{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A4BJ47AIBURPA5JBCZ5JSD4XSV","short_pith_number":"pith:A4BJ47AI","schema_version":"1.0","canonical_sha256":"07029e7c080d22f07521167a990f97957033c74d61b23d5ddb829b477c6c2ca4","source":{"kind":"arxiv","id":"2508.08781","version":1},"attestation_state":"computed","paper":{"title":"SHREC 2025: Retrieval of Optimal Objects for Multi-modal Enhanced Language and Spatial Assistance (ROOMELSA)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh-Duong Tran, Bao Huynh Thai, Dat Phan Thanh, Dinh-Khoi Vo, Duc-Vu Nguyen, Hien-Long Le-Hoang, Hoang-Phuc Nguyen, Hoang Tran Van, Huy Nguyen Phong, Kim Nguyen, Long Le Bao, Man-Khoi Tran, Minh-Chinh Nguyen, Minh-Huy Le-Hoang, Minh Nguyen Anh, Minh-Quan Ho, Minh-Triet Tran, Ngoc-Long Tran, Nguyen-Khang Le, Nhan Nguyen Viet Thien, Phat Nguyen Thuan, Phu-Hoa Pham, Quang-Thuc Nguyen, Quan Nguyen Hung, Tam V. Nguyen, Thai Hoang Minh, Thang Nguyen Tien, Tien Huynh Viet, Trong-Thuan Nguyen, Trung-Nghia Le, Van-Loc Nguyen, Viet-Tham Huynh, Vinh-Tiep Nguyen","submitted_at":"2025-08-12T09:36:05Z","abstract_excerpt":"Recent 3D retrieval systems are typically designed for simple, controlled scenarios, such as identifying an object from a cropped image or a brief description. However, real-world scenarios are more complex, often requiring the recognition of an object in a cluttered scene based on a vague, free-form description. To this end, we present ROOMELSA, a new benchmark designed to evaluate a system's ability to interpret natural language. Specifically, ROOMELSA attends to a specific region within a panoramic room image and accurately retrieves the corresponding 3D model from a large database. In addi"},"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":"2508.08781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T09:36:05Z","cross_cats_sorted":[],"title_canon_sha256":"a31da6cf79ea29c59e4f17c0f2053703aacf7ceffedd98a548ac56e92d646f2c","abstract_canon_sha256":"b75e2f0f9d7d27b9e12f9d7e552d61d35c792ff4d7df721c911bfb886bd64dfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:34.122965Z","signature_b64":"Xt6STXUuA9FwUkhnZfIzK9Ql5gJ7Eg18SZ4qbBfhb24nnlK46E7jkFpNSSU64ASVZTrut8g+WwfS3hl2ReE9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07029e7c080d22f07521167a990f97957033c74d61b23d5ddb829b477c6c2ca4","last_reissued_at":"2026-07-05T11:52:34.122444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:34.122444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SHREC 2025: Retrieval of Optimal Objects for Multi-modal Enhanced Language and Spatial Assistance (ROOMELSA)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh-Duong Tran, Bao Huynh Thai, Dat Phan Thanh, Dinh-Khoi Vo, Duc-Vu Nguyen, Hien-Long Le-Hoang, Hoang-Phuc Nguyen, Hoang Tran Van, Huy Nguyen Phong, Kim Nguyen, Long Le Bao, Man-Khoi Tran, Minh-Chinh Nguyen, Minh-Huy Le-Hoang, Minh Nguyen Anh, Minh-Quan Ho, Minh-Triet Tran, Ngoc-Long Tran, Nguyen-Khang Le, Nhan Nguyen Viet Thien, Phat Nguyen Thuan, Phu-Hoa Pham, Quang-Thuc Nguyen, Quan Nguyen Hung, Tam V. Nguyen, Thai Hoang Minh, Thang Nguyen Tien, Tien Huynh Viet, Trong-Thuan Nguyen, Trung-Nghia Le, Van-Loc Nguyen, Viet-Tham Huynh, Vinh-Tiep Nguyen","submitted_at":"2025-08-12T09:36:05Z","abstract_excerpt":"Recent 3D retrieval systems are typically designed for simple, controlled scenarios, such as identifying an object from a cropped image or a brief description. However, real-world scenarios are more complex, often requiring the recognition of an object in a cluttered scene based on a vague, free-form description. To this end, we present ROOMELSA, a new benchmark designed to evaluate a system's ability to interpret natural language. Specifically, ROOMELSA attends to a specific region within a panoramic room image and accurately retrieves the corresponding 3D model from a large database. In addi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08781","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/2508.08781/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":"2508.08781","created_at":"2026-07-05T11:52:34.122509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08781v1","created_at":"2026-07-05T11:52:34.122509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08781","created_at":"2026-07-05T11:52:34.122509+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4BJ47AIBURP","created_at":"2026-07-05T11:52:34.122509+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4BJ47AIBURPA5JB","created_at":"2026-07-05T11:52:34.122509+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4BJ47AI","created_at":"2026-07-05T11:52:34.122509+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/A4BJ47AIBURPA5JBCZ5JSD4XSV","json":"https://pith.science/pith/A4BJ47AIBURPA5JBCZ5JSD4XSV.json","graph_json":"https://pith.science/api/pith-number/A4BJ47AIBURPA5JBCZ5JSD4XSV/graph.json","events_json":"https://pith.science/api/pith-number/A4BJ47AIBURPA5JBCZ5JSD4XSV/events.json","paper":"https://pith.science/paper/A4BJ47AI"},"agent_actions":{"view_html":"https://pith.science/pith/A4BJ47AIBURPA5JBCZ5JSD4XSV","download_json":"https://pith.science/pith/A4BJ47AIBURPA5JBCZ5JSD4XSV.json","view_paper":"https://pith.science/paper/A4BJ47AI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08781&json=true","fetch_graph":"https://pith.science/api/pith-number/A4BJ47AIBURPA5JBCZ5JSD4XSV/graph.json","fetch_events":"https://pith.science/api/pith-number/A4BJ47AIBURPA5JBCZ5JSD4XSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4BJ47AIBURPA5JBCZ5JSD4XSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4BJ47AIBURPA5JBCZ5JSD4XSV/action/storage_attestation","attest_author":"https://pith.science/pith/A4BJ47AIBURPA5JBCZ5JSD4XSV/action/author_attestation","sign_citation":"https://pith.science/pith/A4BJ47AIBURPA5JBCZ5JSD4XSV/action/citation_signature","submit_replication":"https://pith.science/pith/A4BJ47AIBURPA5JBCZ5JSD4XSV/action/replication_record"}},"created_at":"2026-07-05T11:52:34.122509+00:00","updated_at":"2026-07-05T11:52:34.122509+00:00"}