{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W7ODX6J2ZEGX5TGZU7VVUYBDMK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"86bc574ba40a33bf92865aa7f5b730c5ceb9e71ab24337655c78aba0ee7e64ca","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T14:29:04Z","title_canon_sha256":"f9e4134a93b2d41ec63aba834742e324666e67d42bbfe42bd99624800aa18e14"},"schema_version":"1.0","source":{"id":"2605.25901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25901","created_at":"2026-05-26T02:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25901v1","created_at":"2026-05-26T02:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25901","created_at":"2026-05-26T02:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"W7ODX6J2ZEGX","created_at":"2026-05-26T02:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"W7ODX6J2ZEGX5TGZ","created_at":"2026-05-26T02:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"W7ODX6J2","created_at":"2026-05-26T02:05:17Z"}],"graph_snapshots":[{"event_id":"sha256:fe68ea5fe1d187f985c393200175f0ad12ccd7d3e80e42ceb3927d3c7836944f","target":"graph","created_at":"2026-05-26T02:05:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.25901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cuong Huynh, Denis Gridusov, Maxim Popov, Sergey Kolyubin","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T14:29:04Z","title":"AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25901","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:591dfed93b9e95036c76bfd301297794259bde335fcc53325f2f0b2e41514d63","target":"record","created_at":"2026-05-26T02:05:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"86bc574ba40a33bf92865aa7f5b730c5ceb9e71ab24337655c78aba0ee7e64ca","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T14:29:04Z","title_canon_sha256":"f9e4134a93b2d41ec63aba834742e324666e67d42bbfe42bd99624800aa18e14"},"schema_version":"1.0","source":{"id":"2605.25901","kind":"arxiv","version":1}},"canonical_sha256":"b7dc3bf93ac90d7eccd9a7eb5a60236291de66cf60a9c1b6024b4d5172d527a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7dc3bf93ac90d7eccd9a7eb5a60236291de66cf60a9c1b6024b4d5172d527a8","first_computed_at":"2026-05-26T02:05:17.559651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:17.559651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sdjrcElE9YTdrQMt9WfGm9vEHhr60LrdJ4ytrL4nCHEb8xWBCjdw86wCqFwi4PR3w80w06+oS4gK3cirusLTDQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:17.560359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:591dfed93b9e95036c76bfd301297794259bde335fcc53325f2f0b2e41514d63","sha256:fe68ea5fe1d187f985c393200175f0ad12ccd7d3e80e42ceb3927d3c7836944f"],"state_sha256":"f31bd2215ee1f0ffbf2644d05bbba83764364aac32582116da0c9b6b0842ee8b"}