{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3P46EXV5KEGWKRJRALONHZXNCK","short_pith_number":"pith:3P46EXV5","schema_version":"1.0","canonical_sha256":"dbf9e25ebd510d65453102dcd3e6ed1282b7e3be4b39c412cfe9b7d789f50891","source":{"kind":"arxiv","id":"2307.02138","version":1},"attestation_state":"computed","paper":{"title":"Prompting Diffusion Representations for Cross-Domain Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Sun, Julio Delgado Mangas, Luc Van Gool, Martin Danelljan, Rui Gong","submitted_at":"2023-07-05T09:28:25Z","abstract_excerpt":"While originally designed for image generation, diffusion models have recently shown to provide excellent pretrained feature representations for semantic segmentation. Intrigued by this result, we set out to explore how well diffusion-pretrained representations generalize to new domains, a crucial ability for any representation. We find that diffusion-pretraining achieves extraordinary domain generalization results for semantic segmentation, outperforming both supervised and self-supervised backbone networks. Motivated by this, we investigate how to utilize the model's unique ability of taking"},"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":"2307.02138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-05T09:28:25Z","cross_cats_sorted":[],"title_canon_sha256":"37ee3e07e9ff30b7ac19e3774c5dac40797df9f725647746ef6a480f9f62e076","abstract_canon_sha256":"047afcc370e8b2570565838e6d8441c536a7228a49826adf06d6f078d13fbd12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:05.653523Z","signature_b64":"CNmyTkUg3j2LDlraczSv0d5JgdAQDdejF+t7Dd3tGIMVnJBIzE0HCoE2nepjAx9/LnPOPIciNQYsXIwBMV5pAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbf9e25ebd510d65453102dcd3e6ed1282b7e3be4b39c412cfe9b7d789f50891","last_reissued_at":"2026-07-05T06:28:05.653130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:05.653130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompting Diffusion Representations for Cross-Domain Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Sun, Julio Delgado Mangas, Luc Van Gool, Martin Danelljan, Rui Gong","submitted_at":"2023-07-05T09:28:25Z","abstract_excerpt":"While originally designed for image generation, diffusion models have recently shown to provide excellent pretrained feature representations for semantic segmentation. Intrigued by this result, we set out to explore how well diffusion-pretrained representations generalize to new domains, a crucial ability for any representation. We find that diffusion-pretraining achieves extraordinary domain generalization results for semantic segmentation, outperforming both supervised and self-supervised backbone networks. Motivated by this, we investigate how to utilize the model's unique ability of taking"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02138","kind":"arxiv","version":1},"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/2307.02138/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":"2307.02138","created_at":"2026-07-05T06:28:05.653190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02138v1","created_at":"2026-07-05T06:28:05.653190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02138","created_at":"2026-07-05T06:28:05.653190+00:00"},{"alias_kind":"pith_short_12","alias_value":"3P46EXV5KEGW","created_at":"2026-07-05T06:28:05.653190+00:00"},{"alias_kind":"pith_short_16","alias_value":"3P46EXV5KEGWKRJR","created_at":"2026-07-05T06:28:05.653190+00:00"},{"alias_kind":"pith_short_8","alias_value":"3P46EXV5","created_at":"2026-07-05T06:28:05.653190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.12507","citing_title":"Segment Any-Quality Images with Generative Latent Space Enhancement","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02018","citing_title":"Towards Any-Quality Image Segmentation via Generative and Adaptive Latent Space Enhancement","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3P46EXV5KEGWKRJRALONHZXNCK","json":"https://pith.science/pith/3P46EXV5KEGWKRJRALONHZXNCK.json","graph_json":"https://pith.science/api/pith-number/3P46EXV5KEGWKRJRALONHZXNCK/graph.json","events_json":"https://pith.science/api/pith-number/3P46EXV5KEGWKRJRALONHZXNCK/events.json","paper":"https://pith.science/paper/3P46EXV5"},"agent_actions":{"view_html":"https://pith.science/pith/3P46EXV5KEGWKRJRALONHZXNCK","download_json":"https://pith.science/pith/3P46EXV5KEGWKRJRALONHZXNCK.json","view_paper":"https://pith.science/paper/3P46EXV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02138&json=true","fetch_graph":"https://pith.science/api/pith-number/3P46EXV5KEGWKRJRALONHZXNCK/graph.json","fetch_events":"https://pith.science/api/pith-number/3P46EXV5KEGWKRJRALONHZXNCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3P46EXV5KEGWKRJRALONHZXNCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3P46EXV5KEGWKRJRALONHZXNCK/action/storage_attestation","attest_author":"https://pith.science/pith/3P46EXV5KEGWKRJRALONHZXNCK/action/author_attestation","sign_citation":"https://pith.science/pith/3P46EXV5KEGWKRJRALONHZXNCK/action/citation_signature","submit_replication":"https://pith.science/pith/3P46EXV5KEGWKRJRALONHZXNCK/action/replication_record"}},"created_at":"2026-07-05T06:28:05.653190+00:00","updated_at":"2026-07-05T06:28:05.653190+00:00"}