{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UE3X33WR4D5NRIZ37XAFAQU6WE","short_pith_number":"pith:UE3X33WR","schema_version":"1.0","canonical_sha256":"a1377deed1e0fad8a33bfdc050429eb1031bce2b66e0a21e129b6ae078d9ebb5","source":{"kind":"arxiv","id":"2603.06168","version":3},"attestation_state":"computed","paper":{"title":"JOPP-3D: Joint Open Vocabulary Semantic Segmentation on Point Clouds and Panoramas","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Didier Stricker, Hideaki Kanayama, Jason Rambach, Kanta Shimizu, Mahdi Chamseddine, Sandeep Inuganti, Soichiro Yokota","submitted_at":"2026-03-06T11:22:14Z","abstract_excerpt":"Semantic segmentation across visual modalities such as 3D point clouds and panoramic images remains a challenging task, primarily due to the scarcity of annotated data and the limited adaptability of fixed-label models. In this paper, we present JOPP-3D, an open-vocabulary segmentation framework that jointly leverages panoramic and point cloud data to enable language-driven scene understanding. We convert RGB-D panoramic images into their corresponding wide field-of-view tangential perspectives and 3D point clouds, then use these modalities to extract and align foundational vision-language fea"},"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":"2603.06168","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-06T11:22:14Z","cross_cats_sorted":[],"title_canon_sha256":"e1eb4fc6a25ffb2c7fa879881b3e1218b9fb094569230982e5acb4eaf9dd47aa","abstract_canon_sha256":"a09442b67ec06fc96d59c1f4ccd94248f5c4d2ae7d659a2e4342ab816024567f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:35.648696Z","signature_b64":"0E+/61rhb9/fDgXMxky4zRu7elWCY2J3bJCcXh1jVSzMTW75oZiwUv0C125J0JIBgt8DvLRWYy2ymN5JiGmpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1377deed1e0fad8a33bfdc050429eb1031bce2b66e0a21e129b6ae078d9ebb5","last_reissued_at":"2026-06-30T01:17:35.648103Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:35.648103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JOPP-3D: Joint Open Vocabulary Semantic Segmentation on Point Clouds and Panoramas","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Didier Stricker, Hideaki Kanayama, Jason Rambach, Kanta Shimizu, Mahdi Chamseddine, Sandeep Inuganti, Soichiro Yokota","submitted_at":"2026-03-06T11:22:14Z","abstract_excerpt":"Semantic segmentation across visual modalities such as 3D point clouds and panoramic images remains a challenging task, primarily due to the scarcity of annotated data and the limited adaptability of fixed-label models. In this paper, we present JOPP-3D, an open-vocabulary segmentation framework that jointly leverages panoramic and point cloud data to enable language-driven scene understanding. We convert RGB-D panoramic images into their corresponding wide field-of-view tangential perspectives and 3D point clouds, then use these modalities to extract and align foundational vision-language fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.06168","kind":"arxiv","version":3},"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/2603.06168/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":"2603.06168","created_at":"2026-06-30T01:17:35.648183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.06168v3","created_at":"2026-06-30T01:17:35.648183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.06168","created_at":"2026-06-30T01:17:35.648183+00:00"},{"alias_kind":"pith_short_12","alias_value":"UE3X33WR4D5N","created_at":"2026-06-30T01:17:35.648183+00:00"},{"alias_kind":"pith_short_16","alias_value":"UE3X33WR4D5NRIZ3","created_at":"2026-06-30T01:17:35.648183+00:00"},{"alias_kind":"pith_short_8","alias_value":"UE3X33WR","created_at":"2026-06-30T01:17:35.648183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.27745","citing_title":"Panoramic Scene Analysis: A Survey from Distortion-Aware Engineering to Sphere-Native Foundation Modeling","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UE3X33WR4D5NRIZ37XAFAQU6WE","json":"https://pith.science/pith/UE3X33WR4D5NRIZ37XAFAQU6WE.json","graph_json":"https://pith.science/api/pith-number/UE3X33WR4D5NRIZ37XAFAQU6WE/graph.json","events_json":"https://pith.science/api/pith-number/UE3X33WR4D5NRIZ37XAFAQU6WE/events.json","paper":"https://pith.science/paper/UE3X33WR"},"agent_actions":{"view_html":"https://pith.science/pith/UE3X33WR4D5NRIZ37XAFAQU6WE","download_json":"https://pith.science/pith/UE3X33WR4D5NRIZ37XAFAQU6WE.json","view_paper":"https://pith.science/paper/UE3X33WR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.06168&json=true","fetch_graph":"https://pith.science/api/pith-number/UE3X33WR4D5NRIZ37XAFAQU6WE/graph.json","fetch_events":"https://pith.science/api/pith-number/UE3X33WR4D5NRIZ37XAFAQU6WE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UE3X33WR4D5NRIZ37XAFAQU6WE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UE3X33WR4D5NRIZ37XAFAQU6WE/action/storage_attestation","attest_author":"https://pith.science/pith/UE3X33WR4D5NRIZ37XAFAQU6WE/action/author_attestation","sign_citation":"https://pith.science/pith/UE3X33WR4D5NRIZ37XAFAQU6WE/action/citation_signature","submit_replication":"https://pith.science/pith/UE3X33WR4D5NRIZ37XAFAQU6WE/action/replication_record"}},"created_at":"2026-06-30T01:17:35.648183+00:00","updated_at":"2026-06-30T01:17:35.648183+00:00"}