{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XD64DWWDUST4QIR4ERANPQ3GY4","short_pith_number":"pith:XD64DWWD","schema_version":"1.0","canonical_sha256":"b8fdc1dac3a4a7c8223c2440d7c366c7356bbd3ad09b8640adb2a822d12245e0","source":{"kind":"arxiv","id":"2510.06596","version":2},"attestation_state":"computed","paper":{"title":"SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","cs.LG","math.IT"],"primary_cat":"cs.CV","authors_text":"Arnold Zumbrun, Ayush Zenith, Jing Lin, Neel Raut","submitted_at":"2025-10-08T03:01:26Z","abstract_excerpt":"The performance of machine learning models depends heavily on training data. The scarcity of large-scale, well-annotated datasets poses significant challenges in creating robust models. To address this, synthetic data generated through simulations and generative models has emerged as a promising solution, enhancing dataset diversity and improving the performance, reliability, and resilience of models. However, evaluating the quality of this generated data requires an effective metric. We introduce the Synthetic Dataset Quality Metric (SDQM) to assess data quality for object detection tasks wit"},"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":"2510.06596","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-08T03:01:26Z","cross_cats_sorted":["cs.AI","cs.IT","cs.LG","math.IT"],"title_canon_sha256":"8f00f335d0814e394afcfb908d99be5a7d6d6ffb8167aeba31da6bfffbb53932","abstract_canon_sha256":"66cd1f8fb3c06473c7b7020adf302fbce7211d63a2a362f24e36a4de5402fd08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:19.503439Z","signature_b64":"AbLK+Rct5kUxg4sYYGvlaTKmpOwcH3zY117LDZZb0SoBEZ6FApTd/3VlbBeRU602g7y0BOsse1W36AhRmJp2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8fdc1dac3a4a7c8223c2440d7c366c7356bbd3ad09b8640adb2a822d12245e0","last_reissued_at":"2026-06-11T01:09:19.502469Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:19.502469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","cs.LG","math.IT"],"primary_cat":"cs.CV","authors_text":"Arnold Zumbrun, Ayush Zenith, Jing Lin, Neel Raut","submitted_at":"2025-10-08T03:01:26Z","abstract_excerpt":"The performance of machine learning models depends heavily on training data. The scarcity of large-scale, well-annotated datasets poses significant challenges in creating robust models. To address this, synthetic data generated through simulations and generative models has emerged as a promising solution, enhancing dataset diversity and improving the performance, reliability, and resilience of models. However, evaluating the quality of this generated data requires an effective metric. We introduce the Synthetic Dataset Quality Metric (SDQM) to assess data quality for object detection tasks wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.06596","kind":"arxiv","version":2},"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/2510.06596/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":"2510.06596","created_at":"2026-06-11T01:09:19.502607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.06596v2","created_at":"2026-06-11T01:09:19.502607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.06596","created_at":"2026-06-11T01:09:19.502607+00:00"},{"alias_kind":"pith_short_12","alias_value":"XD64DWWDUST4","created_at":"2026-06-11T01:09:19.502607+00:00"},{"alias_kind":"pith_short_16","alias_value":"XD64DWWDUST4QIR4","created_at":"2026-06-11T01:09:19.502607+00:00"},{"alias_kind":"pith_short_8","alias_value":"XD64DWWD","created_at":"2026-06-11T01:09:19.502607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.22467","citing_title":"SADGE: Structure and Appearance Domain Gap Estimation of Synthetic and Real Data","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XD64DWWDUST4QIR4ERANPQ3GY4","json":"https://pith.science/pith/XD64DWWDUST4QIR4ERANPQ3GY4.json","graph_json":"https://pith.science/api/pith-number/XD64DWWDUST4QIR4ERANPQ3GY4/graph.json","events_json":"https://pith.science/api/pith-number/XD64DWWDUST4QIR4ERANPQ3GY4/events.json","paper":"https://pith.science/paper/XD64DWWD"},"agent_actions":{"view_html":"https://pith.science/pith/XD64DWWDUST4QIR4ERANPQ3GY4","download_json":"https://pith.science/pith/XD64DWWDUST4QIR4ERANPQ3GY4.json","view_paper":"https://pith.science/paper/XD64DWWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.06596&json=true","fetch_graph":"https://pith.science/api/pith-number/XD64DWWDUST4QIR4ERANPQ3GY4/graph.json","fetch_events":"https://pith.science/api/pith-number/XD64DWWDUST4QIR4ERANPQ3GY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XD64DWWDUST4QIR4ERANPQ3GY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XD64DWWDUST4QIR4ERANPQ3GY4/action/storage_attestation","attest_author":"https://pith.science/pith/XD64DWWDUST4QIR4ERANPQ3GY4/action/author_attestation","sign_citation":"https://pith.science/pith/XD64DWWDUST4QIR4ERANPQ3GY4/action/citation_signature","submit_replication":"https://pith.science/pith/XD64DWWDUST4QIR4ERANPQ3GY4/action/replication_record"}},"created_at":"2026-06-11T01:09:19.502607+00:00","updated_at":"2026-06-11T01:09:19.502607+00:00"}