{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S3PZLAA22ZDXMEDKG4KVS6ZYDZ","short_pith_number":"pith:S3PZLAA2","schema_version":"1.0","canonical_sha256":"96df95801ad64776106a3715597b381e720cd0ed1b8cb05e0aec518c73173680","source":{"kind":"arxiv","id":"2405.02698","version":1},"attestation_state":"computed","paper":{"title":"Stable Diffusion Dataset Generation for Downstream Classification Tasks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Eugenio Lomurno, Matteo D'Oria, Matteo Matteucci","submitted_at":"2024-05-04T15:37:22Z","abstract_excerpt":"Recent advances in generative artificial intelligence have enabled the creation of high-quality synthetic data that closely mimics real-world data. This paper explores the adaptation of the Stable Diffusion 2.0 model for generating synthetic datasets, using Transfer Learning, Fine-Tuning and generation parameter optimisation techniques to improve the utility of the dataset for downstream classification tasks. We present a class-conditional version of the model that exploits a Class-Encoder and optimisation of key generation parameters. Our methodology led to synthetic datasets that, in a third"},"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":"2405.02698","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-04T15:37:22Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"acc247314ee4a197e4272ed298f0363ddc5d2d0aa06f13ff3b6e32fd1839de02","abstract_canon_sha256":"aaa69c340d3ab792ba3acf8ef7745b418bb78c49985ca94b7a653226fff26839"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:52.209678Z","signature_b64":"YuuqxS14VdsF1OTWZSmqSZVTYT/0iK9gZ1bKHML2uEWOC4NAxDdsIrjpNDef/Zpl62KdEkW4t72sZvj7wrbRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96df95801ad64776106a3715597b381e720cd0ed1b8cb05e0aec518c73173680","last_reissued_at":"2026-07-05T08:15:52.209258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:52.209258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stable Diffusion Dataset Generation for Downstream Classification Tasks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Eugenio Lomurno, Matteo D'Oria, Matteo Matteucci","submitted_at":"2024-05-04T15:37:22Z","abstract_excerpt":"Recent advances in generative artificial intelligence have enabled the creation of high-quality synthetic data that closely mimics real-world data. This paper explores the adaptation of the Stable Diffusion 2.0 model for generating synthetic datasets, using Transfer Learning, Fine-Tuning and generation parameter optimisation techniques to improve the utility of the dataset for downstream classification tasks. We present a class-conditional version of the model that exploits a Class-Encoder and optimisation of key generation parameters. Our methodology led to synthetic datasets that, in a third"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02698","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/2405.02698/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":"2405.02698","created_at":"2026-07-05T08:15:52.209320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02698v1","created_at":"2026-07-05T08:15:52.209320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02698","created_at":"2026-07-05T08:15:52.209320+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3PZLAA22ZDX","created_at":"2026-07-05T08:15:52.209320+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3PZLAA22ZDXMEDK","created_at":"2026-07-05T08:15:52.209320+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3PZLAA2","created_at":"2026-07-05T08:15:52.209320+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.02236","citing_title":"Improving Physical Object State Representation in Text-to-Image Generative Systems","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3PZLAA22ZDXMEDKG4KVS6ZYDZ","json":"https://pith.science/pith/S3PZLAA22ZDXMEDKG4KVS6ZYDZ.json","graph_json":"https://pith.science/api/pith-number/S3PZLAA22ZDXMEDKG4KVS6ZYDZ/graph.json","events_json":"https://pith.science/api/pith-number/S3PZLAA22ZDXMEDKG4KVS6ZYDZ/events.json","paper":"https://pith.science/paper/S3PZLAA2"},"agent_actions":{"view_html":"https://pith.science/pith/S3PZLAA22ZDXMEDKG4KVS6ZYDZ","download_json":"https://pith.science/pith/S3PZLAA22ZDXMEDKG4KVS6ZYDZ.json","view_paper":"https://pith.science/paper/S3PZLAA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02698&json=true","fetch_graph":"https://pith.science/api/pith-number/S3PZLAA22ZDXMEDKG4KVS6ZYDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/S3PZLAA22ZDXMEDKG4KVS6ZYDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3PZLAA22ZDXMEDKG4KVS6ZYDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3PZLAA22ZDXMEDKG4KVS6ZYDZ/action/storage_attestation","attest_author":"https://pith.science/pith/S3PZLAA22ZDXMEDKG4KVS6ZYDZ/action/author_attestation","sign_citation":"https://pith.science/pith/S3PZLAA22ZDXMEDKG4KVS6ZYDZ/action/citation_signature","submit_replication":"https://pith.science/pith/S3PZLAA22ZDXMEDKG4KVS6ZYDZ/action/replication_record"}},"created_at":"2026-07-05T08:15:52.209320+00:00","updated_at":"2026-07-05T08:15:52.209320+00:00"}