{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VYEQI47WDZVDSJUDHYSIIPKQVG","short_pith_number":"pith:VYEQI47W","schema_version":"1.0","canonical_sha256":"ae090473f61e6a3926833e24843d50a9af83588b83522f0862144abd3e469ab1","source":{"kind":"arxiv","id":"2402.04717","version":1},"attestation_state":"computed","paper":{"title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenguo Lin, Yadong Mu","submitted_at":"2024-02-07T10:09:00Z","abstract_excerpt":"Comprehending natural language instructions is a charming property for 3D indoor scene synthesis systems. Existing methods directly model object joint distributions and express object relations implicitly within a scene, thereby hindering the controllability of generation. We introduce InstructScene, a novel generative framework that integrates a semantic graph prior and a layout decoder to improve controllability and fidelity for 3D scene synthesis. The proposed semantic graph prior jointly learns scene appearances and layout distributions, exhibiting versatility across various downstream tas"},"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":"2402.04717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T10:09:00Z","cross_cats_sorted":[],"title_canon_sha256":"a8764eff3052b889d998eceee35792fefdafd2e2bf036f76eb8c6b5f2b0a5591","abstract_canon_sha256":"c3c7fb34a07357170ab99260ce0d3452385f53b9985d41de1d085e0c5d2d3bc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:31.315715Z","signature_b64":"2YCepHcQIWEF4P4cPIKtq09fg+yeQEjIpJ3vINW2zqd5+qbBqsil0mt8mLk40RqwEyySlq0L/5iwZWmcQV5QDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae090473f61e6a3926833e24843d50a9af83588b83522f0862144abd3e469ab1","last_reissued_at":"2026-07-05T07:42:31.315197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:31.315197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenguo Lin, Yadong Mu","submitted_at":"2024-02-07T10:09:00Z","abstract_excerpt":"Comprehending natural language instructions is a charming property for 3D indoor scene synthesis systems. Existing methods directly model object joint distributions and express object relations implicitly within a scene, thereby hindering the controllability of generation. We introduce InstructScene, a novel generative framework that integrates a semantic graph prior and a layout decoder to improve controllability and fidelity for 3D scene synthesis. The proposed semantic graph prior jointly learns scene appearances and layout distributions, exhibiting versatility across various downstream tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04717","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/2402.04717/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":"2402.04717","created_at":"2026-07-05T07:42:31.315252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04717v1","created_at":"2026-07-05T07:42:31.315252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04717","created_at":"2026-07-05T07:42:31.315252+00:00"},{"alias_kind":"pith_short_12","alias_value":"VYEQI47WDZVD","created_at":"2026-07-05T07:42:31.315252+00:00"},{"alias_kind":"pith_short_16","alias_value":"VYEQI47WDZVDSJUD","created_at":"2026-07-05T07:42:31.315252+00:00"},{"alias_kind":"pith_short_8","alias_value":"VYEQI47W","created_at":"2026-07-05T07:42:31.315252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05392","citing_title":"SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02407","citing_title":"Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07117","citing_title":"Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic Alignment","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2512.11234","citing_title":"RoomPilot: Controllable Indoor Scene Synthesis via Multimodal Semantic Parsing","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16137","citing_title":"STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17102","citing_title":"VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19587","citing_title":"SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16807","citing_title":"DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00503","citing_title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13586","citing_title":"HetScene: Heterogeneity-Aware Diffusion for Dense Indoor Scene Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10772","citing_title":"HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10125","citing_title":"PhyMix: Towards Physically Consistent Single-Image 3D Indoor Scene Generation with Implicit--Explicit Optimization","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06074","citing_title":"Graph-PiT: Enhancing Structural Coherence in Part-Based Image Synthesis via Graph Priors","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VYEQI47WDZVDSJUDHYSIIPKQVG","json":"https://pith.science/pith/VYEQI47WDZVDSJUDHYSIIPKQVG.json","graph_json":"https://pith.science/api/pith-number/VYEQI47WDZVDSJUDHYSIIPKQVG/graph.json","events_json":"https://pith.science/api/pith-number/VYEQI47WDZVDSJUDHYSIIPKQVG/events.json","paper":"https://pith.science/paper/VYEQI47W"},"agent_actions":{"view_html":"https://pith.science/pith/VYEQI47WDZVDSJUDHYSIIPKQVG","download_json":"https://pith.science/pith/VYEQI47WDZVDSJUDHYSIIPKQVG.json","view_paper":"https://pith.science/paper/VYEQI47W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04717&json=true","fetch_graph":"https://pith.science/api/pith-number/VYEQI47WDZVDSJUDHYSIIPKQVG/graph.json","fetch_events":"https://pith.science/api/pith-number/VYEQI47WDZVDSJUDHYSIIPKQVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VYEQI47WDZVDSJUDHYSIIPKQVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VYEQI47WDZVDSJUDHYSIIPKQVG/action/storage_attestation","attest_author":"https://pith.science/pith/VYEQI47WDZVDSJUDHYSIIPKQVG/action/author_attestation","sign_citation":"https://pith.science/pith/VYEQI47WDZVDSJUDHYSIIPKQVG/action/citation_signature","submit_replication":"https://pith.science/pith/VYEQI47WDZVDSJUDHYSIIPKQVG/action/replication_record"}},"created_at":"2026-07-05T07:42:31.315252+00:00","updated_at":"2026-07-05T07:42:31.315252+00:00"}