{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SQ6LMZEVLZS74PRAXOLXEZLTZ5","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":"439ddef1b8241c121b85ffdc72ff582be1415379b898d1dc27eab5c62a0214e0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-20T14:57:31Z","title_canon_sha256":"739e37a30c3145a561b8c3a845e3a70fe940dad241101f9b411ea341419d5f3e"},"schema_version":"1.0","source":{"id":"2404.13400","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13400","created_at":"2026-07-05T09:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13400v2","created_at":"2026-07-05T09:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13400","created_at":"2026-07-05T09:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"SQ6LMZEVLZS7","created_at":"2026-07-05T09:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"SQ6LMZEVLZS74PRA","created_at":"2026-07-05T09:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"SQ6LMZEV","created_at":"2026-07-05T09:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:535b0a1b8555872d7c501e5881941deb2e164637f7d5d9c303ccdcd70ce222ef","target":"graph","created_at":"2026-07-05T09:03:19Z","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/2404.13400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding, which aims to ground a visual region via natural language, is a task that heavily relies on cross-modal alignment. Existing works utilized uni-modal pre-trained models to transfer visual or linguistic knowledge separately while ignoring the multimodal corresponding information. Motivated by recent advancements in contrastive language-image pre-training and low-rank adaptation (LoRA) methods, we aim to solve the grounding task based on multimodal pre-training. However, there exists significant task gaps between pre-training and grounding. Therefore, to address these gaps, we p","authors_text":"Changsheng Xu, Fang Peng, Linhui Xiao, Xiaoshan Yang, Yaowei Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-20T14:57:31Z","title":"HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13400","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:cfa0ecf53cff430f2b98073eae6c627744fce893c88879d7d0d0a3ccbc323e28","target":"record","created_at":"2026-07-05T09:03:19Z","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":"439ddef1b8241c121b85ffdc72ff582be1415379b898d1dc27eab5c62a0214e0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-20T14:57:31Z","title_canon_sha256":"739e37a30c3145a561b8c3a845e3a70fe940dad241101f9b411ea341419d5f3e"},"schema_version":"1.0","source":{"id":"2404.13400","kind":"arxiv","version":2}},"canonical_sha256":"943cb664955e65fe3e20bb97726573cf70a918b8aa0c88eff00221c4c4f7709a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"943cb664955e65fe3e20bb97726573cf70a918b8aa0c88eff00221c4c4f7709a","first_computed_at":"2026-07-05T09:03:19.794460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:19.794460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k1Bw7lXRNySTBL6hW1C4yHZEpAjH8elmt8c7dVAeVeGPUk3sVx1est79SQ0S9aRDCbix/5nXMX0SbZxJrVlPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:19.794955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.13400","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfa0ecf53cff430f2b98073eae6c627744fce893c88879d7d0d0a3ccbc323e28","sha256:535b0a1b8555872d7c501e5881941deb2e164637f7d5d9c303ccdcd70ce222ef"],"state_sha256":"c199412b8d1c26db5c2fb904397c686a39c9a48f2a5c8d0cbafb320069a574c1"}