{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SWOKGWPVJHVQBPT3KUMDBPIFHL","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":"74b8a6ea531b78605e1dcdacdb1438bded8cd2e7d957a1aa9416da2e5c0ffee6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:59:56Z","title_canon_sha256":"fa36a8d6e0d13265cd35b637938d284359f0e3ff00345e4c207f3d2a6b2ce5a6"},"schema_version":"1.0","source":{"id":"2505.23766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23766","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23766v1","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23766","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_12","alias_value":"SWOKGWPVJHVQ","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_16","alias_value":"SWOKGWPVJHVQBPT3","created_at":"2026-07-05T11:12:13Z"},{"alias_kind":"pith_short_8","alias_value":"SWOKGWPV","created_at":"2026-07-05T11:12:13Z"}],"graph_snapshots":[{"event_id":"sha256:b945162b7b751e672f7f6023dc65366e785d5502db146e43769037e45be6eb9c","target":"graph","created_at":"2026-07-05T11:12:13Z","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/2505.23766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks, yet they often struggle with vision-centric scenarios where precise visual focus is needed for accurate reasoning. In this paper, we introduce Argus to address these limitations with a new visual attention grounding mechanism. Our approach employs object-centric grounding as visual chain-of-thought signals, enabling more effective goal-conditioned visual attention during multimodal reasoning tasks. Evaluations on diverse benchmarks demonstrate that Argus excels in bot","authors_text":"De-An Huang, Guilin Liu, Jan Kautz, Liang-Yan Gui, Shilong Liu, Shiwei Sheng, Yunze Man, Yu-Xiong Wang, Zhiding Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:59:56Z","title":"Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23766","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:a75e1dd86fea367abfb12ae9b568523e0c14f0aaafb825efce57c352ab29166f","target":"record","created_at":"2026-07-05T11:12:13Z","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":"74b8a6ea531b78605e1dcdacdb1438bded8cd2e7d957a1aa9416da2e5c0ffee6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:59:56Z","title_canon_sha256":"fa36a8d6e0d13265cd35b637938d284359f0e3ff00345e4c207f3d2a6b2ce5a6"},"schema_version":"1.0","source":{"id":"2505.23766","kind":"arxiv","version":1}},"canonical_sha256":"959ca359f549eb00be7b551830bd053ae30d3145034fbbc7378cde047d07d6ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"959ca359f549eb00be7b551830bd053ae30d3145034fbbc7378cde047d07d6ec","first_computed_at":"2026-07-05T11:12:13.959237Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:13.959237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8LY/zbtDdf7KRGkYOEil8l+N85pMbi353yxnIXlQ8XPzWCXZ4JGiOv/D468dKKWGCjt8uGXhlQyWoz7xL/xIAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:13.959717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a75e1dd86fea367abfb12ae9b568523e0c14f0aaafb825efce57c352ab29166f","sha256:b945162b7b751e672f7f6023dc65366e785d5502db146e43769037e45be6eb9c"],"state_sha256":"4221f2656a685346dddb4afca54ade00911a3459bc1aadc1bf9c6616b55faab4"}