{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:X5BIM7OORHV7UUYPCNHSBDAWXO","short_pith_number":"pith:X5BIM7OO","canonical_record":{"source":{"id":"2003.13048","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-29T15:01:05Z","cross_cats_sorted":[],"title_canon_sha256":"40cbf72f08e41c3191d28a92e732165e200d163e39ce23533ac59bf17a2e4301","abstract_canon_sha256":"901b9d0a5858429d5f880be7d00ef06ee90bcb470c6bcb2aa13e783c76953ec3"},"schema_version":"1.0"},"canonical_sha256":"bf42867dce89ebfa530f134f208c16bb854c151da5547ee612b34fbdd5fb1603","source":{"kind":"arxiv","id":"2003.13048","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13048","created_at":"2026-07-05T00:52:53Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13048v2","created_at":"2026-07-05T00:52:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13048","created_at":"2026-07-05T00:52:53Z"},{"alias_kind":"pith_short_12","alias_value":"X5BIM7OORHV7","created_at":"2026-07-05T00:52:53Z"},{"alias_kind":"pith_short_16","alias_value":"X5BIM7OORHV7UUYP","created_at":"2026-07-05T00:52:53Z"},{"alias_kind":"pith_short_8","alias_value":"X5BIM7OO","created_at":"2026-07-05T00:52:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:X5BIM7OORHV7UUYPCNHSBDAWXO","target":"record","payload":{"canonical_record":{"source":{"id":"2003.13048","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-29T15:01:05Z","cross_cats_sorted":[],"title_canon_sha256":"40cbf72f08e41c3191d28a92e732165e200d163e39ce23533ac59bf17a2e4301","abstract_canon_sha256":"901b9d0a5858429d5f880be7d00ef06ee90bcb470c6bcb2aa13e783c76953ec3"},"schema_version":"1.0"},"canonical_sha256":"bf42867dce89ebfa530f134f208c16bb854c151da5547ee612b34fbdd5fb1603","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:53.449901Z","signature_b64":"nQy+qvcJaV/QTUJfIBk/5shP86KknV/JGYSmBHr/4I18YKpqT9vYvM4qOUxIQrsLrcSeq63pna40rzqvD32KDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf42867dce89ebfa530f134f208c16bb854c151da5547ee612b34fbdd5fb1603","last_reissued_at":"2026-07-05T00:52:53.449474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:53.449474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.13048","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":"2026-07-05T00:52:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aKFNgHmEhMjDSYnDxaIj++xKXePNH0jBur45Ch8Mf6bI06XH0X6XQibR+qqlUfVS9Mcyx+3EvcKBpadzDZ/bBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:44:05.168221Z"},"content_sha256":"117d4ea2c9caeca312bc3b1932459cfb83fc9ed0c225fefe698ebec8691e435f","schema_version":"1.0","event_id":"sha256:117d4ea2c9caeca312bc3b1932459cfb83fc9ed0c225fefe698ebec8691e435f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:X5BIM7OORHV7UUYPCNHSBDAWXO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Devesh Walawalkar, Marios Savvides, Zechun Liu, Zhiqiang Shen","submitted_at":"2020-03-29T15:01:05Z","abstract_excerpt":"Convolutional neural networks (CNN) are capable of learning robust representation with different regularization methods and activations as convolutional layers are spatially correlated. Based on this property, a large variety of regional dropout strategies have been proposed, such as Cutout, DropBlock, CutMix, etc. These methods aim to promote the network to generalize better by partially occluding the discriminative parts of objects. However, all of them perform this operation randomly, without capturing the most important region(s) within an object. In this paper, we propose Attentive CutMix"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13048","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/2003.13048/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":"2026-07-05T00:52:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6RQO24Fkx/Y2OCT3k1qgbNzDzrV+0TrPm2IG2l/lVGUn/FsvX0OY4JfeoAV5sugCI0ps1rd0pJEIh2ucWJEIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:44:05.168817Z"},"content_sha256":"b878233a089e36598817e3af804246e3ce5d416541071b0ff378e491113e2547","schema_version":"1.0","event_id":"sha256:b878233a089e36598817e3af804246e3ce5d416541071b0ff378e491113e2547"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X5BIM7OORHV7UUYPCNHSBDAWXO/bundle.json","state_url":"https://pith.science/pith/X5BIM7OORHV7UUYPCNHSBDAWXO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X5BIM7OORHV7UUYPCNHSBDAWXO/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":"2026-08-22T13:44:05Z","links":{"resolver":"https://pith.science/pith/X5BIM7OORHV7UUYPCNHSBDAWXO","bundle":"https://pith.science/pith/X5BIM7OORHV7UUYPCNHSBDAWXO/bundle.json","state":"https://pith.science/pith/X5BIM7OORHV7UUYPCNHSBDAWXO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X5BIM7OORHV7UUYPCNHSBDAWXO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:X5BIM7OORHV7UUYPCNHSBDAWXO","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":"901b9d0a5858429d5f880be7d00ef06ee90bcb470c6bcb2aa13e783c76953ec3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-29T15:01:05Z","title_canon_sha256":"40cbf72f08e41c3191d28a92e732165e200d163e39ce23533ac59bf17a2e4301"},"schema_version":"1.0","source":{"id":"2003.13048","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13048","created_at":"2026-07-05T00:52:53Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13048v2","created_at":"2026-07-05T00:52:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13048","created_at":"2026-07-05T00:52:53Z"},{"alias_kind":"pith_short_12","alias_value":"X5BIM7OORHV7","created_at":"2026-07-05T00:52:53Z"},{"alias_kind":"pith_short_16","alias_value":"X5BIM7OORHV7UUYP","created_at":"2026-07-05T00:52:53Z"},{"alias_kind":"pith_short_8","alias_value":"X5BIM7OO","created_at":"2026-07-05T00:52:53Z"}],"graph_snapshots":[{"event_id":"sha256:b878233a089e36598817e3af804246e3ce5d416541071b0ff378e491113e2547","target":"graph","created_at":"2026-07-05T00:52:53Z","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/2003.13048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Convolutional neural networks (CNN) are capable of learning robust representation with different regularization methods and activations as convolutional layers are spatially correlated. Based on this property, a large variety of regional dropout strategies have been proposed, such as Cutout, DropBlock, CutMix, etc. These methods aim to promote the network to generalize better by partially occluding the discriminative parts of objects. However, all of them perform this operation randomly, without capturing the most important region(s) within an object. In this paper, we propose Attentive CutMix","authors_text":"Devesh Walawalkar, Marios Savvides, Zechun Liu, Zhiqiang Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-29T15:01:05Z","title":"Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13048","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":"sha256:117d4ea2c9caeca312bc3b1932459cfb83fc9ed0c225fefe698ebec8691e435f","target":"record","created_at":"2026-07-05T00:52:53Z","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":"901b9d0a5858429d5f880be7d00ef06ee90bcb470c6bcb2aa13e783c76953ec3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-03-29T15:01:05Z","title_canon_sha256":"40cbf72f08e41c3191d28a92e732165e200d163e39ce23533ac59bf17a2e4301"},"schema_version":"1.0","source":{"id":"2003.13048","kind":"arxiv","version":2}},"canonical_sha256":"bf42867dce89ebfa530f134f208c16bb854c151da5547ee612b34fbdd5fb1603","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf42867dce89ebfa530f134f208c16bb854c151da5547ee612b34fbdd5fb1603","first_computed_at":"2026-07-05T00:52:53.449474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:52:53.449474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nQy+qvcJaV/QTUJfIBk/5shP86KknV/JGYSmBHr/4I18YKpqT9vYvM4qOUxIQrsLrcSeq63pna40rzqvD32KDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:52:53.449901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.13048","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:117d4ea2c9caeca312bc3b1932459cfb83fc9ed0c225fefe698ebec8691e435f","sha256:b878233a089e36598817e3af804246e3ce5d416541071b0ff378e491113e2547"],"state_sha256":"3bff94aca84f128cd6a32f8383ee2fdeebac7b94ec6e8c61acc9def35c3cb07f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+U19MlY2fl3IwkA2PC+tzfDoSQ261XoCKjos8gUAczYjeuTjB7SWBOD6Y9IJ0+z8Z0CG45eYt9DGyUL9rC5JBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T13:44:05.173429Z","bundle_sha256":"b58ac364b267cf3b649eb15d77ea1b0eeb432044caae04d0c177b7312d775c9e"}}