{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KH7FCWR5MKMOSPF4PSNZL7BBIO","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":"14ff29606c38179cb21ae1e114882e0d755210d998899c1686336da3db0f22b1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-08T17:24:42Z","title_canon_sha256":"a38cb8808b7f7f462b1ebcf4a6637d7bdeaff40717f0f640b33db387b4528a4d"},"schema_version":"1.0","source":{"id":"2503.06287","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06287","created_at":"2026-07-05T10:27:29Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06287v1","created_at":"2026-07-05T10:27:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06287","created_at":"2026-07-05T10:27:29Z"},{"alias_kind":"pith_short_12","alias_value":"KH7FCWR5MKMO","created_at":"2026-07-05T10:27:29Z"},{"alias_kind":"pith_short_16","alias_value":"KH7FCWR5MKMOSPF4","created_at":"2026-07-05T10:27:29Z"},{"alias_kind":"pith_short_8","alias_value":"KH7FCWR5","created_at":"2026-07-05T10:27:29Z"}],"graph_snapshots":[{"event_id":"sha256:88ddc53f1d3a3d1a026272070ab88c5c48567ead36808c3d3ab16db2e4df0990","target":"graph","created_at":"2026-07-05T10:27:29Z","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/2503.06287/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual grounding seeks to localize the image region corresponding to a free-form text description. Recently, the strong multimodal capabilities of Large Vision-Language Models (LVLMs) have driven substantial improvements in visual grounding, though they inevitably require fine-tuning and additional model components to explicitly generate bounding boxes or segmentation masks. However, we discover that a few attention heads in frozen LVLMs demonstrate strong visual grounding capabilities. We refer to these heads, which consistently capture object locations related to text semantics, as localizat","authors_text":"Jinyeong Kim, Junhyeok Kim, Seil Kang, Seong Jae Hwang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-08T17:24:42Z","title":"Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06287","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:b1ea81d5047d17bad640ee22d76da8ac34a40451f5affa28d67820b42e1f0384","target":"record","created_at":"2026-07-05T10:27:29Z","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":"14ff29606c38179cb21ae1e114882e0d755210d998899c1686336da3db0f22b1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-08T17:24:42Z","title_canon_sha256":"a38cb8808b7f7f462b1ebcf4a6637d7bdeaff40717f0f640b33db387b4528a4d"},"schema_version":"1.0","source":{"id":"2503.06287","kind":"arxiv","version":1}},"canonical_sha256":"51fe515a3d6298e93cbc7c9b95fc2143869308f69df740428d9c69f221db0ffb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51fe515a3d6298e93cbc7c9b95fc2143869308f69df740428d9c69f221db0ffb","first_computed_at":"2026-07-05T10:27:29.839467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:29.839467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+x/otuNGenHbMb94fsCt6ZgFeINskJJSmOU8bgM79+3UDwC83ysy+11+WaCA3CVRcJSXT+Ld7KdNk95AL3+QBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:29.840087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.06287","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1ea81d5047d17bad640ee22d76da8ac34a40451f5affa28d67820b42e1f0384","sha256:88ddc53f1d3a3d1a026272070ab88c5c48567ead36808c3d3ab16db2e4df0990"],"state_sha256":"4dfcfb5e95ddc168ccf63f8b905d39e20219e20422493f67e2ae6d9cf774917f"}