{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PTJDQP2RT7MR6524QS4ABEF5OS","short_pith_number":"pith:PTJDQP2R","schema_version":"1.0","canonical_sha256":"7cd2383f519fd91f775c84b80090bd74bcd173a1e2747f3ead49ac4c4d7b0def","source":{"kind":"arxiv","id":"2308.12469","version":3},"attestation_state":"computed","paper":{"title":"Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Colaco, Junjiao Tian, Lavisha Aggarwal, Mar Gonzalez-Franco, Zsolt Kira","submitted_at":"2023-08-23T23:44:44Z","abstract_excerpt":"Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised training to enable segmentation without dense annotations. However, constructing a model capable of segmenting anything in a zero-shot manner without any annotations is still challenging. In this paper, we propose to utilize the self-attention layers in stable diffusion models to achieve this goal because the pre-trained stable diffusion model has learned inherent "},"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":"2308.12469","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T23:44:44Z","cross_cats_sorted":[],"title_canon_sha256":"106bd666360e657e0843a858d958c54dd560406ba21430a65e44890291540f99","abstract_canon_sha256":"3f1a615474fd311a0e769754c453e7cd9ee756ddd8f40d904a8fe2f4467bac90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:26.293057Z","signature_b64":"UU+OUu6zjpOk2aGMGgtf5pgIJIHxUW0giV8w8di79e8aQAvIWjD2o9q66FDRGFLnxingoWcqY5MYry6eOMI/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cd2383f519fd91f775c84b80090bd74bcd173a1e2747f3ead49ac4c4d7b0def","last_reissued_at":"2026-07-05T08:03:26.292598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:26.292598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Colaco, Junjiao Tian, Lavisha Aggarwal, Mar Gonzalez-Franco, Zsolt Kira","submitted_at":"2023-08-23T23:44:44Z","abstract_excerpt":"Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised training to enable segmentation without dense annotations. However, constructing a model capable of segmenting anything in a zero-shot manner without any annotations is still challenging. In this paper, we propose to utilize the self-attention layers in stable diffusion models to achieve this goal because the pre-trained stable diffusion model has learned inherent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12469","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/2308.12469/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":"2308.12469","created_at":"2026-07-05T08:03:26.292650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12469v3","created_at":"2026-07-05T08:03:26.292650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12469","created_at":"2026-07-05T08:03:26.292650+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTJDQP2RT7MR","created_at":"2026-07-05T08:03:26.292650+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTJDQP2RT7MR6524","created_at":"2026-07-05T08:03:26.292650+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTJDQP2R","created_at":"2026-07-05T08:03:26.292650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20005","citing_title":"StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention Distillation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":207,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00658","citing_title":"UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTJDQP2RT7MR6524QS4ABEF5OS","json":"https://pith.science/pith/PTJDQP2RT7MR6524QS4ABEF5OS.json","graph_json":"https://pith.science/api/pith-number/PTJDQP2RT7MR6524QS4ABEF5OS/graph.json","events_json":"https://pith.science/api/pith-number/PTJDQP2RT7MR6524QS4ABEF5OS/events.json","paper":"https://pith.science/paper/PTJDQP2R"},"agent_actions":{"view_html":"https://pith.science/pith/PTJDQP2RT7MR6524QS4ABEF5OS","download_json":"https://pith.science/pith/PTJDQP2RT7MR6524QS4ABEF5OS.json","view_paper":"https://pith.science/paper/PTJDQP2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12469&json=true","fetch_graph":"https://pith.science/api/pith-number/PTJDQP2RT7MR6524QS4ABEF5OS/graph.json","fetch_events":"https://pith.science/api/pith-number/PTJDQP2RT7MR6524QS4ABEF5OS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTJDQP2RT7MR6524QS4ABEF5OS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTJDQP2RT7MR6524QS4ABEF5OS/action/storage_attestation","attest_author":"https://pith.science/pith/PTJDQP2RT7MR6524QS4ABEF5OS/action/author_attestation","sign_citation":"https://pith.science/pith/PTJDQP2RT7MR6524QS4ABEF5OS/action/citation_signature","submit_replication":"https://pith.science/pith/PTJDQP2RT7MR6524QS4ABEF5OS/action/replication_record"}},"created_at":"2026-07-05T08:03:26.292650+00:00","updated_at":"2026-07-05T08:03:26.292650+00:00"}