{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2LKU5FN4FMWVZASR4RBHVXB3JY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ead21b2372fecd5cb39b5d745d5eb0c6aabc80ce5676154d2eae65812a1c250e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-08T18:58:26Z","title_canon_sha256":"61dcfdee0597a8fd579a85dc6f7a6f8a7a960f102ca967e9705c698fd6f4386a"},"schema_version":"1.0","source":{"id":"2303.04803","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04803","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04803v4","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04803","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_12","alias_value":"2LKU5FN4FMWV","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_16","alias_value":"2LKU5FN4FMWVZASR","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_8","alias_value":"2LKU5FN4","created_at":"2026-07-05T05:58:20Z"}],"graph_snapshots":[{"event_id":"sha256:a721f1bc48e8685fbd90ce4fbe7df957c8436fd6bfaa252ef9ccd92077238060","target":"graph","created_at":"2026-07-05T05:58:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.04803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arash Vahdat, Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Xiaolong Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-08T18:58:26Z","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04803","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:55770021888e7264a6ae3624d5e69ce86262391388a14a189c5a8a5191a95318","target":"record","created_at":"2026-07-05T05:58:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ead21b2372fecd5cb39b5d745d5eb0c6aabc80ce5676154d2eae65812a1c250e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-08T18:58:26Z","title_canon_sha256":"61dcfdee0597a8fd579a85dc6f7a6f8a7a960f102ca967e9705c698fd6f4386a"},"schema_version":"1.0","source":{"id":"2303.04803","kind":"arxiv","version":4}},"canonical_sha256":"d2d54e95bc2b2d5c8251e4427adc3b4e1b8848614b2663d9859c7598f032c7ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2d54e95bc2b2d5c8251e4427adc3b4e1b8848614b2663d9859c7598f032c7ab","first_computed_at":"2026-07-05T05:58:20.101643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:20.101643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9jhFqqSSQ5izL39g9ezaFD4cpVkVFYX3BkZK2PFUQRSHgJUuy+DxIie/7IhTWK5Hn5wFuRzGvEbg/300/4qwDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:20.102187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.04803","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55770021888e7264a6ae3624d5e69ce86262391388a14a189c5a8a5191a95318","sha256:a721f1bc48e8685fbd90ce4fbe7df957c8436fd6bfaa252ef9ccd92077238060"],"state_sha256":"3a6b494adb7134cbb4ce3b7b58160a634c5fe628026a2d5b125074578129e4b7"}