{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CYL7SZ7SWYLQKJI3TOCBTR3MO7","short_pith_number":"pith:CYL7SZ7S","schema_version":"1.0","canonical_sha256":"1617f967f2b61705251b9b8419c76c77d3ad5b68304e76110626cc24673d138b","source":{"kind":"arxiv","id":"2401.02402","version":3},"attestation_state":"computed","paper":{"title":"3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Zihao Zhu, Anelia Angelova, Chiyu Max Jiang, Jingwei Ji, Longlong Jing, Shangxuan Wu, Shiwei Sheng, Thomas Funkhouser, Weicheng Kuo, Wei-Chih Hung, Yin Zhou, Zihao Xiao","submitted_at":"2024-01-04T18:39:32Z","abstract_excerpt":"3D panoptic segmentation is a challenging perception task, especially in autonomous driving. It aims to predict both semantic and instance annotations for 3D points in a scene. Although prior 3D panoptic segmentation approaches have achieved great performance on closed-set benchmarks, generalizing these approaches to unseen things and unseen stuff categories remains an open problem. For unseen object categories, 2D open-vocabulary segmentation has achieved promising results that solely rely on frozen CLIP backbones and ensembling multiple classification outputs. However, we find that simply ex"},"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":"2401.02402","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T18:39:32Z","cross_cats_sorted":[],"title_canon_sha256":"9503517421fab06e218bbb1d9b5eebf986e8ef8e2276af3f427faac2b83124c3","abstract_canon_sha256":"5c9ef50b78d9ecb56445a1fe3953c1b6a48b9468495431f96ae5761c6cca9907"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:47.585017Z","signature_b64":"BfEggZAP2hp59c3F43VYqyIvls/tB0ND0AEKYeTnme+732s7NSViXL5b5qyY96ukjIdvXUBtBLHKmTUXOJv3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1617f967f2b61705251b9b8419c76c77d3ad5b68304e76110626cc24673d138b","last_reissued_at":"2026-07-05T08:03:47.584471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:47.584471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Zihao Zhu, Anelia Angelova, Chiyu Max Jiang, Jingwei Ji, Longlong Jing, Shangxuan Wu, Shiwei Sheng, Thomas Funkhouser, Weicheng Kuo, Wei-Chih Hung, Yin Zhou, Zihao Xiao","submitted_at":"2024-01-04T18:39:32Z","abstract_excerpt":"3D panoptic segmentation is a challenging perception task, especially in autonomous driving. It aims to predict both semantic and instance annotations for 3D points in a scene. Although prior 3D panoptic segmentation approaches have achieved great performance on closed-set benchmarks, generalizing these approaches to unseen things and unseen stuff categories remains an open problem. For unseen object categories, 2D open-vocabulary segmentation has achieved promising results that solely rely on frozen CLIP backbones and ensembling multiple classification outputs. However, we find that simply ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02402","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/2401.02402/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":"2401.02402","created_at":"2026-07-05T08:03:47.584536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02402v3","created_at":"2026-07-05T08:03:47.584536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02402","created_at":"2026-07-05T08:03:47.584536+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYL7SZ7SWYLQ","created_at":"2026-07-05T08:03:47.584536+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYL7SZ7SWYLQKJI3","created_at":"2026-07-05T08:03:47.584536+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYL7SZ7S","created_at":"2026-07-05T08:03:47.584536+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/CYL7SZ7SWYLQKJI3TOCBTR3MO7","json":"https://pith.science/pith/CYL7SZ7SWYLQKJI3TOCBTR3MO7.json","graph_json":"https://pith.science/api/pith-number/CYL7SZ7SWYLQKJI3TOCBTR3MO7/graph.json","events_json":"https://pith.science/api/pith-number/CYL7SZ7SWYLQKJI3TOCBTR3MO7/events.json","paper":"https://pith.science/paper/CYL7SZ7S"},"agent_actions":{"view_html":"https://pith.science/pith/CYL7SZ7SWYLQKJI3TOCBTR3MO7","download_json":"https://pith.science/pith/CYL7SZ7SWYLQKJI3TOCBTR3MO7.json","view_paper":"https://pith.science/paper/CYL7SZ7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02402&json=true","fetch_graph":"https://pith.science/api/pith-number/CYL7SZ7SWYLQKJI3TOCBTR3MO7/graph.json","fetch_events":"https://pith.science/api/pith-number/CYL7SZ7SWYLQKJI3TOCBTR3MO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYL7SZ7SWYLQKJI3TOCBTR3MO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYL7SZ7SWYLQKJI3TOCBTR3MO7/action/storage_attestation","attest_author":"https://pith.science/pith/CYL7SZ7SWYLQKJI3TOCBTR3MO7/action/author_attestation","sign_citation":"https://pith.science/pith/CYL7SZ7SWYLQKJI3TOCBTR3MO7/action/citation_signature","submit_replication":"https://pith.science/pith/CYL7SZ7SWYLQKJI3TOCBTR3MO7/action/replication_record"}},"created_at":"2026-07-05T08:03:47.584536+00:00","updated_at":"2026-07-05T08:03:47.584536+00:00"}