908","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-05T08:24:12Z","cross_cats_sorted":["cs.CL","cs.CV","cs.HC"],"title_canon_sha256":"abf026a6b930d4fe8b1c5739c3aeee037b0a65b297262dfe69c44820e5b7b2a2","abstract_canon_sha256":"6153f4fb13a755090c577d6fcf9f189e80d13d7b51cce07b7c9fe2434535f4ad"},"schema_version":"1.0"},"canonical_sha256":"bfc50f47940e8febcc73eaa05fefc31955e35d67ce99e597387eafb5a585827d","source":{"kind":"arxiv","id":"2509.04908","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04908","created_at":"2026-07-05T12:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04908v1","created_at":"2026-07-05T12:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04908","created_at":"2026-07-05T12:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"X7CQ6R4UB2H6","created_at":"2026-07-05T12:05:32Z"},{"alias_kind":"pith_short_16","alias_value":"X7CQ6R4UB2H6XTDT","created_at":"2026-07-05T12:05:32Z"},{"alias_kind":"pith_short_8","alias_value":"X7CQ6R4U","created_at":"2026-07-05T12:05:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:X7CQ6R4UB2H6XTDT5KQF736DDF","target":"record","payload":{"canonical_record":{"source":{"id":"2509.04908","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-05T08:24:12Z","cross_cats_sorted":["cs.CL","cs.CV","cs.HC"],"title_canon_sha256":"abf026a6b930d4fe8b1c5739c3aeee037b0a65b297262dfe69c44820e5b7b2a2","abstract_canon_sha256":"6153f4fb13a755090c577d6fcf9f189e80d13d7b51cce07b7c9fe2434535f4ad"},"schema_version":"1.0"},"canonical_sha256":"bfc50f47940e8febcc73eaa05fefc31955e35d67ce99e597387eafb5a585827d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:32.059359Z","signature_b64":"mapuXn+Dz604Ae3dwhgGLHf8bBo3EkiJq1j/5tjNZCT0a+o+WuMTpzdd6mA0+oMqmRUIoYzavtsTT0Q2FCH7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfc50f47940e8febcc73eaa05fefc31955e35d67ce99e597387eafb5a585827d","last_reissued_at":"2026-07-05T12:05:32.058842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:32.058842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.04908","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":"2026-07-05T12:05:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zYNwcBm1ObNjKRO98X9+ls0eHdxYIUI0D/qoBltgKUcJ06NPT0wJWlWI/vyOv6PV2HcE0qtkUhujjAyPhE9OBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:46:26.281484Z"},"content_sha256":"f56aea59b771675e2d11a8552887d3c686ba455eb54645a5fc448580184f2832","schema_version":"1.0","event_id":"sha256:f56aea59b771675e2d11a8552887d3c686ba455eb54645a5fc448580184f2832"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:X7CQ6R4UB2H6XTDT5KQF736DDF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SparkUI-Parser: Enhancing GUI Perception with Robust Grounding and Parsing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.HC"],"primary_cat":"cs.AI","authors_text":"Chenguang Ma, Chen Rao, Hongyi Jing, Huaizhong Lin, Jiafu Chen, Jiajie Teng, Juncheng Mo, Lei Zhao, Rui Lv, Shuo Fang, Tianyi Chu, Ziqiang Dang","submitted_at":"2025-09-05T08:24:12Z","abstract_excerpt":"The existing Multimodal Large Language Models (MLLMs) for GUI perception have made great progress. However, the following challenges still exist in prior methods: 1) They model discrete coordinates based on text autoregressive mechanism, which results in lower grounding accuracy and slower inference speed. 2) They can only locate predefined sets of elements and are not capable of parsing the entire interface, which hampers the broad application and support for downstream tasks. To address the above issues, we propose SparkUI-Parser, a novel end-to-end framework where higher localization precis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04908","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/2509.04908/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":"2026-07-05T12:05:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NANXv4O+XIWOhE3JS/IkvkdPac/6NZn6x1cOnwxmdHCmDd95MadhWA4hdgjCvkSaRkLSso1ll62wDngrx0ybAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:46:26.281859Z"},"content_sha256":"f2f0fe0c1783be40258aa0a8fb9c18c6f8ff2c23f2c8007b8f6aeb89b0b6a6f0","schema_version":"1.0","event_id":"sha256:f2f0fe0c1783be40258aa0a8fb9c18c6f8ff2c23f2c8007b8f6aeb89b0b6a6f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X7CQ6R4UB2H6XTDT5KQF736DDF/bundle.json","state_url":"https://pith.science/pith/X7CQ6R4UB2H6XTDT5KQF736DDF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X7CQ6R4UB2H6XTDT5KQF736DDF/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":"2026-07-06T18:46:26Z","links":{"resolver":"https://pith.science/pith/X7CQ6R4UB2H6XTDT5KQF736DDF","bundle":"https://pith.science/pith/X7CQ6R4UB2H6XTDT5KQF736DDF/bundle.json","state":"https://pith.science/pith/X7CQ6R4UB2H6XTDT5KQF736DDF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X7CQ6R4UB2H6XTDT5KQF736DDF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X7CQ6R4UB2H6XTDT5KQF736DDF","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":"6153f4fb13a755090c577d6fcf9f189e80d13d7b51cce07b7c9fe2434535f4ad","cross_cats_sorted":["cs.CL","cs.CV","cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-05T08:24:12Z","title_canon_sha256":"abf026a6b930d4fe8b1c5739c3aeee037b0a65b297262dfe69c44820e5b7b2a2"},"schema_version":"1.0","source":{"id":"2509.04908","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04908","created_at":"2026-07-05T12:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04908v1","created_at":"2026-07-05T12:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04908","created_at":"2026-07-05T12:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"X7CQ6R4UB2H6","created_at":"2026-07-05T12:05:32Z"},{"alias_kind":"pith_short_16","alias_value":"X7CQ6R4UB2H6XTDT","created_at":"2026-07-05T12:05:32Z"},{"alias_kind":"pith_short_8","alias_value":"X7CQ6R4U","created_at":"2026-07-05T12:05:32Z"}],"graph_snapshots":[{"event_id":"sha256:f2f0fe0c1783be40258aa0a8fb9c18c6f8ff2c23f2c8007b8f6aeb89b0b6a6f0","target":"graph","created_at":"2026-07-05T12:05:32Z","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/2509.04908/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The existing Multimodal Large Language Models (MLLMs) for GUI perception have made great progress. However, the following challenges still exist in prior methods: 1) They model discrete coordinates based on text autoregressive mechanism, which results in lower grounding accuracy and slower inference speed. 2) They can only locate predefined sets of elements and are not capable of parsing the entire interface, which hampers the broad application and support for downstream tasks. To address the above issues, we propose SparkUI-Parser, a novel end-to-end framework where higher localization precis","authors_text":"Chenguang Ma, Chen Rao, Hongyi Jing, Huaizhong Lin, Jiafu Chen, Jiajie Teng, Juncheng Mo, Lei Zhao, Rui Lv, Shuo Fang, Tianyi Chu, Ziqiang Dang","cross_cats":["cs.CL","cs.CV","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-05T08:24:12Z","title":"SparkUI-Parser: Enhancing GUI Perception with Robust Grounding and Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04908","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:f56aea59b771675e2d11a8552887d3c686ba455eb54645a5fc448580184f2832","target":"record","created_at":"2026-07-05T12:05:32Z","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":"6153f4fb13a755090c577d6fcf9f189e80d13d7b51cce07b7c9fe2434535f4ad","cross_cats_sorted":["cs.CL","cs.CV","cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-05T08:24:12Z","title_canon_sha256":"abf026a6b930d4fe8b1c5739c3aeee037b0a65b297262dfe69c44820e5b7b2a2"},"schema_version":"1.0","source":{"id":"2509.04908","kind":"arxiv","version":1}},"canonical_sha256":"bfc50f47940e8febcc73eaa05fefc31955e35d67ce99e597387eafb5a585827d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfc50f47940e8febcc73eaa05fefc31955e35d67ce99e597387eafb5a585827d","first_computed_at":"2026-07-05T12:05:32.058842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:32.058842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mapuXn+Dz604Ae3dwhgGLHf8bBo3EkiJq1j/5tjNZCT0a+o+WuMTpzdd6mA0+oMqmRUIoYzavtsTT0Q2FCH7DA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:32.059359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04908","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f56aea59b771675e2d11a8552887d3c686ba455eb54645a5fc448580184f2832","sha256:f2f0fe0c1783be40258aa0a8fb9c18c6f8ff2c23f2c8007b8f6aeb89b0b6a6f0"],"state_sha256":"26051656031ddc2f679a03a5e5f14a3238b882df79a728e1c011c53b4f611cdf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fxTwNmF/skRwyUv4a2VyYyJy+tdRg6W7tiKk8foKWn8LpGz5XWTj89WmworkQCL/H+XPOSyVdrwRXt0BqBOGCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:46:26.283822Z","bundle_sha256":"f466ee45ba91de5b6229377e3314f1a374765a83aed1f5b00073fb15ec14e5e6"}}