{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N5DPKGCDOU6QLSME3WEE6X45JH","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":"95320ead1cfe2ffb21742d08b46ea8ce839a15dbd33afe2a27215b69910beb8f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T04:36:19Z","title_canon_sha256":"ae009e1e44aaab822b972a75eb00255b9a4b5858a9f66bbe1f87c2455ca081c4"},"schema_version":"1.0","source":{"id":"2409.17531","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17531","created_at":"2026-07-05T09:27:05Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17531v2","created_at":"2026-07-05T09:27:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17531","created_at":"2026-07-05T09:27:05Z"},{"alias_kind":"pith_short_12","alias_value":"N5DPKGCDOU6Q","created_at":"2026-07-05T09:27:05Z"},{"alias_kind":"pith_short_16","alias_value":"N5DPKGCDOU6QLSME","created_at":"2026-07-05T09:27:05Z"},{"alias_kind":"pith_short_8","alias_value":"N5DPKGCD","created_at":"2026-07-05T09:27:05Z"}],"graph_snapshots":[{"event_id":"sha256:195dcb8da9637084f54589e15d7c2d1956c21973b555bfbb5c4b953ebc8991dd","target":"graph","created_at":"2026-07-05T09:27:05Z","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/2409.17531/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding is a common vision task that involves grounding descriptive sentences to the corresponding regions of an image. Most existing methods use independent image-text encoding and apply complex hand-crafted modules or encoder-decoder architectures for modal interaction and query reasoning. However, their performance significantly drops when dealing with complex textual expressions. This is because the former paradigm only utilizes limited downstream data to fit the multi-modal feature fusion. Therefore, it is only effective when the textual expressions are relatively simple. In cont","authors_text":"Lingfeng Yang, Ming Dai, Wankou Yang, Yihao Xu, Zhenhua Feng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T04:36:19Z","title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17531","kind":"arxiv","version":2},"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:ad653b03a57446eb6cfcffef5d7b98bcf01ad30052da2d1bf768d706c6c7cbbe","target":"record","created_at":"2026-07-05T09:27:05Z","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":"95320ead1cfe2ffb21742d08b46ea8ce839a15dbd33afe2a27215b69910beb8f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T04:36:19Z","title_canon_sha256":"ae009e1e44aaab822b972a75eb00255b9a4b5858a9f66bbe1f87c2455ca081c4"},"schema_version":"1.0","source":{"id":"2409.17531","kind":"arxiv","version":2}},"canonical_sha256":"6f46f51843753d05c984dd884f5f9d49f7d0e826fc94a81f12af8632b5a1863d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f46f51843753d05c984dd884f5f9d49f7d0e826fc94a81f12af8632b5a1863d","first_computed_at":"2026-07-05T09:27:05.239300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:05.239300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R8yS1rKeaWtci3mWbhnY8bYlnPiH7zvPf/t3Y55/sN+1tFex0cbun70jqX1fTKycCsiA6I+nW8LW7IAv8kf5BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:05.239804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17531","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad653b03a57446eb6cfcffef5d7b98bcf01ad30052da2d1bf768d706c6c7cbbe","sha256:195dcb8da9637084f54589e15d7c2d1956c21973b555bfbb5c4b953ebc8991dd"],"state_sha256":"26027903abde31a5fc4f776451c0dbb19833d078fc5161acb1f2da312af87356"}