{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EI4WX4QYA4XVAHU7ORKD4NYZOF","short_pith_number":"pith:EI4WX4QY","schema_version":"1.0","canonical_sha256":"22396bf218072f501e9f74543e3719715f09f4ca76993c1cfbb619a3dfcfd03e","source":{"kind":"arxiv","id":"2605.21788","version":1},"attestation_state":"computed","paper":{"title":"SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Brendan Crowe, Christoffer Heckman, Doncey Albin, Xuefei Sun, Xujia Zhang","submitted_at":"2026-05-20T22:30:51Z","abstract_excerpt":"Zero-shot 3D visual grounding requires localizing objects in unstructured environments from free-form natural language. Recent vision-language model (VLM) approaches achieve promising results but rely on view-dependent reasoning or implicit representations, limiting spatial consistency and interpretability for compositional queries. We propose SceneGraphGrounder, a framework that reformulates 3D grounding as structured graph matching over a reconstructed 3D scene graph. To enable this formulation, we introduce a visual marker prompting strategy that enables a VLM to infer object-object relatio"},"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":"2605.21788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T22:30:51Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"29e5f99aa779767fc76481df8a112687199659d4a425010f26053ef62f12c660","abstract_canon_sha256":"3679eb95284592a7e57530aa095be18d104340d2541501aa2549e72c22cc9cc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:32.470826Z","signature_b64":"deiZA7MzSDX9cDVCWeLNjUQoW/BQaD7p/72b7HKHis+vDZvaKD6llXpk53nKnMzsox052yoJQLM6S6BquaekAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22396bf218072f501e9f74543e3719715f09f4ca76993c1cfbb619a3dfcfd03e","last_reissued_at":"2026-05-22T01:03:32.470159Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:32.470159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Brendan Crowe, Christoffer Heckman, Doncey Albin, Xuefei Sun, Xujia Zhang","submitted_at":"2026-05-20T22:30:51Z","abstract_excerpt":"Zero-shot 3D visual grounding requires localizing objects in unstructured environments from free-form natural language. Recent vision-language model (VLM) approaches achieve promising results but rely on view-dependent reasoning or implicit representations, limiting spatial consistency and interpretability for compositional queries. We propose SceneGraphGrounder, a framework that reformulates 3D grounding as structured graph matching over a reconstructed 3D scene graph. To enable this formulation, we introduce a visual marker prompting strategy that enables a VLM to infer object-object relatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21788","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/2605.21788/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":"2605.21788","created_at":"2026-05-22T01:03:32.470244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21788v1","created_at":"2026-05-22T01:03:32.470244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21788","created_at":"2026-05-22T01:03:32.470244+00:00"},{"alias_kind":"pith_short_12","alias_value":"EI4WX4QYA4XV","created_at":"2026-05-22T01:03:32.470244+00:00"},{"alias_kind":"pith_short_16","alias_value":"EI4WX4QYA4XVAHU7","created_at":"2026-05-22T01:03:32.470244+00:00"},{"alias_kind":"pith_short_8","alias_value":"EI4WX4QY","created_at":"2026-05-22T01:03:32.470244+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/EI4WX4QYA4XVAHU7ORKD4NYZOF","json":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF.json","graph_json":"https://pith.science/api/pith-number/EI4WX4QYA4XVAHU7ORKD4NYZOF/graph.json","events_json":"https://pith.science/api/pith-number/EI4WX4QYA4XVAHU7ORKD4NYZOF/events.json","paper":"https://pith.science/paper/EI4WX4QY"},"agent_actions":{"view_html":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF","download_json":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF.json","view_paper":"https://pith.science/paper/EI4WX4QY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21788&json=true","fetch_graph":"https://pith.science/api/pith-number/EI4WX4QYA4XVAHU7ORKD4NYZOF/graph.json","fetch_events":"https://pith.science/api/pith-number/EI4WX4QYA4XVAHU7ORKD4NYZOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF/action/storage_attestation","attest_author":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF/action/author_attestation","sign_citation":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF/action/citation_signature","submit_replication":"https://pith.science/pith/EI4WX4QYA4XVAHU7ORKD4NYZOF/action/replication_record"}},"created_at":"2026-05-22T01:03:32.470244+00:00","updated_at":"2026-05-22T01:03:32.470244+00:00"}