{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5XKNML4SBFWJHVPCTD7TAUHIQU","short_pith_number":"pith:5XKNML4S","schema_version":"1.0","canonical_sha256":"edd4d62f92096c93d5e298ff3050e88528482bd8306d10164c83fd093ef0618e","source":{"kind":"arxiv","id":"2406.07113","version":4},"attestation_state":"computed","paper":{"title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aleksei Valenkov, Dmitry Yudin, Maxim Monastyrny, Roman Titkov, Sergey Linok, Svetlana Ladanova, Tatiana Zemskova","submitted_at":"2024-06-11T09:57:04Z","abstract_excerpt":"Locating objects described in natural language presents a significant challenge for autonomous agents. Existing CLIP-based open-vocabulary methods successfully perform 3D object grounding with simple (bare) queries, but cannot cope with ambiguous descriptions that demand an understanding of object relations. To tackle this problem, we propose a modular approach called BBQ (Beyond Bare Queries), which constructs 3D scene graph representation with metric and semantic spatial edges and utilizes a large language model as a human-to-agent interface through our deductive scene reasoning algorithm. B"},"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":"2406.07113","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T09:57:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f318bbfb8cc34a621688a385a5d4f36d994d20a0246b5955ffac47e6267c7d06","abstract_canon_sha256":"a6aca4875d171ba4f0ca68260cf7e6512a98d9be66018c72bf0ebfec1cc683a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:00.779402Z","signature_b64":"I+C2tPN7aFOdZaYEKpOui38N16phgghtO/i2TNZfbShiuMxDRy+feJhkVqc07SOBR2NGm3LMdvdDAn0axL3KDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edd4d62f92096c93d5e298ff3050e88528482bd8306d10164c83fd093ef0618e","last_reissued_at":"2026-07-05T10:59:00.778909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:00.778909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aleksei Valenkov, Dmitry Yudin, Maxim Monastyrny, Roman Titkov, Sergey Linok, Svetlana Ladanova, Tatiana Zemskova","submitted_at":"2024-06-11T09:57:04Z","abstract_excerpt":"Locating objects described in natural language presents a significant challenge for autonomous agents. Existing CLIP-based open-vocabulary methods successfully perform 3D object grounding with simple (bare) queries, but cannot cope with ambiguous descriptions that demand an understanding of object relations. To tackle this problem, we propose a modular approach called BBQ (Beyond Bare Queries), which constructs 3D scene graph representation with metric and semantic spatial edges and utilizes a large language model as a human-to-agent interface through our deductive scene reasoning algorithm. B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07113","kind":"arxiv","version":4},"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/2406.07113/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":"2406.07113","created_at":"2026-07-05T10:59:00.778966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07113v4","created_at":"2026-07-05T10:59:00.778966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07113","created_at":"2026-07-05T10:59:00.778966+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XKNML4SBFWJ","created_at":"2026-07-05T10:59:00.778966+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XKNML4SBFWJHVPC","created_at":"2026-07-05T10:59:00.778966+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XKNML4S","created_at":"2026-07-05T10:59:00.778966+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26831","citing_title":"OSMa-Bench++: Toward Open-Ended Benchmarking of Semantic Mapping for Manipulation with Prompt-Generated Synthetic Scenes","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21788","citing_title":"SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13654","citing_title":"Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap","ref_index":126,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU","json":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU.json","graph_json":"https://pith.science/api/pith-number/5XKNML4SBFWJHVPCTD7TAUHIQU/graph.json","events_json":"https://pith.science/api/pith-number/5XKNML4SBFWJHVPCTD7TAUHIQU/events.json","paper":"https://pith.science/paper/5XKNML4S"},"agent_actions":{"view_html":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU","download_json":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU.json","view_paper":"https://pith.science/paper/5XKNML4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07113&json=true","fetch_graph":"https://pith.science/api/pith-number/5XKNML4SBFWJHVPCTD7TAUHIQU/graph.json","fetch_events":"https://pith.science/api/pith-number/5XKNML4SBFWJHVPCTD7TAUHIQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU/action/storage_attestation","attest_author":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU/action/author_attestation","sign_citation":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU/action/citation_signature","submit_replication":"https://pith.science/pith/5XKNML4SBFWJHVPCTD7TAUHIQU/action/replication_record"}},"created_at":"2026-07-05T10:59:00.778966+00:00","updated_at":"2026-07-05T10:59:00.778966+00:00"}