{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SOUVAG5H5IYWVCTOM5SCED5AHQ","short_pith_number":"pith:SOUVAG5H","schema_version":"1.0","canonical_sha256":"93a9501ba7ea316a8a6e6764220fa03c3cf1d12fc53dd66acd7d3ad508572211","source":{"kind":"arxiv","id":"2309.14303","version":4},"attestation_state":"computed","paper":{"title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Tran, Khoi Nguyen, Quang Nguyen, Truong Vu","submitted_at":"2023-09-25T17:19:26Z","abstract_excerpt":"Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce image-level category labels, we propose a novel method for generating pixel-level semantic segmentation labels using the text-to-image generative model Stable Diffusion (SD). By utilizing the text prompts, cross-attention, and self-attention of SD, we introduce three new techniques: class-prompt appending, class-prompt cross-attention, and self-attention exponentiation. These tec"},"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":"2309.14303","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T17:19:26Z","cross_cats_sorted":[],"title_canon_sha256":"edcb93e505a0d05d00d92f29005c5fb2add284de604be61d0d71d06ad7ce9048","abstract_canon_sha256":"3c5d7db6a4dd472804ed1339818733cc7f182417142a399d473f57ed0e8ec76c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:59.899147Z","signature_b64":"CjQ1mOVCF10sb5auN+ajz44f2NI90BNHRBZRrz872HfgdYxYA7DLw7cpUhnIgBn07sEKccG+xlF94DGqJslcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93a9501ba7ea316a8a6e6764220fa03c3cf1d12fc53dd66acd7d3ad508572211","last_reissued_at":"2026-07-05T07:11:59.898661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:59.898661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh Tran, Khoi Nguyen, Quang Nguyen, Truong Vu","submitted_at":"2023-09-25T17:19:26Z","abstract_excerpt":"Preparing training data for deep vision models is a labor-intensive task. To address this, generative models have emerged as an effective solution for generating synthetic data. While current generative models produce image-level category labels, we propose a novel method for generating pixel-level semantic segmentation labels using the text-to-image generative model Stable Diffusion (SD). By utilizing the text prompts, cross-attention, and self-attention of SD, we introduce three new techniques: class-prompt appending, class-prompt cross-attention, and self-attention exponentiation. These tec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14303","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/2309.14303/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":"2309.14303","created_at":"2026-07-05T07:11:59.898736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.14303v4","created_at":"2026-07-05T07:11:59.898736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14303","created_at":"2026-07-05T07:11:59.898736+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOUVAG5H5IYW","created_at":"2026-07-05T07:11:59.898736+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOUVAG5H5IYWVCTO","created_at":"2026-07-05T07:11:59.898736+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOUVAG5H","created_at":"2026-07-05T07:11:59.898736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23038","citing_title":"Inpainting is All You Need: A Diffusion-based Augmentation Method for Semi-supervised Medical Image Segmentation","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SOUVAG5H5IYWVCTOM5SCED5AHQ","json":"https://pith.science/pith/SOUVAG5H5IYWVCTOM5SCED5AHQ.json","graph_json":"https://pith.science/api/pith-number/SOUVAG5H5IYWVCTOM5SCED5AHQ/graph.json","events_json":"https://pith.science/api/pith-number/SOUVAG5H5IYWVCTOM5SCED5AHQ/events.json","paper":"https://pith.science/paper/SOUVAG5H"},"agent_actions":{"view_html":"https://pith.science/pith/SOUVAG5H5IYWVCTOM5SCED5AHQ","download_json":"https://pith.science/pith/SOUVAG5H5IYWVCTOM5SCED5AHQ.json","view_paper":"https://pith.science/paper/SOUVAG5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.14303&json=true","fetch_graph":"https://pith.science/api/pith-number/SOUVAG5H5IYWVCTOM5SCED5AHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SOUVAG5H5IYWVCTOM5SCED5AHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOUVAG5H5IYWVCTOM5SCED5AHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOUVAG5H5IYWVCTOM5SCED5AHQ/action/storage_attestation","attest_author":"https://pith.science/pith/SOUVAG5H5IYWVCTOM5SCED5AHQ/action/author_attestation","sign_citation":"https://pith.science/pith/SOUVAG5H5IYWVCTOM5SCED5AHQ/action/citation_signature","submit_replication":"https://pith.science/pith/SOUVAG5H5IYWVCTOM5SCED5AHQ/action/replication_record"}},"created_at":"2026-07-05T07:11:59.898736+00:00","updated_at":"2026-07-05T07:11:59.898736+00:00"}