{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JSBS5UCFAQQICBPOTQKIYPU7KD","short_pith_number":"pith:JSBS5UCF","schema_version":"1.0","canonical_sha256":"4c832ed04504208105ee9c148c3e9f50dc6b6e3e290c3bd8e668c2839fab4ee2","source":{"kind":"arxiv","id":"2305.14093","version":4},"attestation_state":"computed","paper":{"title":"Weakly Supervised 3D Open-vocabulary Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdulmotaleb El Saddik, Christian Theobalt, Eric Xing, Fangneng Zhan, Jiahui Zhang, Kunhao Liu, Muyu Xu, Shijian Lu, Yingchen Yu","submitted_at":"2023-05-23T14:16:49Z","abstract_excerpt":"Open-vocabulary segmentation of 3D scenes is a fundamental function of human perception and thus a crucial objective in computer vision research. However, this task is heavily impeded by the lack of large-scale and diverse 3D open-vocabulary segmentation datasets for training robust and generalizable models. Distilling knowledge from pre-trained 2D open-vocabulary segmentation models helps but it compromises the open-vocabulary feature as the 2D models are mostly finetuned with close-vocabulary datasets. We tackle the challenges in 3D open-vocabulary segmentation by exploiting pre-trained foun"},"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":"2305.14093","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-23T14:16:49Z","cross_cats_sorted":[],"title_canon_sha256":"b6ede0309ac9e0d034542dc216fc38f048087c4a7967eb83f90d3655265c5bad","abstract_canon_sha256":"c615545c5cdc501622d5231a9c2e279471d9cb3720dfac2fa500d9e133ee7a71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:28.445814Z","signature_b64":"3MXaM4Dct/7xfAlBDsdm4sH0SrFP2Eg811b1yJQrZDLn/5G2S0WHu88f2MQQeaAG9BMYzJuP35//XthbOFy/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c832ed04504208105ee9c148c3e9f50dc6b6e3e290c3bd8e668c2839fab4ee2","last_reissued_at":"2026-07-05T07:31:28.445350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:28.445350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weakly Supervised 3D Open-vocabulary Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdulmotaleb El Saddik, Christian Theobalt, Eric Xing, Fangneng Zhan, Jiahui Zhang, Kunhao Liu, Muyu Xu, Shijian Lu, Yingchen Yu","submitted_at":"2023-05-23T14:16:49Z","abstract_excerpt":"Open-vocabulary segmentation of 3D scenes is a fundamental function of human perception and thus a crucial objective in computer vision research. However, this task is heavily impeded by the lack of large-scale and diverse 3D open-vocabulary segmentation datasets for training robust and generalizable models. Distilling knowledge from pre-trained 2D open-vocabulary segmentation models helps but it compromises the open-vocabulary feature as the 2D models are mostly finetuned with close-vocabulary datasets. We tackle the challenges in 3D open-vocabulary segmentation by exploiting pre-trained foun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14093","kind":"arxiv","version":4},"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/2305.14093/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":"2305.14093","created_at":"2026-07-05T07:31:28.445409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14093v4","created_at":"2026-07-05T07:31:28.445409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14093","created_at":"2026-07-05T07:31:28.445409+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSBS5UCFAQQI","created_at":"2026-07-05T07:31:28.445409+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSBS5UCFAQQICBPO","created_at":"2026-07-05T07:31:28.445409+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSBS5UCF","created_at":"2026-07-05T07:31:28.445409+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01628","citing_title":"Online Segment 3D Gaussians via Launching Virtual Drones","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2310.11441","citing_title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JSBS5UCFAQQICBPOTQKIYPU7KD","json":"https://pith.science/pith/JSBS5UCFAQQICBPOTQKIYPU7KD.json","graph_json":"https://pith.science/api/pith-number/JSBS5UCFAQQICBPOTQKIYPU7KD/graph.json","events_json":"https://pith.science/api/pith-number/JSBS5UCFAQQICBPOTQKIYPU7KD/events.json","paper":"https://pith.science/paper/JSBS5UCF"},"agent_actions":{"view_html":"https://pith.science/pith/JSBS5UCFAQQICBPOTQKIYPU7KD","download_json":"https://pith.science/pith/JSBS5UCFAQQICBPOTQKIYPU7KD.json","view_paper":"https://pith.science/paper/JSBS5UCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14093&json=true","fetch_graph":"https://pith.science/api/pith-number/JSBS5UCFAQQICBPOTQKIYPU7KD/graph.json","fetch_events":"https://pith.science/api/pith-number/JSBS5UCFAQQICBPOTQKIYPU7KD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSBS5UCFAQQICBPOTQKIYPU7KD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSBS5UCFAQQICBPOTQKIYPU7KD/action/storage_attestation","attest_author":"https://pith.science/pith/JSBS5UCFAQQICBPOTQKIYPU7KD/action/author_attestation","sign_citation":"https://pith.science/pith/JSBS5UCFAQQICBPOTQKIYPU7KD/action/citation_signature","submit_replication":"https://pith.science/pith/JSBS5UCFAQQICBPOTQKIYPU7KD/action/replication_record"}},"created_at":"2026-07-05T07:31:28.445409+00:00","updated_at":"2026-07-05T07:31:28.445409+00:00"}