{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JXHF26ZZFBXTXVJUFH3W6A7DY3","short_pith_number":"pith:JXHF26ZZ","canonical_record":{"source":{"id":"2509.04243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T14:17:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a3c9c1265200c71ee56a1c3e77ab4bcc620b7168b5757391e1bcf128dc475835","abstract_canon_sha256":"a48535d4abdb43a9d73fbdfb27aa63c60134d987964433c91509e9d9eb9477c7"},"schema_version":"1.0"},"canonical_sha256":"4dce5d7b39286f3bd53429f76f03e3c6d301ea337f5e76add6491458a539389c","source":{"kind":"arxiv","id":"2509.04243","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04243","created_at":"2026-07-05T12:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04243v1","created_at":"2026-07-05T12:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04243","created_at":"2026-07-05T12:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"JXHF26ZZFBXT","created_at":"2026-07-05T12:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"JXHF26ZZFBXTXVJU","created_at":"2026-07-05T12:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"JXHF26ZZ","created_at":"2026-07-05T12:04:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JXHF26ZZFBXTXVJUFH3W6A7DY3","target":"record","payload":{"canonical_record":{"source":{"id":"2509.04243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T14:17:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a3c9c1265200c71ee56a1c3e77ab4bcc620b7168b5757391e1bcf128dc475835","abstract_canon_sha256":"a48535d4abdb43a9d73fbdfb27aa63c60134d987964433c91509e9d9eb9477c7"},"schema_version":"1.0"},"canonical_sha256":"4dce5d7b39286f3bd53429f76f03e3c6d301ea337f5e76add6491458a539389c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:56.153648Z","signature_b64":"2rOpO7X6qPEyFAkRu0DNpTMVgPgFXOuU13fzOmZHHEzlFeD0ePW6ScasYYdPmA5C74jo7tw+RCamax3pzv23Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dce5d7b39286f3bd53429f76f03e3c6d301ea337f5e76add6491458a539389c","last_reissued_at":"2026-07-05T12:04:56.153084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:56.153084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.04243","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":"2026-07-05T12:04:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CVRtak9Is9GrbX/67COx1beYsGlq6sbUHwHuhtRMgNTzzaL/6nEJo2qu9JcI6h96w2WwwV1d9MinVxDt69YdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:04:05.134264Z"},"content_sha256":"7659b429759019c7d9830a4d2c2040df881960e3892d5873d62d900711da98c2","schema_version":"1.0","event_id":"sha256:7659b429759019c7d9830a4d2c2040df881960e3892d5873d62d900711da98c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JXHF26ZZFBXTXVJUFH3W6A7DY3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Active Perception via Self-Evolving Preference Optimization for GUI Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guangquan Xue, Juntao Li, Qipeng Huang, Wanfu Wang, Xiaobo Liang","submitted_at":"2025-09-04T14:17:01Z","abstract_excerpt":"Vision Language Models (VLMs) have recently achieved significant progress in bridging visual perception and linguistic reasoning. Recently, OpenAI o3 model introduced a zoom-in search strategy that effectively elicits active perception capabilities in VLMs, improving downstream task performance. However, enabling VLMs to reason effectively over appropriate image regions remains a core challenge in GUI grounding, particularly under high-resolution inputs and complex multi-element visual interactions. In this work, we propose LASER, a self-evolving framework that progressively endows VLMs with m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04243","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/2509.04243/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":"2026-07-05T12:04:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lm7nGUAIuuas/PiwTvE96zWN57NM/BF+AYdNmbuT8HsSNzhvGhx43w7PRpmYBBpgMjQkFkCj69jVfHWrsHEgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:04:05.134647Z"},"content_sha256":"146374d0fe3ce9a1447a774b9e719a22b76f8e7d6f821f168c7afec5f5e0b913","schema_version":"1.0","event_id":"sha256:146374d0fe3ce9a1447a774b9e719a22b76f8e7d6f821f168c7afec5f5e0b913"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JXHF26ZZFBXTXVJUFH3W6A7DY3/bundle.json","state_url":"https://pith.science/pith/JXHF26ZZFBXTXVJUFH3W6A7DY3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JXHF26ZZFBXTXVJUFH3W6A7DY3/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":"2026-08-23T04:04:05Z","links":{"resolver":"https://pith.science/pith/JXHF26ZZFBXTXVJUFH3W6A7DY3","bundle":"https://pith.science/pith/JXHF26ZZFBXTXVJUFH3W6A7DY3/bundle.json","state":"https://pith.science/pith/JXHF26ZZFBXTXVJUFH3W6A7DY3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JXHF26ZZFBXTXVJUFH3W6A7DY3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JXHF26ZZFBXTXVJUFH3W6A7DY3","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":"a48535d4abdb43a9d73fbdfb27aa63c60134d987964433c91509e9d9eb9477c7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T14:17:01Z","title_canon_sha256":"a3c9c1265200c71ee56a1c3e77ab4bcc620b7168b5757391e1bcf128dc475835"},"schema_version":"1.0","source":{"id":"2509.04243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04243","created_at":"2026-07-05T12:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04243v1","created_at":"2026-07-05T12:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04243","created_at":"2026-07-05T12:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"JXHF26ZZFBXT","created_at":"2026-07-05T12:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"JXHF26ZZFBXTXVJU","created_at":"2026-07-05T12:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"JXHF26ZZ","created_at":"2026-07-05T12:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:146374d0fe3ce9a1447a774b9e719a22b76f8e7d6f821f168c7afec5f5e0b913","target":"graph","created_at":"2026-07-05T12:04:56Z","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/2509.04243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) have recently achieved significant progress in bridging visual perception and linguistic reasoning. Recently, OpenAI o3 model introduced a zoom-in search strategy that effectively elicits active perception capabilities in VLMs, improving downstream task performance. However, enabling VLMs to reason effectively over appropriate image regions remains a core challenge in GUI grounding, particularly under high-resolution inputs and complex multi-element visual interactions. In this work, we propose LASER, a self-evolving framework that progressively endows VLMs with m","authors_text":"Guangquan Xue, Juntao Li, Qipeng Huang, Wanfu Wang, Xiaobo Liang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T14:17:01Z","title":"Learning Active Perception via Self-Evolving Preference Optimization for GUI Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04243","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":"sha256:7659b429759019c7d9830a4d2c2040df881960e3892d5873d62d900711da98c2","target":"record","created_at":"2026-07-05T12:04:56Z","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":"a48535d4abdb43a9d73fbdfb27aa63c60134d987964433c91509e9d9eb9477c7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T14:17:01Z","title_canon_sha256":"a3c9c1265200c71ee56a1c3e77ab4bcc620b7168b5757391e1bcf128dc475835"},"schema_version":"1.0","source":{"id":"2509.04243","kind":"arxiv","version":1}},"canonical_sha256":"4dce5d7b39286f3bd53429f76f03e3c6d301ea337f5e76add6491458a539389c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dce5d7b39286f3bd53429f76f03e3c6d301ea337f5e76add6491458a539389c","first_computed_at":"2026-07-05T12:04:56.153084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:56.153084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2rOpO7X6qPEyFAkRu0DNpTMVgPgFXOuU13fzOmZHHEzlFeD0ePW6ScasYYdPmA5C74jo7tw+RCamax3pzv23Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:56.153648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7659b429759019c7d9830a4d2c2040df881960e3892d5873d62d900711da98c2","sha256:146374d0fe3ce9a1447a774b9e719a22b76f8e7d6f821f168c7afec5f5e0b913"],"state_sha256":"7702a43af2ef8897e704e03430f67bb8cd4fc8df9e2327db90efa9b3dfeebfad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AVNf5y4MFEKfPejSniPcMm1LsA1wQsMIHAqsxXsGtPzkhD3V57IlrbYT9I+l2Gve2W1JizroNctRbVzhU1OJBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T04:04:05.137243Z","bundle_sha256":"6341c190b5c42d8293de68d15a4fbc0cd51a2e17b08d43837e7ca854ad2ebcf5"}}