{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LBNX2EXJMZCWT75GM2BLFSE4KI","short_pith_number":"pith:LBNX2EXJ","schema_version":"1.0","canonical_sha256":"585b7d12e9664569ffa66682b2c89c5212b70994444c2cc1806023b56610b4c9","source":{"kind":"arxiv","id":"2506.21924","version":1},"attestation_state":"computed","paper":{"title":"SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jingyi Liao, Rong-Cheng Tu, Shunyu Liu, Wenhao Sun, Xiao Luo, Zhao Jin","submitted_at":"2025-06-27T05:34:57Z","abstract_excerpt":"3D Visual Grounding (3DVG) aims to localize target objects within a 3D scene based on natural language queries. To alleviate the reliance on costly 3D training data, recent studies have explored zero-shot 3DVG by leveraging the extensive knowledge and powerful reasoning capabilities of pre-trained LLMs and VLMs. However, existing paradigms tend to emphasize either spatial (3D-based) or semantic (2D-based) understanding, limiting their effectiveness in complex real-world applications. In this work, we introduce SPAZER - a VLM-driven agent that combines both modalities in a progressive reasoning"},"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":"2506.21924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T05:34:57Z","cross_cats_sorted":[],"title_canon_sha256":"53e749c68985fc4c5120c64b6e93da6e24ca615bacd9df7dff0a3fa20b968cbf","abstract_canon_sha256":"1d710b48ee4fed3d26cc2e2ec5c074bfe703c10700ddd12f398b83fa5bd9fa71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:18.496839Z","signature_b64":"vr3dsknw1tiTg3I53nkELhO9x/uTw0925mUVZY/JpN91sdJ+hCPtYA6nXrRKVG0ECQp+gVuaCVxky1Q7d0ZuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"585b7d12e9664569ffa66682b2c89c5212b70994444c2cc1806023b56610b4c9","last_reissued_at":"2026-07-05T11:28:18.496245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:18.496245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dacheng Tao, Jingyi Liao, Rong-Cheng Tu, Shunyu Liu, Wenhao Sun, Xiao Luo, Zhao Jin","submitted_at":"2025-06-27T05:34:57Z","abstract_excerpt":"3D Visual Grounding (3DVG) aims to localize target objects within a 3D scene based on natural language queries. To alleviate the reliance on costly 3D training data, recent studies have explored zero-shot 3DVG by leveraging the extensive knowledge and powerful reasoning capabilities of pre-trained LLMs and VLMs. However, existing paradigms tend to emphasize either spatial (3D-based) or semantic (2D-based) understanding, limiting their effectiveness in complex real-world applications. In this work, we introduce SPAZER - a VLM-driven agent that combines both modalities in a progressive reasoning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21924","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/2506.21924/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":"2506.21924","created_at":"2026-07-05T11:28:18.496309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21924v1","created_at":"2026-07-05T11:28:18.496309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21924","created_at":"2026-07-05T11:28:18.496309+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBNX2EXJMZCW","created_at":"2026-07-05T11:28:18.496309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBNX2EXJMZCWT75G","created_at":"2026-07-05T11:28:18.496309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBNX2EXJ","created_at":"2026-07-05T11:28:18.496309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24649","citing_title":"Agentic Collaborative Cognition for Zero-Shot 3D Understanding","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24649","citing_title":"Agentic Collaborative Cognition for Zero-Shot 3D Understanding","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28490","citing_title":"SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI","json":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI.json","graph_json":"https://pith.science/api/pith-number/LBNX2EXJMZCWT75GM2BLFSE4KI/graph.json","events_json":"https://pith.science/api/pith-number/LBNX2EXJMZCWT75GM2BLFSE4KI/events.json","paper":"https://pith.science/paper/LBNX2EXJ"},"agent_actions":{"view_html":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI","download_json":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI.json","view_paper":"https://pith.science/paper/LBNX2EXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21924&json=true","fetch_graph":"https://pith.science/api/pith-number/LBNX2EXJMZCWT75GM2BLFSE4KI/graph.json","fetch_events":"https://pith.science/api/pith-number/LBNX2EXJMZCWT75GM2BLFSE4KI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI/action/storage_attestation","attest_author":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI/action/author_attestation","sign_citation":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI/action/citation_signature","submit_replication":"https://pith.science/pith/LBNX2EXJMZCWT75GM2BLFSE4KI/action/replication_record"}},"created_at":"2026-07-05T11:28:18.496309+00:00","updated_at":"2026-07-05T11:28:18.496309+00:00"}