{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2LKU5FN4FMWVZASR4RBHVXB3JY","short_pith_number":"pith:2LKU5FN4","schema_version":"1.0","canonical_sha256":"d2d54e95bc2b2d5c8251e4427adc3b4e1b8848614b2663d9859c7598f032c7ab","source":{"kind":"arxiv","id":"2303.04803","version":4},"attestation_state":"computed","paper":{"title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arash Vahdat, Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Xiaolong Wang","submitted_at":"2023-03-08T18:58:26Z","abstract_excerpt":"We present ODISE: Open-vocabulary DIffusion-based panoptic SEgmentation, which unifies pre-trained text-image diffusion and discriminative models to perform open-vocabulary panoptic segmentation. Text-to-image diffusion models have the remarkable ability to generate high-quality images with diverse open-vocabulary language descriptions. This demonstrates that their internal representation space is highly correlated with open concepts in the real world. Text-image discriminative models like CLIP, on the other hand, are good at classifying images into open-vocabulary labels. We leverage the froz"},"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":"2303.04803","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-08T18:58:26Z","cross_cats_sorted":[],"title_canon_sha256":"61dcfdee0597a8fd579a85dc6f7a6f8a7a960f102ca967e9705c698fd6f4386a","abstract_canon_sha256":"ead21b2372fecd5cb39b5d745d5eb0c6aabc80ce5676154d2eae65812a1c250e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:20.102187Z","signature_b64":"9jhFqqSSQ5izL39g9ezaFD4cpVkVFYX3BkZK2PFUQRSHgJUuy+DxIie/7IhTWK5Hn5wFuRzGvEbg/300/4qwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2d54e95bc2b2d5c8251e4427adc3b4e1b8848614b2663d9859c7598f032c7ab","last_reissued_at":"2026-07-05T05:58:20.101643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:20.101643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arash Vahdat, Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Xiaolong Wang","submitted_at":"2023-03-08T18:58:26Z","abstract_excerpt":"We present ODISE: Open-vocabulary DIffusion-based panoptic SEgmentation, which unifies pre-trained text-image diffusion and discriminative models to perform open-vocabulary panoptic segmentation. Text-to-image diffusion models have the remarkable ability to generate high-quality images with diverse open-vocabulary language descriptions. This demonstrates that their internal representation space is highly correlated with open concepts in the real world. Text-image discriminative models like CLIP, on the other hand, are good at classifying images into open-vocabulary labels. We leverage the froz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04803","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/2303.04803/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":"2303.04803","created_at":"2026-07-05T05:58:20.101701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.04803v4","created_at":"2026-07-05T05:58:20.101701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04803","created_at":"2026-07-05T05:58:20.101701+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LKU5FN4FMWV","created_at":"2026-07-05T05:58:20.101701+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LKU5FN4FMWVZASR","created_at":"2026-07-05T05:58:20.101701+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LKU5FN4","created_at":"2026-07-05T05:58:20.101701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20122","citing_title":"MEBench: A Novel Benchmark for Understanding Mutual Exclusivity Bias in Vision-Language Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2LKU5FN4FMWVZASR4RBHVXB3JY","json":"https://pith.science/pith/2LKU5FN4FMWVZASR4RBHVXB3JY.json","graph_json":"https://pith.science/api/pith-number/2LKU5FN4FMWVZASR4RBHVXB3JY/graph.json","events_json":"https://pith.science/api/pith-number/2LKU5FN4FMWVZASR4RBHVXB3JY/events.json","paper":"https://pith.science/paper/2LKU5FN4"},"agent_actions":{"view_html":"https://pith.science/pith/2LKU5FN4FMWVZASR4RBHVXB3JY","download_json":"https://pith.science/pith/2LKU5FN4FMWVZASR4RBHVXB3JY.json","view_paper":"https://pith.science/paper/2LKU5FN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.04803&json=true","fetch_graph":"https://pith.science/api/pith-number/2LKU5FN4FMWVZASR4RBHVXB3JY/graph.json","fetch_events":"https://pith.science/api/pith-number/2LKU5FN4FMWVZASR4RBHVXB3JY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LKU5FN4FMWVZASR4RBHVXB3JY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LKU5FN4FMWVZASR4RBHVXB3JY/action/storage_attestation","attest_author":"https://pith.science/pith/2LKU5FN4FMWVZASR4RBHVXB3JY/action/author_attestation","sign_citation":"https://pith.science/pith/2LKU5FN4FMWVZASR4RBHVXB3JY/action/citation_signature","submit_replication":"https://pith.science/pith/2LKU5FN4FMWVZASR4RBHVXB3JY/action/replication_record"}},"created_at":"2026-07-05T05:58:20.101701+00:00","updated_at":"2026-07-05T05:58:20.101701+00:00"}