{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3DZOOHB2GZOEA3I62XGK6L5TWI","short_pith_number":"pith:3DZOOHB2","schema_version":"1.0","canonical_sha256":"d8f2e71c3a365c406d1ed5ccaf2fb3b21ce0e33d11b1d277f2c5148ab8fd6ba4","source":{"kind":"arxiv","id":"2506.13629","version":2},"attestation_state":"computed","paper":{"title":"FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenlu Zhan, Gaoang Wang, Hongwei Wang, Yufei Zhang","submitted_at":"2025-06-16T15:56:50Z","abstract_excerpt":"Semantic querying in complex 3D scenes through free-form language presents a significant challenge. Existing 3D scene understanding methods use large-scale training data and CLIP to align text queries with 3D semantic features. However, their reliance on predefined vocabulary priors from training data hinders free-form semantic querying. Besides, recent advanced methods rely on LLMs for scene understanding but lack comprehensive 3D scene-level information and often overlook the potential inconsistencies in LLM-generated outputs. In our paper, we propose FreeQ-Graph, which enables Free-form Que"},"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":"2506.13629","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-16T15:56:50Z","cross_cats_sorted":[],"title_canon_sha256":"7eb0f4432177b4feef0f2293acaf00745da5572bffaf83f87c57fd8ee7eecb7c","abstract_canon_sha256":"ed9027babb283672961aa210010cb2ce651e868200f97cc036f22ea487ae5930"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:07.411245Z","signature_b64":"ar+Uf1GP0HcCNeVKqv8SN5Fz5VSdBPE8wAn52FTKVN1C2N6Zk697UkvsljNhyc1SeYcTv6Ep4L+xysCXJGX1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8f2e71c3a365c406d1ed5ccaf2fb3b21ce0e33d11b1d277f2c5148ab8fd6ba4","last_reissued_at":"2026-07-05T11:44:07.410706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:07.410706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenlu Zhan, Gaoang Wang, Hongwei Wang, Yufei Zhang","submitted_at":"2025-06-16T15:56:50Z","abstract_excerpt":"Semantic querying in complex 3D scenes through free-form language presents a significant challenge. Existing 3D scene understanding methods use large-scale training data and CLIP to align text queries with 3D semantic features. However, their reliance on predefined vocabulary priors from training data hinders free-form semantic querying. Besides, recent advanced methods rely on LLMs for scene understanding but lack comprehensive 3D scene-level information and often overlook the potential inconsistencies in LLM-generated outputs. In our paper, we propose FreeQ-Graph, which enables Free-form Que"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13629","kind":"arxiv","version":2},"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/2506.13629/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":"2506.13629","created_at":"2026-07-05T11:44:07.410765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13629v2","created_at":"2026-07-05T11:44:07.410765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13629","created_at":"2026-07-05T11:44:07.410765+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DZOOHB2GZOE","created_at":"2026-07-05T11:44:07.410765+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DZOOHB2GZOEA3I6","created_at":"2026-07-05T11:44:07.410765+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DZOOHB2","created_at":"2026-07-05T11:44:07.410765+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19383","citing_title":"3D Scene Graphs: Open Challenges and Future Directions","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05638","citing_title":"PanopticQuery: Unified Query-Time Reasoning for 4D Scenes","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DZOOHB2GZOEA3I62XGK6L5TWI","json":"https://pith.science/pith/3DZOOHB2GZOEA3I62XGK6L5TWI.json","graph_json":"https://pith.science/api/pith-number/3DZOOHB2GZOEA3I62XGK6L5TWI/graph.json","events_json":"https://pith.science/api/pith-number/3DZOOHB2GZOEA3I62XGK6L5TWI/events.json","paper":"https://pith.science/paper/3DZOOHB2"},"agent_actions":{"view_html":"https://pith.science/pith/3DZOOHB2GZOEA3I62XGK6L5TWI","download_json":"https://pith.science/pith/3DZOOHB2GZOEA3I62XGK6L5TWI.json","view_paper":"https://pith.science/paper/3DZOOHB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13629&json=true","fetch_graph":"https://pith.science/api/pith-number/3DZOOHB2GZOEA3I62XGK6L5TWI/graph.json","fetch_events":"https://pith.science/api/pith-number/3DZOOHB2GZOEA3I62XGK6L5TWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DZOOHB2GZOEA3I62XGK6L5TWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DZOOHB2GZOEA3I62XGK6L5TWI/action/storage_attestation","attest_author":"https://pith.science/pith/3DZOOHB2GZOEA3I62XGK6L5TWI/action/author_attestation","sign_citation":"https://pith.science/pith/3DZOOHB2GZOEA3I62XGK6L5TWI/action/citation_signature","submit_replication":"https://pith.science/pith/3DZOOHB2GZOEA3I62XGK6L5TWI/action/replication_record"}},"created_at":"2026-07-05T11:44:07.410765+00:00","updated_at":"2026-07-05T11:44:07.410765+00:00"}