{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RL3YDK4V43VYIQICKARNTDW6U5","short_pith_number":"pith:RL3YDK4V","schema_version":"1.0","canonical_sha256":"8af781ab95e6eb8441025022d98edea76df67de4958360ddad9e5278244e1049","source":{"kind":"arxiv","id":"2411.15714","version":1},"attestation_state":"computed","paper":{"title":"ROOT: VLM based System for Indoor Scene Understanding and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Li, Houqiang Li, Shi-Yong Chen, Siyi Li, Wengang Zhou, Yonghui Wang, Zhenxing Zhou","submitted_at":"2024-11-24T04:51:24Z","abstract_excerpt":"Recently, Vision Language Models (VLMs) have experienced significant advancements, yet these models still face challenges in spatial hierarchical reasoning within indoor scenes. In this study, we introduce ROOT, a VLM-based system designed to enhance the analysis of indoor scenes. Specifically, we first develop an iterative object perception algorithm using GPT-4V to detect object entities within indoor scenes. This is followed by employing vision foundation models to acquire additional meta-information about the scene, such as bounding boxes. Building on this foundational data, we propose a s"},"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":"2411.15714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-24T04:51:24Z","cross_cats_sorted":[],"title_canon_sha256":"d0d94a2c22f756017c82045a19af2c6cddf76dea8a241af990622e0cab806ef9","abstract_canon_sha256":"11680142aad0220cac163f1e966a4a701ef09dc24ef739dbbee8b2c29b2723f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:39.818518Z","signature_b64":"dg/dxwoPM+vfsFSr68ziQ8tQbcobaUt1Mz8FIpllFZaM8dlTqznDplC6gVtZCraoTQoAK0390VYdTbRJyqD5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8af781ab95e6eb8441025022d98edea76df67de4958360ddad9e5278244e1049","last_reissued_at":"2026-07-05T09:39:39.817993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:39.817993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ROOT: VLM based System for Indoor Scene Understanding and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Li, Houqiang Li, Shi-Yong Chen, Siyi Li, Wengang Zhou, Yonghui Wang, Zhenxing Zhou","submitted_at":"2024-11-24T04:51:24Z","abstract_excerpt":"Recently, Vision Language Models (VLMs) have experienced significant advancements, yet these models still face challenges in spatial hierarchical reasoning within indoor scenes. In this study, we introduce ROOT, a VLM-based system designed to enhance the analysis of indoor scenes. Specifically, we first develop an iterative object perception algorithm using GPT-4V to detect object entities within indoor scenes. This is followed by employing vision foundation models to acquire additional meta-information about the scene, such as bounding boxes. Building on this foundational data, we propose a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15714","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/2411.15714/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":"2411.15714","created_at":"2026-07-05T09:39:39.818052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15714v1","created_at":"2026-07-05T09:39:39.818052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15714","created_at":"2026-07-05T09:39:39.818052+00:00"},{"alias_kind":"pith_short_12","alias_value":"RL3YDK4V43VY","created_at":"2026-07-05T09:39:39.818052+00:00"},{"alias_kind":"pith_short_16","alias_value":"RL3YDK4V43VYIQIC","created_at":"2026-07-05T09:39:39.818052+00:00"},{"alias_kind":"pith_short_8","alias_value":"RL3YDK4V","created_at":"2026-07-05T09:39:39.818052+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/RL3YDK4V43VYIQICKARNTDW6U5","json":"https://pith.science/pith/RL3YDK4V43VYIQICKARNTDW6U5.json","graph_json":"https://pith.science/api/pith-number/RL3YDK4V43VYIQICKARNTDW6U5/graph.json","events_json":"https://pith.science/api/pith-number/RL3YDK4V43VYIQICKARNTDW6U5/events.json","paper":"https://pith.science/paper/RL3YDK4V"},"agent_actions":{"view_html":"https://pith.science/pith/RL3YDK4V43VYIQICKARNTDW6U5","download_json":"https://pith.science/pith/RL3YDK4V43VYIQICKARNTDW6U5.json","view_paper":"https://pith.science/paper/RL3YDK4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15714&json=true","fetch_graph":"https://pith.science/api/pith-number/RL3YDK4V43VYIQICKARNTDW6U5/graph.json","fetch_events":"https://pith.science/api/pith-number/RL3YDK4V43VYIQICKARNTDW6U5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RL3YDK4V43VYIQICKARNTDW6U5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RL3YDK4V43VYIQICKARNTDW6U5/action/storage_attestation","attest_author":"https://pith.science/pith/RL3YDK4V43VYIQICKARNTDW6U5/action/author_attestation","sign_citation":"https://pith.science/pith/RL3YDK4V43VYIQICKARNTDW6U5/action/citation_signature","submit_replication":"https://pith.science/pith/RL3YDK4V43VYIQICKARNTDW6U5/action/replication_record"}},"created_at":"2026-07-05T09:39:39.818052+00:00","updated_at":"2026-07-05T09:39:39.818052+00:00"}