{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2T3NOECK75TYKICO2C7H2GUKGU","short_pith_number":"pith:2T3NOECK","schema_version":"1.0","canonical_sha256":"d4f6d7104aff6785204ed0be7d1a8a352b0ccab75dccbdb26b616ccccec02f70","source":{"kind":"arxiv","id":"2310.03923","version":1},"attestation_state":"computed","paper":{"title":"Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Gianfranco Doretto, Kashu Yamazaki, Khoa Vo, Minh Tran, Ngan Le, Taisei Hanyu, Thang Pham","submitted_at":"2023-10-05T21:57:36Z","abstract_excerpt":"Precise 3D environmental mapping is pivotal in robotics. Existing methods often rely on predefined concepts during training or are time-intensive when generating semantic maps. This paper presents Open-Fusion, a groundbreaking approach for real-time open-vocabulary 3D mapping and queryable scene representation using RGB-D data. Open-Fusion harnesses the power of a pre-trained vision-language foundation model (VLFM) for open-set semantic comprehension and employs the Truncated Signed Distance Function (TSDF) for swift 3D scene reconstruction. By leveraging the VLFM, we extract region-based embe"},"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":"2310.03923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T21:57:36Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a79544b87454cb8abb839752c0f217ddbddda44596e3ada30467a1782b4b7214","abstract_canon_sha256":"da7256850fa5917515a4289b4f2c6c2a54e5effbbbdbd489d8cf626cab810236"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:43.005101Z","signature_b64":"ZbAYsBbK8Th0Ag/GhmjjNfIg0NbvuWm9LrjtiCzhJsriZ1gyszcBYfuyo3ln1YzIpKxovzWBNHeCe2C6hEN0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4f6d7104aff6785204ed0be7d1a8a352b0ccab75dccbdb26b616ccccec02f70","last_reissued_at":"2026-07-05T06:57:43.004613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:43.004613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Gianfranco Doretto, Kashu Yamazaki, Khoa Vo, Minh Tran, Ngan Le, Taisei Hanyu, Thang Pham","submitted_at":"2023-10-05T21:57:36Z","abstract_excerpt":"Precise 3D environmental mapping is pivotal in robotics. Existing methods often rely on predefined concepts during training or are time-intensive when generating semantic maps. This paper presents Open-Fusion, a groundbreaking approach for real-time open-vocabulary 3D mapping and queryable scene representation using RGB-D data. Open-Fusion harnesses the power of a pre-trained vision-language foundation model (VLFM) for open-set semantic comprehension and employs the Truncated Signed Distance Function (TSDF) for swift 3D scene reconstruction. By leveraging the VLFM, we extract region-based embe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03923","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/2310.03923/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":"2310.03923","created_at":"2026-07-05T06:57:43.004680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03923v1","created_at":"2026-07-05T06:57:43.004680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03923","created_at":"2026-07-05T06:57:43.004680+00:00"},{"alias_kind":"pith_short_12","alias_value":"2T3NOECK75TY","created_at":"2026-07-05T06:57:43.004680+00:00"},{"alias_kind":"pith_short_16","alias_value":"2T3NOECK75TYKICO","created_at":"2026-07-05T06:57:43.004680+00:00"},{"alias_kind":"pith_short_8","alias_value":"2T3NOECK","created_at":"2026-07-05T06:57:43.004680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03669","citing_title":"FUS3DMaps: Scalable and Accurate Open-Vocabulary Semantic Mapping by 3D Fusion of Voxel- and Instance-Level Layers","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2T3NOECK75TYKICO2C7H2GUKGU","json":"https://pith.science/pith/2T3NOECK75TYKICO2C7H2GUKGU.json","graph_json":"https://pith.science/api/pith-number/2T3NOECK75TYKICO2C7H2GUKGU/graph.json","events_json":"https://pith.science/api/pith-number/2T3NOECK75TYKICO2C7H2GUKGU/events.json","paper":"https://pith.science/paper/2T3NOECK"},"agent_actions":{"view_html":"https://pith.science/pith/2T3NOECK75TYKICO2C7H2GUKGU","download_json":"https://pith.science/pith/2T3NOECK75TYKICO2C7H2GUKGU.json","view_paper":"https://pith.science/paper/2T3NOECK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03923&json=true","fetch_graph":"https://pith.science/api/pith-number/2T3NOECK75TYKICO2C7H2GUKGU/graph.json","fetch_events":"https://pith.science/api/pith-number/2T3NOECK75TYKICO2C7H2GUKGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2T3NOECK75TYKICO2C7H2GUKGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2T3NOECK75TYKICO2C7H2GUKGU/action/storage_attestation","attest_author":"https://pith.science/pith/2T3NOECK75TYKICO2C7H2GUKGU/action/author_attestation","sign_citation":"https://pith.science/pith/2T3NOECK75TYKICO2C7H2GUKGU/action/citation_signature","submit_replication":"https://pith.science/pith/2T3NOECK75TYKICO2C7H2GUKGU/action/replication_record"}},"created_at":"2026-07-05T06:57:43.004680+00:00","updated_at":"2026-07-05T06:57:43.004680+00:00"}