{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W7ODX6J2ZEGX5TGZU7VVUYBDMK","short_pith_number":"pith:W7ODX6J2","schema_version":"1.0","canonical_sha256":"b7dc3bf93ac90d7eccd9a7eb5a60236291de66cf60a9c1b6024b4d5172d527a8","source":{"kind":"arxiv","id":"2605.25901","version":1},"attestation_state":"computed","paper":{"title":"AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Cuong Huynh, Denis Gridusov, Maxim Popov, Sergey Kolyubin","submitted_at":"2026-05-25T14:29:04Z","abstract_excerpt":"3D Visual Grounding (3DVG) is an essential capability for embodied AI, requiring agents to localize objects in 3D scenes based on natural language descriptions. Recent zero-shot methods leverage 2D vision-language models (LVLMs). However, they often rely on existing sets of multi-view images and struggle with the limited semantic and spatial details provided by standard 3D segmentation tools. We present $\\textbf{AgentGrounder}$, a zero-shot 3D visual grounding framework that operates directly on colored point clouds without task-specific 3D training. Our approach follows a two-stage design: (1"},"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":"2605.25901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T14:29:04Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f9e4134a93b2d41ec63aba834742e324666e67d42bbfe42bd99624800aa18e14","abstract_canon_sha256":"86bc574ba40a33bf92865aa7f5b730c5ceb9e71ab24337655c78aba0ee7e64ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:17.560359Z","signature_b64":"sdjrcElE9YTdrQMt9WfGm9vEHhr60LrdJ4ytrL4nCHEb8xWBCjdw86wCqFwi4PR3w80w06+oS4gK3cirusLTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7dc3bf93ac90d7eccd9a7eb5a60236291de66cf60a9c1b6024b4d5172d527a8","last_reissued_at":"2026-05-26T02:05:17.559651Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:17.559651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Cuong Huynh, Denis Gridusov, Maxim Popov, Sergey Kolyubin","submitted_at":"2026-05-25T14:29:04Z","abstract_excerpt":"3D Visual Grounding (3DVG) is an essential capability for embodied AI, requiring agents to localize objects in 3D scenes based on natural language descriptions. Recent zero-shot methods leverage 2D vision-language models (LVLMs). However, they often rely on existing sets of multi-view images and struggle with the limited semantic and spatial details provided by standard 3D segmentation tools. We present $\\textbf{AgentGrounder}$, a zero-shot 3D visual grounding framework that operates directly on colored point clouds without task-specific 3D training. Our approach follows a two-stage design: (1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25901","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/2605.25901/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":"2605.25901","created_at":"2026-05-26T02:05:17.559778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25901v1","created_at":"2026-05-26T02:05:17.559778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25901","created_at":"2026-05-26T02:05:17.559778+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7ODX6J2ZEGX","created_at":"2026-05-26T02:05:17.559778+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7ODX6J2ZEGX5TGZ","created_at":"2026-05-26T02:05:17.559778+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7ODX6J2","created_at":"2026-05-26T02:05:17.559778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W7ODX6J2ZEGX5TGZU7VVUYBDMK","json":"https://pith.science/pith/W7ODX6J2ZEGX5TGZU7VVUYBDMK.json","graph_json":"https://pith.science/api/pith-number/W7ODX6J2ZEGX5TGZU7VVUYBDMK/graph.json","events_json":"https://pith.science/api/pith-number/W7ODX6J2ZEGX5TGZU7VVUYBDMK/events.json","paper":"https://pith.science/paper/W7ODX6J2"},"agent_actions":{"view_html":"https://pith.science/pith/W7ODX6J2ZEGX5TGZU7VVUYBDMK","download_json":"https://pith.science/pith/W7ODX6J2ZEGX5TGZU7VVUYBDMK.json","view_paper":"https://pith.science/paper/W7ODX6J2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25901&json=true","fetch_graph":"https://pith.science/api/pith-number/W7ODX6J2ZEGX5TGZU7VVUYBDMK/graph.json","fetch_events":"https://pith.science/api/pith-number/W7ODX6J2ZEGX5TGZU7VVUYBDMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7ODX6J2ZEGX5TGZU7VVUYBDMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7ODX6J2ZEGX5TGZU7VVUYBDMK/action/storage_attestation","attest_author":"https://pith.science/pith/W7ODX6J2ZEGX5TGZU7VVUYBDMK/action/author_attestation","sign_citation":"https://pith.science/pith/W7ODX6J2ZEGX5TGZU7VVUYBDMK/action/citation_signature","submit_replication":"https://pith.science/pith/W7ODX6J2ZEGX5TGZU7VVUYBDMK/action/replication_record"}},"created_at":"2026-05-26T02:05:17.559778+00:00","updated_at":"2026-05-26T02:05:17.559778+00:00"}