{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FLVMAFY4ZPJBNOMQ2C5XUZ5BBP","short_pith_number":"pith:FLVMAFY4","schema_version":"1.0","canonical_sha256":"2aeac0171ccbd216b990d0bb7a67a10bc9a5bd1b25d5bb3a66031f89f987f966","source":{"kind":"arxiv","id":"2507.12123","version":1},"attestation_state":"computed","paper":{"title":"Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gleb Naumov, Sergey Linok","submitted_at":"2025-07-16T10:47:12Z","abstract_excerpt":"We propose OVIGo-3DHSG method - Open-Vocabulary Indoor Grounding of objects using 3D Hierarchical Scene Graph. OVIGo-3DHSG represents an extensive indoor environment over a Hierarchical Scene Graph derived from sequences of RGB-D frames utilizing a set of open-vocabulary foundation models and sensor data processing. The hierarchical representation explicitly models spatial relations across floors, rooms, locations, and objects. To effectively address complex queries involving spatial reference to other objects, we integrate the hierarchical scene graph with a Large Language Model for multistep"},"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":"2507.12123","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T10:47:12Z","cross_cats_sorted":[],"title_canon_sha256":"b36723e0cd047cb81801cf4363987b4d0ccc09f5321953e11b7240fbea754b73","abstract_canon_sha256":"3b1561728e9a45403ba1e65447159d1b5dc93e970ddae2d405b2793ec241b3e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:14.884199Z","signature_b64":"1FyWykN81YF1uXgwqWhsY+oWgGZJ52r5l2VQverLcRctr87THX/1/aiw63X5Gm/5005gQBn+Pi2ojHou5/GqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2aeac0171ccbd216b990d0bb7a67a10bc9a5bd1b25d5bb3a66031f89f987f966","last_reissued_at":"2026-07-05T11:38:14.883659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:14.883659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gleb Naumov, Sergey Linok","submitted_at":"2025-07-16T10:47:12Z","abstract_excerpt":"We propose OVIGo-3DHSG method - Open-Vocabulary Indoor Grounding of objects using 3D Hierarchical Scene Graph. OVIGo-3DHSG represents an extensive indoor environment over a Hierarchical Scene Graph derived from sequences of RGB-D frames utilizing a set of open-vocabulary foundation models and sensor data processing. The hierarchical representation explicitly models spatial relations across floors, rooms, locations, and objects. To effectively address complex queries involving spatial reference to other objects, we integrate the hierarchical scene graph with a Large Language Model for multistep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12123","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/2507.12123/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":"2507.12123","created_at":"2026-07-05T11:38:14.883750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12123v1","created_at":"2026-07-05T11:38:14.883750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12123","created_at":"2026-07-05T11:38:14.883750+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLVMAFY4ZPJB","created_at":"2026-07-05T11:38:14.883750+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLVMAFY4ZPJBNOMQ","created_at":"2026-07-05T11:38:14.883750+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLVMAFY4","created_at":"2026-07-05T11:38:14.883750+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/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP","json":"https://pith.science/pith/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP.json","graph_json":"https://pith.science/api/pith-number/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP/graph.json","events_json":"https://pith.science/api/pith-number/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP/events.json","paper":"https://pith.science/paper/FLVMAFY4"},"agent_actions":{"view_html":"https://pith.science/pith/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP","download_json":"https://pith.science/pith/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP.json","view_paper":"https://pith.science/paper/FLVMAFY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12123&json=true","fetch_graph":"https://pith.science/api/pith-number/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP/graph.json","fetch_events":"https://pith.science/api/pith-number/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP/action/storage_attestation","attest_author":"https://pith.science/pith/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP/action/author_attestation","sign_citation":"https://pith.science/pith/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP/action/citation_signature","submit_replication":"https://pith.science/pith/FLVMAFY4ZPJBNOMQ2C5XUZ5BBP/action/replication_record"}},"created_at":"2026-07-05T11:38:14.883750+00:00","updated_at":"2026-07-05T11:38:14.883750+00:00"}