{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XHJYGIMM7UMHO72XYFC3WHZD7J","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":"5bfc61b91ac3e77191886da3bdbc9cf65c02f79aed2b6f25de0758e475fd09d5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T10:19:20Z","title_canon_sha256":"55463aae7879da1e272dd93833dc884ce11e34b8f0e842d041b362c51cedfdbf"},"schema_version":"1.0","source":{"id":"2412.19155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19155","created_at":"2026-07-05T09:54:31Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19155v1","created_at":"2026-07-05T09:54:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19155","created_at":"2026-07-05T09:54:31Z"},{"alias_kind":"pith_short_12","alias_value":"XHJYGIMM7UMH","created_at":"2026-07-05T09:54:31Z"},{"alias_kind":"pith_short_16","alias_value":"XHJYGIMM7UMHO72X","created_at":"2026-07-05T09:54:31Z"},{"alias_kind":"pith_short_8","alias_value":"XHJYGIMM","created_at":"2026-07-05T09:54:31Z"}],"graph_snapshots":[{"event_id":"sha256:4142ac2386c2d70a8a7fb42a64944bd9eb9c4beaa03d131f998e0e328b24a604","target":"graph","created_at":"2026-07-05T09:54:31Z","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/2412.19155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Grounding aims to localize the referring object in an image given a natural language expression. Recent advancements in DETR-based visual grounding methods have attracted considerable attention, as they directly predict the coordinates of the target object without relying on additional efforts, such as pre-generated proposal candidates or pre-defined anchor boxes. However, existing research primarily focuses on designing stronger multi-modal decoder, which typically generates learnable queries by random initialization or by using linguistic embeddings. This vanilla query generation appr","authors_text":"Le Wang, Ming Yang, Qingpei Guo, Sanping Zhou, Yabing Wang, Zheng Qin, Zhuotao Tian","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T10:19:20Z","title":"Referencing Where to Focus: Improving VisualGrounding with Referential Query"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19155","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:b5eddfdad6cc3d1ec84e97e6c1acd9667398a91abbad7d57700ec8fee8e077d5","target":"record","created_at":"2026-07-05T09:54:31Z","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":"5bfc61b91ac3e77191886da3bdbc9cf65c02f79aed2b6f25de0758e475fd09d5","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T10:19:20Z","title_canon_sha256":"55463aae7879da1e272dd93833dc884ce11e34b8f0e842d041b362c51cedfdbf"},"schema_version":"1.0","source":{"id":"2412.19155","kind":"arxiv","version":1}},"canonical_sha256":"b9d383218cfd18777f57c145bb1f23fa4645e2bcc13dfe31af13d958d3223b53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9d383218cfd18777f57c145bb1f23fa4645e2bcc13dfe31af13d958d3223b53","first_computed_at":"2026-07-05T09:54:31.599422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:31.599422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vIzqx0gSCLZSWPP5NsA08dRjUDDkcSJtdXWV32Xqr3vwAPMhW1jwbwJjmSvR0BDTIoNq+CMJkgUQOI3tEw2PBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:31.599845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5eddfdad6cc3d1ec84e97e6c1acd9667398a91abbad7d57700ec8fee8e077d5","sha256:4142ac2386c2d70a8a7fb42a64944bd9eb9c4beaa03d131f998e0e328b24a604"],"state_sha256":"3e0051e2ab53b7eefa7bc33945cdac1a2543ddf2e6727ba3a4b72daf6024e7c8"}