{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R6NIKHHTANBPIYIE2QFYSN44XK","short_pith_number":"pith:R6NIKHHT","schema_version":"1.0","canonical_sha256":"8f9a851cf30342f46104d40b89379cba9fa02764d9d28f1d16f395181d0b865c","source":{"kind":"arxiv","id":"2512.20907","version":2},"attestation_state":"computed","paper":{"title":"PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gunwoo Jeon, Jongwoo Lim, Minsu Cho, Seongho Choi, Seongmin Jung","submitted_at":"2025-12-24T03:18:51Z","abstract_excerpt":"3D Visual Grounding (3DVG) is a critical bridge from vision-language perception to robotics, requiring both language understanding and 3D scene reasoning. Traditional supervised models leverage explicit 3D geometry but exhibit limited generalization, owing to the scarcity of 3D vision-language datasets and the limited reasoning capabilities compared to modern vision-language models (VLMs). We propose a generalizable 3DVG framework, PanoGrounder, that couples multi-modal panoramic representation with pretrained 2D VLMs for strong vision-language reasoning. Panoramic renderings, augmented with 3"},"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":"2512.20907","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-24T03:18:51Z","cross_cats_sorted":[],"title_canon_sha256":"d3890748873af66faae5f50148290c46066cf9494999fc3f515d796f8c7c31ec","abstract_canon_sha256":"095c3856fb027def7dc876c743900eb0e189229b31904415a21c42d2d61c594e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:26.614258Z","signature_b64":"zEYrwnzU47J0eQyIxKzd7FrjoLlmVUwXtM0K/m1aL5Ys2YmgD6YGWtqVUbmZgMHGk5Lyks+Omf8F/LbMf6YIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f9a851cf30342f46104d40b89379cba9fa02764d9d28f1d16f395181d0b865c","last_reissued_at":"2026-07-02T01:17:26.613743Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:26.613743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gunwoo Jeon, Jongwoo Lim, Minsu Cho, Seongho Choi, Seongmin Jung","submitted_at":"2025-12-24T03:18:51Z","abstract_excerpt":"3D Visual Grounding (3DVG) is a critical bridge from vision-language perception to robotics, requiring both language understanding and 3D scene reasoning. Traditional supervised models leverage explicit 3D geometry but exhibit limited generalization, owing to the scarcity of 3D vision-language datasets and the limited reasoning capabilities compared to modern vision-language models (VLMs). We propose a generalizable 3DVG framework, PanoGrounder, that couples multi-modal panoramic representation with pretrained 2D VLMs for strong vision-language reasoning. Panoramic renderings, augmented with 3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.20907","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/2512.20907/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":"2512.20907","created_at":"2026-07-02T01:17:26.613804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.20907v2","created_at":"2026-07-02T01:17:26.613804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.20907","created_at":"2026-07-02T01:17:26.613804+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6NIKHHTANBP","created_at":"2026-07-02T01:17:26.613804+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6NIKHHTANBPIYIE","created_at":"2026-07-02T01:17:26.613804+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6NIKHHT","created_at":"2026-07-02T01:17:26.613804+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.31148","citing_title":"PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding","ref_index":108,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27745","citing_title":"Panoramic Scene Analysis: A Survey from Distortion-Aware Engineering to Sphere-Native Foundation Modeling","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6NIKHHTANBPIYIE2QFYSN44XK","json":"https://pith.science/pith/R6NIKHHTANBPIYIE2QFYSN44XK.json","graph_json":"https://pith.science/api/pith-number/R6NIKHHTANBPIYIE2QFYSN44XK/graph.json","events_json":"https://pith.science/api/pith-number/R6NIKHHTANBPIYIE2QFYSN44XK/events.json","paper":"https://pith.science/paper/R6NIKHHT"},"agent_actions":{"view_html":"https://pith.science/pith/R6NIKHHTANBPIYIE2QFYSN44XK","download_json":"https://pith.science/pith/R6NIKHHTANBPIYIE2QFYSN44XK.json","view_paper":"https://pith.science/paper/R6NIKHHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.20907&json=true","fetch_graph":"https://pith.science/api/pith-number/R6NIKHHTANBPIYIE2QFYSN44XK/graph.json","fetch_events":"https://pith.science/api/pith-number/R6NIKHHTANBPIYIE2QFYSN44XK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6NIKHHTANBPIYIE2QFYSN44XK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6NIKHHTANBPIYIE2QFYSN44XK/action/storage_attestation","attest_author":"https://pith.science/pith/R6NIKHHTANBPIYIE2QFYSN44XK/action/author_attestation","sign_citation":"https://pith.science/pith/R6NIKHHTANBPIYIE2QFYSN44XK/action/citation_signature","submit_replication":"https://pith.science/pith/R6NIKHHTANBPIYIE2QFYSN44XK/action/replication_record"}},"created_at":"2026-07-02T01:17:26.613804+00:00","updated_at":"2026-07-02T01:17:26.613804+00:00"}