{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N726AP3UL7IZNGFG4VYBRFZOZF","short_pith_number":"pith:N726AP3U","schema_version":"1.0","canonical_sha256":"6ff5e03f745fd19698a6e57018972ec97a4cc5e627f4956aeaeea50732f3d724","source":{"kind":"arxiv","id":"2305.09018","version":1},"attestation_state":"computed","paper":{"title":"DATED: Guidelines for Creating Synthetic Datasets for Engineering Design Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cyril Picard, Faez Ahmed, J\\\"urg Schiffmann","submitted_at":"2023-05-15T21:00:09Z","abstract_excerpt":"Exploiting the recent advancements in artificial intelligence, showcased by ChatGPT and DALL-E, in real-world applications necessitates vast, domain-specific, and publicly accessible datasets. Unfortunately, the scarcity of such datasets poses a significant challenge for researchers aiming to apply these breakthroughs in engineering design. Synthetic datasets emerge as a viable alternative. However, practitioners are often uncertain about generating high-quality datasets that accurately represent real-world data and are suitable for the intended downstream applications. This study aims to fill"},"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":"2305.09018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-15T21:00:09Z","cross_cats_sorted":[],"title_canon_sha256":"b200e7b1682def78ef35ae62e5312b8a2b9e70a92d5caf2ce1d46110d94a3528","abstract_canon_sha256":"b08460185f75fadc8d409963e5d075085a9da211efb01ca4bc8ffc314fe54161"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:42.597683Z","signature_b64":"zVrYDlbAtCxkXaqPNqvoapM5xCDlv9d1P02H1YKmbDOsdiHBqxawph04rj+O728SzQaa81m7bc9YJOP1A/jKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ff5e03f745fd19698a6e57018972ec97a4cc5e627f4956aeaeea50732f3d724","last_reissued_at":"2026-07-05T06:10:42.597235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:42.597235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DATED: Guidelines for Creating Synthetic Datasets for Engineering Design Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cyril Picard, Faez Ahmed, J\\\"urg Schiffmann","submitted_at":"2023-05-15T21:00:09Z","abstract_excerpt":"Exploiting the recent advancements in artificial intelligence, showcased by ChatGPT and DALL-E, in real-world applications necessitates vast, domain-specific, and publicly accessible datasets. Unfortunately, the scarcity of such datasets poses a significant challenge for researchers aiming to apply these breakthroughs in engineering design. Synthetic datasets emerge as a viable alternative. However, practitioners are often uncertain about generating high-quality datasets that accurately represent real-world data and are suitable for the intended downstream applications. This study aims to fill"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09018","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/2305.09018/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":"2305.09018","created_at":"2026-07-05T06:10:42.597296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.09018v1","created_at":"2026-07-05T06:10:42.597296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09018","created_at":"2026-07-05T06:10:42.597296+00:00"},{"alias_kind":"pith_short_12","alias_value":"N726AP3UL7IZ","created_at":"2026-07-05T06:10:42.597296+00:00"},{"alias_kind":"pith_short_16","alias_value":"N726AP3UL7IZNGFG","created_at":"2026-07-05T06:10:42.597296+00:00"},{"alias_kind":"pith_short_8","alias_value":"N726AP3U","created_at":"2026-07-05T06:10:42.597296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.08171","citing_title":"Comprehensive and Comparative Analysis between Transfer Learning and Custom Built VGG and CNN-SVM Models for Wildfire Detection","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N726AP3UL7IZNGFG4VYBRFZOZF","json":"https://pith.science/pith/N726AP3UL7IZNGFG4VYBRFZOZF.json","graph_json":"https://pith.science/api/pith-number/N726AP3UL7IZNGFG4VYBRFZOZF/graph.json","events_json":"https://pith.science/api/pith-number/N726AP3UL7IZNGFG4VYBRFZOZF/events.json","paper":"https://pith.science/paper/N726AP3U"},"agent_actions":{"view_html":"https://pith.science/pith/N726AP3UL7IZNGFG4VYBRFZOZF","download_json":"https://pith.science/pith/N726AP3UL7IZNGFG4VYBRFZOZF.json","view_paper":"https://pith.science/paper/N726AP3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.09018&json=true","fetch_graph":"https://pith.science/api/pith-number/N726AP3UL7IZNGFG4VYBRFZOZF/graph.json","fetch_events":"https://pith.science/api/pith-number/N726AP3UL7IZNGFG4VYBRFZOZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N726AP3UL7IZNGFG4VYBRFZOZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N726AP3UL7IZNGFG4VYBRFZOZF/action/storage_attestation","attest_author":"https://pith.science/pith/N726AP3UL7IZNGFG4VYBRFZOZF/action/author_attestation","sign_citation":"https://pith.science/pith/N726AP3UL7IZNGFG4VYBRFZOZF/action/citation_signature","submit_replication":"https://pith.science/pith/N726AP3UL7IZNGFG4VYBRFZOZF/action/replication_record"}},"created_at":"2026-07-05T06:10:42.597296+00:00","updated_at":"2026-07-05T06:10:42.597296+00:00"}