{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XHJYGIMM7UMHO72XYFC3WHZD7J","short_pith_number":"pith:XHJYGIMM","schema_version":"1.0","canonical_sha256":"b9d383218cfd18777f57c145bb1f23fa4645e2bcc13dfe31af13d958d3223b53","source":{"kind":"arxiv","id":"2412.19155","version":1},"attestation_state":"computed","paper":{"title":"Referencing Where to Focus: Improving VisualGrounding with Referential Query","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Le Wang, Ming Yang, Qingpei Guo, Sanping Zhou, Yabing Wang, Zheng Qin, Zhuotao Tian","submitted_at":"2024-12-26T10:19:20Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.19155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T10:19:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"55463aae7879da1e272dd93833dc884ce11e34b8f0e842d041b362c51cedfdbf","abstract_canon_sha256":"5bfc61b91ac3e77191886da3bdbc9cf65c02f79aed2b6f25de0758e475fd09d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:31.599845Z","signature_b64":"vIzqx0gSCLZSWPP5NsA08dRjUDDkcSJtdXWV32Xqr3vwAPMhW1jwbwJjmSvR0BDTIoNq+CMJkgUQOI3tEw2PBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9d383218cfd18777f57c145bb1f23fa4645e2bcc13dfe31af13d958d3223b53","last_reissued_at":"2026-07-05T09:54:31.599422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:31.599422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Referencing Where to Focus: Improving VisualGrounding with Referential Query","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Le Wang, Ming Yang, Qingpei Guo, Sanping Zhou, Yabing Wang, Zheng Qin, Zhuotao Tian","submitted_at":"2024-12-26T10:19:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19155","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.19155/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.19155","created_at":"2026-07-05T09:54:31.599478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19155v1","created_at":"2026-07-05T09:54:31.599478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19155","created_at":"2026-07-05T09:54:31.599478+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHJYGIMM7UMH","created_at":"2026-07-05T09:54:31.599478+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHJYGIMM7UMHO72X","created_at":"2026-07-05T09:54:31.599478+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHJYGIMM","created_at":"2026-07-05T09:54:31.599478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHJYGIMM7UMHO72XYFC3WHZD7J","json":"https://pith.science/pith/XHJYGIMM7UMHO72XYFC3WHZD7J.json","graph_json":"https://pith.science/api/pith-number/XHJYGIMM7UMHO72XYFC3WHZD7J/graph.json","events_json":"https://pith.science/api/pith-number/XHJYGIMM7UMHO72XYFC3WHZD7J/events.json","paper":"https://pith.science/paper/XHJYGIMM"},"agent_actions":{"view_html":"https://pith.science/pith/XHJYGIMM7UMHO72XYFC3WHZD7J","download_json":"https://pith.science/pith/XHJYGIMM7UMHO72XYFC3WHZD7J.json","view_paper":"https://pith.science/paper/XHJYGIMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19155&json=true","fetch_graph":"https://pith.science/api/pith-number/XHJYGIMM7UMHO72XYFC3WHZD7J/graph.json","fetch_events":"https://pith.science/api/pith-number/XHJYGIMM7UMHO72XYFC3WHZD7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHJYGIMM7UMHO72XYFC3WHZD7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHJYGIMM7UMHO72XYFC3WHZD7J/action/storage_attestation","attest_author":"https://pith.science/pith/XHJYGIMM7UMHO72XYFC3WHZD7J/action/author_attestation","sign_citation":"https://pith.science/pith/XHJYGIMM7UMHO72XYFC3WHZD7J/action/citation_signature","submit_replication":"https://pith.science/pith/XHJYGIMM7UMHO72XYFC3WHZD7J/action/replication_record"}},"created_at":"2026-07-05T09:54:31.599478+00:00","updated_at":"2026-07-05T09:54:31.599478+00:00"}