{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R364ZTBVVCKOTJKLII2JIU2MRO","short_pith_number":"pith:R364ZTBV","schema_version":"1.0","canonical_sha256":"8efdcccc35a894e9a54b423494534c8b8e32a92bef01d10f27191ee6e9eeae0c","source":{"kind":"arxiv","id":"2504.13153","version":1},"attestation_state":"computed","paper":{"title":"Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liujuan Cao, Shaohui Dai, Shengchuan Zhang, Xinyang Li, Yansong Qu, Zheyan Li","submitted_at":"2025-04-17T17:56:07Z","abstract_excerpt":"Bridging natural language and 3D geometry is a crucial step toward flexible, language-driven scene understanding. While recent advances in 3D Gaussian Splatting (3DGS) have enabled fast and high-quality scene reconstruction, research has also explored incorporating open-vocabulary understanding into 3DGS. However, most existing methods require iterative optimization over per-view 2D semantic feature maps, which not only results in inefficiencies but also leads to inconsistent 3D semantics across views. To address these limitations, we introduce a training-free framework that constructs a super"},"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":"2504.13153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T17:56:07Z","cross_cats_sorted":[],"title_canon_sha256":"2218c948cf184c8bf3c4f9bc38d7464a9cdd38c5fd580a315bd8c473f6a24027","abstract_canon_sha256":"a106b1a3a02fc030ef22dc8102e7d50be9b2d6874d706fd6e05b5963e4e8fb8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:38.518714Z","signature_b64":"x4SR+zF+RHKfHpogjT9o3ZwG+zBsQ3qAIIrwM80mifexBi6p4fhsx3ambsyZwdJ1KSp4+2sz84xQvy911wAXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8efdcccc35a894e9a54b423494534c8b8e32a92bef01d10f27191ee6e9eeae0c","last_reissued_at":"2026-07-05T10:50:38.518235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:38.518235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liujuan Cao, Shaohui Dai, Shengchuan Zhang, Xinyang Li, Yansong Qu, Zheyan Li","submitted_at":"2025-04-17T17:56:07Z","abstract_excerpt":"Bridging natural language and 3D geometry is a crucial step toward flexible, language-driven scene understanding. While recent advances in 3D Gaussian Splatting (3DGS) have enabled fast and high-quality scene reconstruction, research has also explored incorporating open-vocabulary understanding into 3DGS. However, most existing methods require iterative optimization over per-view 2D semantic feature maps, which not only results in inefficiencies but also leads to inconsistent 3D semantics across views. To address these limitations, we introduce a training-free framework that constructs a super"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13153","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/2504.13153/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":"2504.13153","created_at":"2026-07-05T10:50:38.518292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13153v1","created_at":"2026-07-05T10:50:38.518292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13153","created_at":"2026-07-05T10:50:38.518292+00:00"},{"alias_kind":"pith_short_12","alias_value":"R364ZTBVVCKO","created_at":"2026-07-05T10:50:38.518292+00:00"},{"alias_kind":"pith_short_16","alias_value":"R364ZTBVVCKOTJKL","created_at":"2026-07-05T10:50:38.518292+00:00"},{"alias_kind":"pith_short_8","alias_value":"R364ZTBV","created_at":"2026-07-05T10:50:38.518292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.09977","citing_title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","ref_index":114,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R364ZTBVVCKOTJKLII2JIU2MRO","json":"https://pith.science/pith/R364ZTBVVCKOTJKLII2JIU2MRO.json","graph_json":"https://pith.science/api/pith-number/R364ZTBVVCKOTJKLII2JIU2MRO/graph.json","events_json":"https://pith.science/api/pith-number/R364ZTBVVCKOTJKLII2JIU2MRO/events.json","paper":"https://pith.science/paper/R364ZTBV"},"agent_actions":{"view_html":"https://pith.science/pith/R364ZTBVVCKOTJKLII2JIU2MRO","download_json":"https://pith.science/pith/R364ZTBVVCKOTJKLII2JIU2MRO.json","view_paper":"https://pith.science/paper/R364ZTBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13153&json=true","fetch_graph":"https://pith.science/api/pith-number/R364ZTBVVCKOTJKLII2JIU2MRO/graph.json","fetch_events":"https://pith.science/api/pith-number/R364ZTBVVCKOTJKLII2JIU2MRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R364ZTBVVCKOTJKLII2JIU2MRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R364ZTBVVCKOTJKLII2JIU2MRO/action/storage_attestation","attest_author":"https://pith.science/pith/R364ZTBVVCKOTJKLII2JIU2MRO/action/author_attestation","sign_citation":"https://pith.science/pith/R364ZTBVVCKOTJKLII2JIU2MRO/action/citation_signature","submit_replication":"https://pith.science/pith/R364ZTBVVCKOTJKLII2JIU2MRO/action/replication_record"}},"created_at":"2026-07-05T10:50:38.518292+00:00","updated_at":"2026-07-05T10:50:38.518292+00:00"}