{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:USGXBGTPRGIFB36FOO4PYPLL7F","short_pith_number":"pith:USGXBGTP","schema_version":"1.0","canonical_sha256":"a48d709a6f899050efc573b8fc3d6bf97b954b171ad4c425e64881a7244f6a38","source":{"kind":"arxiv","id":"2309.15940","version":1},"attestation_state":"computed","paper":{"title":"Context-Aware Entity Grounding with Open-Vocabulary 3D Scene Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Abdeslam Boularias, Adeeb Abbas, Eric Jing, Haonan Chang, Kostas Bekris, Kowndinya Boyalakuntla, Lifeng Zhou, Shijie Geng, Shiyang Lu, Shreesh Keskar, Siwei Cai","submitted_at":"2023-09-27T18:32:29Z","abstract_excerpt":"We present an Open-Vocabulary 3D Scene Graph (OVSG), a formal framework for grounding a variety of entities, such as object instances, agents, and regions, with free-form text-based queries. Unlike conventional semantic-based object localization approaches, our system facilitates context-aware entity localization, allowing for queries such as ``pick up a cup on a kitchen table\" or ``navigate to a sofa on which someone is sitting\". In contrast to existing research on 3D scene graphs, OVSG supports free-form text input and open-vocabulary querying. Through a series of comparative experiments usi"},"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":"2309.15940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-27T18:32:29Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b4e8f132c0c954f51a22b432f7896593d93e4e56eeb60c0cec63cd992f6cffc2","abstract_canon_sha256":"7a116c88f97c27e1962ffeea098e4f764bfbb8c8e14d090ba714c5a75d9687a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:09.041960Z","signature_b64":"cQ2daiNIKM8H0m+uvJaHMLZdJDlGwSDvGOtaGzLhk6wknSyj3k2RNajJzNw5iMkd+UtCHYlhRSq9LW4bEZhWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a48d709a6f899050efc573b8fc3d6bf97b954b171ad4c425e64881a7244f6a38","last_reissued_at":"2026-07-05T06:55:09.041480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:09.041480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Aware Entity Grounding with Open-Vocabulary 3D Scene Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Abdeslam Boularias, Adeeb Abbas, Eric Jing, Haonan Chang, Kostas Bekris, Kowndinya Boyalakuntla, Lifeng Zhou, Shijie Geng, Shiyang Lu, Shreesh Keskar, Siwei Cai","submitted_at":"2023-09-27T18:32:29Z","abstract_excerpt":"We present an Open-Vocabulary 3D Scene Graph (OVSG), a formal framework for grounding a variety of entities, such as object instances, agents, and regions, with free-form text-based queries. Unlike conventional semantic-based object localization approaches, our system facilitates context-aware entity localization, allowing for queries such as ``pick up a cup on a kitchen table\" or ``navigate to a sofa on which someone is sitting\". In contrast to existing research on 3D scene graphs, OVSG supports free-form text input and open-vocabulary querying. Through a series of comparative experiments usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15940","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/2309.15940/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":"2309.15940","created_at":"2026-07-05T06:55:09.041542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15940v1","created_at":"2026-07-05T06:55:09.041542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15940","created_at":"2026-07-05T06:55:09.041542+00:00"},{"alias_kind":"pith_short_12","alias_value":"USGXBGTPRGIF","created_at":"2026-07-05T06:55:09.041542+00:00"},{"alias_kind":"pith_short_16","alias_value":"USGXBGTPRGIFB36F","created_at":"2026-07-05T06:55:09.041542+00:00"},{"alias_kind":"pith_short_8","alias_value":"USGXBGTP","created_at":"2026-07-05T06:55:09.041542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23312","citing_title":"From Pixels to Concepts: Growing Rich 3D Semantic Scene Graph Forests utilizing Foundation Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01072","citing_title":"Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/USGXBGTPRGIFB36FOO4PYPLL7F","json":"https://pith.science/pith/USGXBGTPRGIFB36FOO4PYPLL7F.json","graph_json":"https://pith.science/api/pith-number/USGXBGTPRGIFB36FOO4PYPLL7F/graph.json","events_json":"https://pith.science/api/pith-number/USGXBGTPRGIFB36FOO4PYPLL7F/events.json","paper":"https://pith.science/paper/USGXBGTP"},"agent_actions":{"view_html":"https://pith.science/pith/USGXBGTPRGIFB36FOO4PYPLL7F","download_json":"https://pith.science/pith/USGXBGTPRGIFB36FOO4PYPLL7F.json","view_paper":"https://pith.science/paper/USGXBGTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15940&json=true","fetch_graph":"https://pith.science/api/pith-number/USGXBGTPRGIFB36FOO4PYPLL7F/graph.json","fetch_events":"https://pith.science/api/pith-number/USGXBGTPRGIFB36FOO4PYPLL7F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USGXBGTPRGIFB36FOO4PYPLL7F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USGXBGTPRGIFB36FOO4PYPLL7F/action/storage_attestation","attest_author":"https://pith.science/pith/USGXBGTPRGIFB36FOO4PYPLL7F/action/author_attestation","sign_citation":"https://pith.science/pith/USGXBGTPRGIFB36FOO4PYPLL7F/action/citation_signature","submit_replication":"https://pith.science/pith/USGXBGTPRGIFB36FOO4PYPLL7F/action/replication_record"}},"created_at":"2026-07-05T06:55:09.041542+00:00","updated_at":"2026-07-05T06:55:09.041542+00:00"}