{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZT4G4LAHP7B6N5I2WKP57AG3AE","short_pith_number":"pith:ZT4G4LAH","schema_version":"1.0","canonical_sha256":"ccf86e2c077fc3e6f51ab29fdf80db010b7d79a97752ad5b90948e0b57e60059","source":{"kind":"arxiv","id":"2208.08984","version":2},"attestation_state":"computed","paper":{"title":"Open-Vocabulary Universal Image Segmentation with MaskCLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jieke Wang, Zheng Ding, Zhuowen Tu","submitted_at":"2022-08-18T17:55:37Z","abstract_excerpt":"In this paper, we tackle an emerging computer vision task, open-vocabulary universal image segmentation, that aims to perform semantic/instance/panoptic segmentation (background semantic labeling + foreground instance segmentation) for arbitrary categories of text-based descriptions in inference time. We first build a baseline method by directly adopting pre-trained CLIP models without finetuning or distillation. We then develop MaskCLIP, a Transformer-based approach with a MaskCLIP Visual Encoder, which is an encoder-only module that seamlessly integrates mask tokens with a pre-trained ViT CL"},"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":"2208.08984","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T17:55:37Z","cross_cats_sorted":[],"title_canon_sha256":"c7973e9b44b81b6d3d5e72ebeca63119603854c0070652c5ae6a77cf7fec85df","abstract_canon_sha256":"ddfcb468b3b4bc805e04e93ebd14cf6322d62a23c3a738bd2e82aab012dbbc8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:36.166069Z","signature_b64":"ES0dPRhkeDDmrn7iIiBMM0xMcz2TP7rNWSlPryA7lHbVP1jncYBqxhkOMay0iqF34ca1rsW33RSvn7k+OV2oAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccf86e2c077fc3e6f51ab29fdf80db010b7d79a97752ad5b90948e0b57e60059","last_reissued_at":"2026-07-05T06:18:36.165574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:36.165574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Vocabulary Universal Image Segmentation with MaskCLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jieke Wang, Zheng Ding, Zhuowen Tu","submitted_at":"2022-08-18T17:55:37Z","abstract_excerpt":"In this paper, we tackle an emerging computer vision task, open-vocabulary universal image segmentation, that aims to perform semantic/instance/panoptic segmentation (background semantic labeling + foreground instance segmentation) for arbitrary categories of text-based descriptions in inference time. We first build a baseline method by directly adopting pre-trained CLIP models without finetuning or distillation. We then develop MaskCLIP, a Transformer-based approach with a MaskCLIP Visual Encoder, which is an encoder-only module that seamlessly integrates mask tokens with a pre-trained ViT CL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08984","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/2208.08984/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":"2208.08984","created_at":"2026-07-05T06:18:36.165627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.08984v2","created_at":"2026-07-05T06:18:36.165627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08984","created_at":"2026-07-05T06:18:36.165627+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZT4G4LAHP7B6","created_at":"2026-07-05T06:18:36.165627+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZT4G4LAHP7B6N5I2","created_at":"2026-07-05T06:18:36.165627+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZT4G4LAH","created_at":"2026-07-05T06:18:36.165627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11837","citing_title":"LASA: A Weak Supervision Method for Open-Vocabulary Scene Sketch Semantic Segmentation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00987","citing_title":"An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19623","citing_title":"PrAda: Few-Shot Visual Adaptation for Text-Prompted Segmentation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16719","citing_title":"SAM 3: Segment Anything with Concepts","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2310.11441","citing_title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08461","citing_title":"OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE","json":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE.json","graph_json":"https://pith.science/api/pith-number/ZT4G4LAHP7B6N5I2WKP57AG3AE/graph.json","events_json":"https://pith.science/api/pith-number/ZT4G4LAHP7B6N5I2WKP57AG3AE/events.json","paper":"https://pith.science/paper/ZT4G4LAH"},"agent_actions":{"view_html":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE","download_json":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE.json","view_paper":"https://pith.science/paper/ZT4G4LAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.08984&json=true","fetch_graph":"https://pith.science/api/pith-number/ZT4G4LAHP7B6N5I2WKP57AG3AE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZT4G4LAHP7B6N5I2WKP57AG3AE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE/action/storage_attestation","attest_author":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE/action/author_attestation","sign_citation":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE/action/citation_signature","submit_replication":"https://pith.science/pith/ZT4G4LAHP7B6N5I2WKP57AG3AE/action/replication_record"}},"created_at":"2026-07-05T06:18:36.165627+00:00","updated_at":"2026-07-05T06:18:36.165627+00:00"}