{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T4DIQXRP5CAN4DWCQESHFOEUVR","short_pith_number":"pith:T4DIQXRP","schema_version":"1.0","canonical_sha256":"9f06885e2fe880de0ec2812472b894ac612c86ec2b4bfb29d7db56d171d18346","source":{"kind":"arxiv","id":"2407.07805","version":5},"attestation_state":"computed","paper":{"title":"SUMix: Mixup with Semantic and Uncertain Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongchao Liao, Hongyu Zhu, Huafeng Qin, Moun\\^im A. El-Yacoubi, Xinbo Gao, Xin Jin","submitted_at":"2024-07-10T16:25:26Z","abstract_excerpt":"Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image with patches from another to generate the mixed image. Similarly, the corresponding labels are linearly combined by a fixed ratio $\\lambda$ by l. The objects in two images may be overlapped during the mixing process, so some semantic information is corrupted in the mixed samples. In this case, the mixed image does not match the mixed label information. Besid"},"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":"2407.07805","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T16:25:26Z","cross_cats_sorted":[],"title_canon_sha256":"0613059f618cd4681f7dc56f1b5dec2262a81cced47d63fb4f95a0b5b90ba2b2","abstract_canon_sha256":"8392d3cea1b3b1f2d21dcf92fc424bbe44f3e20a4ef0841a6a69a85b5c92d04f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:05.629443Z","signature_b64":"wnFAY4Y2Q95XoTgEFWV2CgiyPau+JT5aSN+yVPc5FFLVQQD6lxgGbTYvZ7yMdH4EQZt0rcwZCn8JZPEv4DxCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f06885e2fe880de0ec2812472b894ac612c86ec2b4bfb29d7db56d171d18346","last_reissued_at":"2026-07-05T09:09:05.628977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:05.628977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SUMix: Mixup with Semantic and Uncertain Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongchao Liao, Hongyu Zhu, Huafeng Qin, Moun\\^im A. El-Yacoubi, Xinbo Gao, Xin Jin","submitted_at":"2024-07-10T16:25:26Z","abstract_excerpt":"Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image with patches from another to generate the mixed image. Similarly, the corresponding labels are linearly combined by a fixed ratio $\\lambda$ by l. The objects in two images may be overlapped during the mixing process, so some semantic information is corrupted in the mixed samples. In this case, the mixed image does not match the mixed label information. Besid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07805","kind":"arxiv","version":5},"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/2407.07805/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":"2407.07805","created_at":"2026-07-05T09:09:05.629033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07805v5","created_at":"2026-07-05T09:09:05.629033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07805","created_at":"2026-07-05T09:09:05.629033+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4DIQXRP5CAN","created_at":"2026-07-05T09:09:05.629033+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4DIQXRP5CAN4DWC","created_at":"2026-07-05T09:09:05.629033+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4DIQXRP","created_at":"2026-07-05T09:09:05.629033+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/T4DIQXRP5CAN4DWCQESHFOEUVR","json":"https://pith.science/pith/T4DIQXRP5CAN4DWCQESHFOEUVR.json","graph_json":"https://pith.science/api/pith-number/T4DIQXRP5CAN4DWCQESHFOEUVR/graph.json","events_json":"https://pith.science/api/pith-number/T4DIQXRP5CAN4DWCQESHFOEUVR/events.json","paper":"https://pith.science/paper/T4DIQXRP"},"agent_actions":{"view_html":"https://pith.science/pith/T4DIQXRP5CAN4DWCQESHFOEUVR","download_json":"https://pith.science/pith/T4DIQXRP5CAN4DWCQESHFOEUVR.json","view_paper":"https://pith.science/paper/T4DIQXRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07805&json=true","fetch_graph":"https://pith.science/api/pith-number/T4DIQXRP5CAN4DWCQESHFOEUVR/graph.json","fetch_events":"https://pith.science/api/pith-number/T4DIQXRP5CAN4DWCQESHFOEUVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4DIQXRP5CAN4DWCQESHFOEUVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4DIQXRP5CAN4DWCQESHFOEUVR/action/storage_attestation","attest_author":"https://pith.science/pith/T4DIQXRP5CAN4DWCQESHFOEUVR/action/author_attestation","sign_citation":"https://pith.science/pith/T4DIQXRP5CAN4DWCQESHFOEUVR/action/citation_signature","submit_replication":"https://pith.science/pith/T4DIQXRP5CAN4DWCQESHFOEUVR/action/replication_record"}},"created_at":"2026-07-05T09:09:05.629033+00:00","updated_at":"2026-07-05T09:09:05.629033+00:00"}