{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NLRW7H3ZJHLEOL7IKZKEEHEXTA","short_pith_number":"pith:NLRW7H3Z","schema_version":"1.0","canonical_sha256":"6ae36f9f7949d6472fe85654421c979808bed40007c514a301f72c168306067c","source":{"kind":"arxiv","id":"2202.00632","version":1},"attestation_state":"computed","paper":{"title":"Reducing the Amount of Real World Data for Object Detector Training with Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Hasenklever, Karoline Plum, Sven Burdorf","submitted_at":"2022-01-31T08:13:12Z","abstract_excerpt":"A number of studies have investigated the training of neural networks with synthetic data for applications in the real world. The aim of this study is to quantify how much real world data can be saved when using a mixed dataset of synthetic and real world data. By modeling the relationship between the number of training examples and detection performance by a simple power law, we find that the need for real world data can be reduced by up to 70% without sacrificing detection performance. The training of object detection networks is especially enhanced by enriching the mixed dataset with classe"},"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":"2202.00632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-31T08:13:12Z","cross_cats_sorted":[],"title_canon_sha256":"d4fb12d5ebc39af0763c3123b17b0727f56cdb737c654f08093dde3aeed19041","abstract_canon_sha256":"709525ed97999d3fbdcfeb0d175da80e7ca4e14b62e58b3e25e3e1e5b995a9b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:23.870695Z","signature_b64":"dlI48z+OmJENXTIobJNERDFbL81Mga3qBFyFISgNlPt2RWF5KvcFxOFgfmwqSn9i8iejtUbRayoZnvOo7Rh6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ae36f9f7949d6472fe85654421c979808bed40007c514a301f72c168306067c","last_reissued_at":"2026-07-05T03:53:23.870265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:23.870265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reducing the Amount of Real World Data for Object Detector Training with Synthetic Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Hasenklever, Karoline Plum, Sven Burdorf","submitted_at":"2022-01-31T08:13:12Z","abstract_excerpt":"A number of studies have investigated the training of neural networks with synthetic data for applications in the real world. The aim of this study is to quantify how much real world data can be saved when using a mixed dataset of synthetic and real world data. By modeling the relationship between the number of training examples and detection performance by a simple power law, we find that the need for real world data can be reduced by up to 70% without sacrificing detection performance. The training of object detection networks is especially enhanced by enriching the mixed dataset with classe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00632","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/2202.00632/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":"2202.00632","created_at":"2026-07-05T03:53:23.870325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00632v1","created_at":"2026-07-05T03:53:23.870325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00632","created_at":"2026-07-05T03:53:23.870325+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLRW7H3ZJHLE","created_at":"2026-07-05T03:53:23.870325+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLRW7H3ZJHLEOL7I","created_at":"2026-07-05T03:53:23.870325+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLRW7H3Z","created_at":"2026-07-05T03:53:23.870325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.24093","citing_title":"Development of Hybrid Artificial Intelligence Training on Real and Synthetic Data: Benchmark on Two Mixed Training Strategies","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NLRW7H3ZJHLEOL7IKZKEEHEXTA","json":"https://pith.science/pith/NLRW7H3ZJHLEOL7IKZKEEHEXTA.json","graph_json":"https://pith.science/api/pith-number/NLRW7H3ZJHLEOL7IKZKEEHEXTA/graph.json","events_json":"https://pith.science/api/pith-number/NLRW7H3ZJHLEOL7IKZKEEHEXTA/events.json","paper":"https://pith.science/paper/NLRW7H3Z"},"agent_actions":{"view_html":"https://pith.science/pith/NLRW7H3ZJHLEOL7IKZKEEHEXTA","download_json":"https://pith.science/pith/NLRW7H3ZJHLEOL7IKZKEEHEXTA.json","view_paper":"https://pith.science/paper/NLRW7H3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00632&json=true","fetch_graph":"https://pith.science/api/pith-number/NLRW7H3ZJHLEOL7IKZKEEHEXTA/graph.json","fetch_events":"https://pith.science/api/pith-number/NLRW7H3ZJHLEOL7IKZKEEHEXTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLRW7H3ZJHLEOL7IKZKEEHEXTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLRW7H3ZJHLEOL7IKZKEEHEXTA/action/storage_attestation","attest_author":"https://pith.science/pith/NLRW7H3ZJHLEOL7IKZKEEHEXTA/action/author_attestation","sign_citation":"https://pith.science/pith/NLRW7H3ZJHLEOL7IKZKEEHEXTA/action/citation_signature","submit_replication":"https://pith.science/pith/NLRW7H3ZJHLEOL7IKZKEEHEXTA/action/replication_record"}},"created_at":"2026-07-05T03:53:23.870325+00:00","updated_at":"2026-07-05T03:53:23.870325+00:00"}