{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7CUDZVLMTJUNPVDKQ5LHFRIMPJ","short_pith_number":"pith:7CUDZVLM","canonical_record":{"source":{"id":"2009.06962","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-15T10:10:23Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"3e4b0f492ee58852354eb58a1ef4cda96fa471605dde626085fe2492f208335a","abstract_canon_sha256":"8f6218f6b4e08e06d4cd792589d17992601b0e13ee41edd57b6b8a0f90a3da3a"},"schema_version":"1.0"},"canonical_sha256":"f8a83cd56c9a68d7d46a875672c50c7a528e344ee1dd4ef4dcf4ec4c98c6a20c","source":{"kind":"arxiv","id":"2009.06962","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.06962","created_at":"2026-07-05T02:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2009.06962v2","created_at":"2026-07-05T02:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.06962","created_at":"2026-07-05T02:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"7CUDZVLMTJUN","created_at":"2026-07-05T02:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"7CUDZVLMTJUNPVDK","created_at":"2026-07-05T02:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"7CUDZVLM","created_at":"2026-07-05T02:02:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7CUDZVLMTJUNPVDKQ5LHFRIMPJ","target":"record","payload":{"canonical_record":{"source":{"id":"2009.06962","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-15T10:10:23Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"3e4b0f492ee58852354eb58a1ef4cda96fa471605dde626085fe2492f208335a","abstract_canon_sha256":"8f6218f6b4e08e06d4cd792589d17992601b0e13ee41edd57b6b8a0f90a3da3a"},"schema_version":"1.0"},"canonical_sha256":"f8a83cd56c9a68d7d46a875672c50c7a528e344ee1dd4ef4dcf4ec4c98c6a20c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:55.706943Z","signature_b64":"K15XO8JdXbICTbE0IbmhlUjk6+LNKSIpa3qLo0FlEYOEsDMTH3AQMNpAYOrnzMaTfbuRX14rk7uniZx9pAYXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8a83cd56c9a68d7d46a875672c50c7a528e344ee1dd4ef4dcf4ec4c98c6a20c","last_reissued_at":"2026-07-05T02:02:55.702268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:55.702268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.06962","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DFPwFtooh/3OWR6Njz0Z9SsHArU4YLSTpmbLLPtj1m7F4GaS7ahE3yA4OKoKUE/dA+AmTtMTDc0Jx09qB9MUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:19:59.445652Z"},"content_sha256":"f5e13effc16321614c614ba9c895489a73ce42a014925377d94222801acaabda","schema_version":"1.0","event_id":"sha256:f5e13effc16321614c614ba9c895489a73ce42a014925377d94222801acaabda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7CUDZVLMTJUNPVDKQ5LHFRIMPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyun Oh Song, Jang-Hyun Kim, Wonho Choo","submitted_at":"2020-09-15T10:10:23Z","abstract_excerpt":"While deep neural networks achieve great performance on fitting the training distribution, the learned networks are prone to overfitting and are susceptible to adversarial attacks. In this regard, a number of mixup based augmentation methods have been recently proposed. However, these approaches mainly focus on creating previously unseen virtual examples and can sometimes provide misleading supervisory signal to the network. To this end, we propose Puzzle Mix, a mixup method for explicitly utilizing the saliency information and the underlying statistics of the natural examples. This leads to a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.06962","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/2009.06962/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tiFNWYRUdmo/+HLX7ACHo0xD4b9WdKVjYicrqnlCpcJJVE7cPdp3MmK8gyuMpElNjmWPvA/LAQhAgbfjy2HXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:19:59.447575Z"},"content_sha256":"2187989eb637141f786eb5fea1f87877abbb891def6e4fc801e095a0121a9c82","schema_version":"1.0","event_id":"sha256:2187989eb637141f786eb5fea1f87877abbb891def6e4fc801e095a0121a9c82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7CUDZVLMTJUNPVDKQ5LHFRIMPJ/bundle.json","state_url":"https://pith.science/pith/7CUDZVLMTJUNPVDKQ5LHFRIMPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7CUDZVLMTJUNPVDKQ5LHFRIMPJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T12:19:59Z","links":{"resolver":"https://pith.science/pith/7CUDZVLMTJUNPVDKQ5LHFRIMPJ","bundle":"https://pith.science/pith/7CUDZVLMTJUNPVDKQ5LHFRIMPJ/bundle.json","state":"https://pith.science/pith/7CUDZVLMTJUNPVDKQ5LHFRIMPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7CUDZVLMTJUNPVDKQ5LHFRIMPJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7CUDZVLMTJUNPVDKQ5LHFRIMPJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8f6218f6b4e08e06d4cd792589d17992601b0e13ee41edd57b6b8a0f90a3da3a","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-15T10:10:23Z","title_canon_sha256":"3e4b0f492ee58852354eb58a1ef4cda96fa471605dde626085fe2492f208335a"},"schema_version":"1.0","source":{"id":"2009.06962","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.06962","created_at":"2026-07-05T02:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2009.06962v2","created_at":"2026-07-05T02:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.06962","created_at":"2026-07-05T02:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"7CUDZVLMTJUN","created_at":"2026-07-05T02:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"7CUDZVLMTJUNPVDK","created_at":"2026-07-05T02:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"7CUDZVLM","created_at":"2026-07-05T02:02:55Z"}],"graph_snapshots":[{"event_id":"sha256:2187989eb637141f786eb5fea1f87877abbb891def6e4fc801e095a0121a9c82","target":"graph","created_at":"2026-07-05T02:02:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2009.06962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While deep neural networks achieve great performance on fitting the training distribution, the learned networks are prone to overfitting and are susceptible to adversarial attacks. In this regard, a number of mixup based augmentation methods have been recently proposed. However, these approaches mainly focus on creating previously unseen virtual examples and can sometimes provide misleading supervisory signal to the network. To this end, we propose Puzzle Mix, a mixup method for explicitly utilizing the saliency information and the underlying statistics of the natural examples. This leads to a","authors_text":"Hyun Oh Song, Jang-Hyun Kim, Wonho Choo","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-15T10:10:23Z","title":"Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.06962","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f5e13effc16321614c614ba9c895489a73ce42a014925377d94222801acaabda","target":"record","created_at":"2026-07-05T02:02:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8f6218f6b4e08e06d4cd792589d17992601b0e13ee41edd57b6b8a0f90a3da3a","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-15T10:10:23Z","title_canon_sha256":"3e4b0f492ee58852354eb58a1ef4cda96fa471605dde626085fe2492f208335a"},"schema_version":"1.0","source":{"id":"2009.06962","kind":"arxiv","version":2}},"canonical_sha256":"f8a83cd56c9a68d7d46a875672c50c7a528e344ee1dd4ef4dcf4ec4c98c6a20c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8a83cd56c9a68d7d46a875672c50c7a528e344ee1dd4ef4dcf4ec4c98c6a20c","first_computed_at":"2026-07-05T02:02:55.702268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:02:55.702268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K15XO8JdXbICTbE0IbmhlUjk6+LNKSIpa3qLo0FlEYOEsDMTH3AQMNpAYOrnzMaTfbuRX14rk7uniZx9pAYXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:02:55.706943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.06962","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5e13effc16321614c614ba9c895489a73ce42a014925377d94222801acaabda","sha256:2187989eb637141f786eb5fea1f87877abbb891def6e4fc801e095a0121a9c82"],"state_sha256":"280e1567bfdabd75976c822486e9ca608130f0f3524885ebded674ba939bf683"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Ze3FFWuzy/i9cxYftiSW8ozhd6l4OP/bXlnrIXs82EGV80Y6jjHW4hpBTba6nz03IUybmvCgynzPj4EyQKTAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:19:59.452052Z","bundle_sha256":"165e6b57764137afe181090eed82187cccca7649f42e8e233d1209f3290c4fb8"}}