{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BAOGTU6CVZSWDERXOPY6BEXBVD","short_pith_number":"pith:BAOGTU6C","schema_version":"1.0","canonical_sha256":"081c69d3c2ae6561923773f1e092e1a8d3eb1ecad6e174aff72130e38b0754ad","source":{"kind":"arxiv","id":"2312.11954","version":2},"attestation_state":"computed","paper":{"title":"Adversarial AutoMixup","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huafeng Qin, Mounim A. El-Yacoubi, Xinbo Gao, Xin Jin, Yun Jiang","submitted_at":"2023-12-19T08:55:00Z","abstract_excerpt":"Data mixing augmentation has been widely applied to improve the generalization ability of deep neural networks. Recently, offline data mixing augmentation, e.g. handcrafted and saliency information-based mixup, has been gradually replaced by automatic mixing approaches. Through minimizing two sub-tasks, namely, mixed sample generation and mixup classification in an end-to-end way, AutoMix significantly improves accuracy on image classification tasks. However, as the optimization objective is consistent for the two sub-tasks, this approach is prone to generating consistent instead of diverse mi"},"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":"2312.11954","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T08:55:00Z","cross_cats_sorted":[],"title_canon_sha256":"e5504e2e9e13215bd6944e5e3e4585330b8deab0541b6d824e3c7fab7a6ffe36","abstract_canon_sha256":"2a699503c6bc8c54df0f7057a96e810d11dac9d89a77c9174f6ea6b77e7c9ba1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:10.877979Z","signature_b64":"b8YyqEVQzCMaFvAOrSIer3QTiTlh2LNZbVO33R1S7j8dCJP+Roe/BKXTWDV7RyAILwozM8rB9cWHffnnXv71Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"081c69d3c2ae6561923773f1e092e1a8d3eb1ecad6e174aff72130e38b0754ad","last_reissued_at":"2026-07-05T07:51:10.877496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:10.877496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial AutoMixup","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huafeng Qin, Mounim A. El-Yacoubi, Xinbo Gao, Xin Jin, Yun Jiang","submitted_at":"2023-12-19T08:55:00Z","abstract_excerpt":"Data mixing augmentation has been widely applied to improve the generalization ability of deep neural networks. Recently, offline data mixing augmentation, e.g. handcrafted and saliency information-based mixup, has been gradually replaced by automatic mixing approaches. Through minimizing two sub-tasks, namely, mixed sample generation and mixup classification in an end-to-end way, AutoMix significantly improves accuracy on image classification tasks. However, as the optimization objective is consistent for the two sub-tasks, this approach is prone to generating consistent instead of diverse mi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11954","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/2312.11954/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":"2312.11954","created_at":"2026-07-05T07:51:10.877552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11954v2","created_at":"2026-07-05T07:51:10.877552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11954","created_at":"2026-07-05T07:51:10.877552+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAOGTU6CVZSW","created_at":"2026-07-05T07:51:10.877552+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAOGTU6CVZSWDERX","created_at":"2026-07-05T07:51:10.877552+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAOGTU6C","created_at":"2026-07-05T07:51:10.877552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02927","citing_title":"SaluNet: Enabling Total Plasticity in Normalization-Free Deep Networks","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAOGTU6CVZSWDERXOPY6BEXBVD","json":"https://pith.science/pith/BAOGTU6CVZSWDERXOPY6BEXBVD.json","graph_json":"https://pith.science/api/pith-number/BAOGTU6CVZSWDERXOPY6BEXBVD/graph.json","events_json":"https://pith.science/api/pith-number/BAOGTU6CVZSWDERXOPY6BEXBVD/events.json","paper":"https://pith.science/paper/BAOGTU6C"},"agent_actions":{"view_html":"https://pith.science/pith/BAOGTU6CVZSWDERXOPY6BEXBVD","download_json":"https://pith.science/pith/BAOGTU6CVZSWDERXOPY6BEXBVD.json","view_paper":"https://pith.science/paper/BAOGTU6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11954&json=true","fetch_graph":"https://pith.science/api/pith-number/BAOGTU6CVZSWDERXOPY6BEXBVD/graph.json","fetch_events":"https://pith.science/api/pith-number/BAOGTU6CVZSWDERXOPY6BEXBVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAOGTU6CVZSWDERXOPY6BEXBVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAOGTU6CVZSWDERXOPY6BEXBVD/action/storage_attestation","attest_author":"https://pith.science/pith/BAOGTU6CVZSWDERXOPY6BEXBVD/action/author_attestation","sign_citation":"https://pith.science/pith/BAOGTU6CVZSWDERXOPY6BEXBVD/action/citation_signature","submit_replication":"https://pith.science/pith/BAOGTU6CVZSWDERXOPY6BEXBVD/action/replication_record"}},"created_at":"2026-07-05T07:51:10.877552+00:00","updated_at":"2026-07-05T07:51:10.877552+00:00"}