{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RL3YDK4V43VYIQICKARNTDW6U5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"11680142aad0220cac163f1e966a4a701ef09dc24ef739dbbee8b2c29b2723f5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-24T04:51:24Z","title_canon_sha256":"d0d94a2c22f756017c82045a19af2c6cddf76dea8a241af990622e0cab806ef9"},"schema_version":"1.0","source":{"id":"2411.15714","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15714","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15714v1","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15714","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_12","alias_value":"RL3YDK4V43VY","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_16","alias_value":"RL3YDK4V43VYIQIC","created_at":"2026-07-05T09:39:39Z"},{"alias_kind":"pith_short_8","alias_value":"RL3YDK4V","created_at":"2026-07-05T09:39:39Z"}],"graph_snapshots":[{"event_id":"sha256:ca1bc45d9d7197f6f4232f0235ecc4f3b412dcc50cabad70162d124328471758","target":"graph","created_at":"2026-07-05T09:39:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.15714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haoran Li, Houqiang Li, Shi-Yong Chen, Siyi Li, Wengang Zhou, Yonghui Wang, Zhenxing Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-24T04:51:24Z","title":"ROOT: VLM based System for Indoor Scene Understanding and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15714","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4085336a9bfea323681c98d870f4517e25c047acb2d0d312b392b07ca1ab4bd2","target":"record","created_at":"2026-07-05T09:39:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"11680142aad0220cac163f1e966a4a701ef09dc24ef739dbbee8b2c29b2723f5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-24T04:51:24Z","title_canon_sha256":"d0d94a2c22f756017c82045a19af2c6cddf76dea8a241af990622e0cab806ef9"},"schema_version":"1.0","source":{"id":"2411.15714","kind":"arxiv","version":1}},"canonical_sha256":"8af781ab95e6eb8441025022d98edea76df67de4958360ddad9e5278244e1049","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8af781ab95e6eb8441025022d98edea76df67de4958360ddad9e5278244e1049","first_computed_at":"2026-07-05T09:39:39.817993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:39.817993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dg/dxwoPM+vfsFSr68ziQ8tQbcobaUt1Mz8FIpllFZaM8dlTqznDplC6gVtZCraoTQoAK0390VYdTbRJyqD5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:39.818518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15714","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4085336a9bfea323681c98d870f4517e25c047acb2d0d312b392b07ca1ab4bd2","sha256:ca1bc45d9d7197f6f4232f0235ecc4f3b412dcc50cabad70162d124328471758"],"state_sha256":"4dc042ade430ee1802994a4a726fcc919cfa087dfa96be0da4f2326c15337ef1"}