{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SWIKC7TB2QSOS667RIQMZ55ZYY","short_pith_number":"pith:SWIKC7TB","schema_version":"1.0","canonical_sha256":"9590a17e61d424e97bdf8a20ccf7b9c637d3cc68eb82ec654e7e177951319d52","source":{"kind":"arxiv","id":"2309.02773","version":3},"attestation_state":"computed","paper":{"title":"Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Xu, Jinglong Wang, Jing Zhang, Lu Sheng, Qian Yu, Qingyuan Xu, Qin Zhou, Xiawei Li","submitted_at":"2023-09-06T06:31:08Z","abstract_excerpt":"The pre-trained text-image discriminative models, such as CLIP, has been explored for open-vocabulary semantic segmentation with unsatisfactory results due to the loss of crucial localization information and awareness of object shapes. Recently, there has been a growing interest in expanding the application of generative models from generation tasks to semantic segmentation. These approaches utilize generative models either for generating annotated data or extracting features to facilitate semantic segmentation. This typically involves generating a considerable amount of synthetic data or requ"},"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":"2309.02773","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T06:31:08Z","cross_cats_sorted":[],"title_canon_sha256":"93a22795ef39ca4dd884ba5a7f8e4d5e94a9a5ec3f907ce9ce49668a40612a5d","abstract_canon_sha256":"8bdaab1e76b5b568432c4c01bbbe672a976cbef005e5637433cf891bc35bbdc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:02.693750Z","signature_b64":"lXZH1pMsearjMfxW0AT3find2gCwoP/PjMlnqA7SVQPrrgz9DotmOrXwHsfJEW0etEXe/QH+MkE/3zg0pkQLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9590a17e61d424e97bdf8a20ccf7b9c637d3cc68eb82ec654e7e177951319d52","last_reissued_at":"2026-07-05T07:36:02.693265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:02.693265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Xu, Jinglong Wang, Jing Zhang, Lu Sheng, Qian Yu, Qingyuan Xu, Qin Zhou, Xiawei Li","submitted_at":"2023-09-06T06:31:08Z","abstract_excerpt":"The pre-trained text-image discriminative models, such as CLIP, has been explored for open-vocabulary semantic segmentation with unsatisfactory results due to the loss of crucial localization information and awareness of object shapes. Recently, there has been a growing interest in expanding the application of generative models from generation tasks to semantic segmentation. These approaches utilize generative models either for generating annotated data or extracting features to facilitate semantic segmentation. This typically involves generating a considerable amount of synthetic data or requ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02773","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/2309.02773/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":"2309.02773","created_at":"2026-07-05T07:36:02.693326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02773v3","created_at":"2026-07-05T07:36:02.693326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02773","created_at":"2026-07-05T07:36:02.693326+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWIKC7TB2QSO","created_at":"2026-07-05T07:36:02.693326+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWIKC7TB2QSOS667","created_at":"2026-07-05T07:36:02.693326+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWIKC7TB","created_at":"2026-07-05T07:36:02.693326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.23323","citing_title":"FA-Seg: A Fast and Accurate Diffusion-Based Method for Open-Vocabulary Segmentation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27889","citing_title":"Noise2Map: End-to-End Diffusion Model for Semantic Segmentation and Change Detection","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03175","citing_title":"DINO Soars: DINOv3 for Open-Vocabulary Semantic Segmentation of Remote Sensing Imagery","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SWIKC7TB2QSOS667RIQMZ55ZYY","json":"https://pith.science/pith/SWIKC7TB2QSOS667RIQMZ55ZYY.json","graph_json":"https://pith.science/api/pith-number/SWIKC7TB2QSOS667RIQMZ55ZYY/graph.json","events_json":"https://pith.science/api/pith-number/SWIKC7TB2QSOS667RIQMZ55ZYY/events.json","paper":"https://pith.science/paper/SWIKC7TB"},"agent_actions":{"view_html":"https://pith.science/pith/SWIKC7TB2QSOS667RIQMZ55ZYY","download_json":"https://pith.science/pith/SWIKC7TB2QSOS667RIQMZ55ZYY.json","view_paper":"https://pith.science/paper/SWIKC7TB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02773&json=true","fetch_graph":"https://pith.science/api/pith-number/SWIKC7TB2QSOS667RIQMZ55ZYY/graph.json","fetch_events":"https://pith.science/api/pith-number/SWIKC7TB2QSOS667RIQMZ55ZYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWIKC7TB2QSOS667RIQMZ55ZYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWIKC7TB2QSOS667RIQMZ55ZYY/action/storage_attestation","attest_author":"https://pith.science/pith/SWIKC7TB2QSOS667RIQMZ55ZYY/action/author_attestation","sign_citation":"https://pith.science/pith/SWIKC7TB2QSOS667RIQMZ55ZYY/action/citation_signature","submit_replication":"https://pith.science/pith/SWIKC7TB2QSOS667RIQMZ55ZYY/action/replication_record"}},"created_at":"2026-07-05T07:36:02.693326+00:00","updated_at":"2026-07-05T07:36:02.693326+00:00"}