{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:USXELHDZGPG6FN5JBF7QUTTCE4","short_pith_number":"pith:USXELHDZ","schema_version":"1.0","canonical_sha256":"a4ae459c7933cde2b7a9097f0a4e62272df41626a230aad9dd7feef9c6c395b9","source":{"kind":"arxiv","id":"2202.11616","version":2},"attestation_state":"computed","paper":{"title":"ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bodo Rosenhahn, Christoph Reinders, Frederik Schubert","submitted_at":"2022-02-23T16:51:22Z","abstract_excerpt":"Deep convolutional neural networks require large amounts of labeled data samples. For many real-world applications, this is a major limitation which is commonly treated by augmentation methods. In this work, we address the problem of learning deep neural networks on small datasets. Our proposed architecture called ChimeraMix learns a data augmentation by generating compositions of instances. The generative model encodes images in pairs, combines the features guided by a mask, and creates new samples. For evaluation, all methods are trained from scratch without any additional data. Several expe"},"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":"2202.11616","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-23T16:51:22Z","cross_cats_sorted":[],"title_canon_sha256":"51691643bfd167dcf40f27bc89967365f5f47157e3a2685304bad8b2e8f5df5f","abstract_canon_sha256":"b3e3ca1f5f9a708f1ede5dde72a8d50770e52dc00cccb4d627e8f9b9e358f35d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:29.304542Z","signature_b64":"OWqtoqTxInNCMbpKiUEyEkbzcBtN7XZaMyT32D/Uf6JyuV9xYKrRUQ5OVHTExCuMto79Cew+0Wnh8Snpx0wLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4ae459c7933cde2b7a9097f0a4e62272df41626a230aad9dd7feef9c6c395b9","last_reissued_at":"2026-07-05T04:44:29.304093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:29.304093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bodo Rosenhahn, Christoph Reinders, Frederik Schubert","submitted_at":"2022-02-23T16:51:22Z","abstract_excerpt":"Deep convolutional neural networks require large amounts of labeled data samples. For many real-world applications, this is a major limitation which is commonly treated by augmentation methods. In this work, we address the problem of learning deep neural networks on small datasets. Our proposed architecture called ChimeraMix learns a data augmentation by generating compositions of instances. The generative model encodes images in pairs, combines the features guided by a mask, and creates new samples. For evaluation, all methods are trained from scratch without any additional data. Several expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.11616","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/2202.11616/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":"2202.11616","created_at":"2026-07-05T04:44:29.304153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.11616v2","created_at":"2026-07-05T04:44:29.304153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.11616","created_at":"2026-07-05T04:44:29.304153+00:00"},{"alias_kind":"pith_short_12","alias_value":"USXELHDZGPG6","created_at":"2026-07-05T04:44:29.304153+00:00"},{"alias_kind":"pith_short_16","alias_value":"USXELHDZGPG6FN5J","created_at":"2026-07-05T04:44:29.304153+00:00"},{"alias_kind":"pith_short_8","alias_value":"USXELHDZ","created_at":"2026-07-05T04:44:29.304153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/USXELHDZGPG6FN5JBF7QUTTCE4","json":"https://pith.science/pith/USXELHDZGPG6FN5JBF7QUTTCE4.json","graph_json":"https://pith.science/api/pith-number/USXELHDZGPG6FN5JBF7QUTTCE4/graph.json","events_json":"https://pith.science/api/pith-number/USXELHDZGPG6FN5JBF7QUTTCE4/events.json","paper":"https://pith.science/paper/USXELHDZ"},"agent_actions":{"view_html":"https://pith.science/pith/USXELHDZGPG6FN5JBF7QUTTCE4","download_json":"https://pith.science/pith/USXELHDZGPG6FN5JBF7QUTTCE4.json","view_paper":"https://pith.science/paper/USXELHDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.11616&json=true","fetch_graph":"https://pith.science/api/pith-number/USXELHDZGPG6FN5JBF7QUTTCE4/graph.json","fetch_events":"https://pith.science/api/pith-number/USXELHDZGPG6FN5JBF7QUTTCE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/USXELHDZGPG6FN5JBF7QUTTCE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/USXELHDZGPG6FN5JBF7QUTTCE4/action/storage_attestation","attest_author":"https://pith.science/pith/USXELHDZGPG6FN5JBF7QUTTCE4/action/author_attestation","sign_citation":"https://pith.science/pith/USXELHDZGPG6FN5JBF7QUTTCE4/action/citation_signature","submit_replication":"https://pith.science/pith/USXELHDZGPG6FN5JBF7QUTTCE4/action/replication_record"}},"created_at":"2026-07-05T04:44:29.304153+00:00","updated_at":"2026-07-05T04:44:29.304153+00:00"}