{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FXIVIKNQGZ56W7W6VG6R2EYEOR","short_pith_number":"pith:FXIVIKNQ","canonical_record":{"source":{"id":"2410.23672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T06:41:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6c13f83a9319d4f28f4c1cf35e773927862215a8dc652743f44fad00a82aa134","abstract_canon_sha256":"423815230579a9f9c712721edec69917092a93b600d0da4644899ddd8cf78329"},"schema_version":"1.0"},"canonical_sha256":"2dd15429b0367beb7edea9bd1d1304744dee2e6384cf2f3b051fce56b274a61e","source":{"kind":"arxiv","id":"2410.23672","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23672","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23672v1","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23672","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"pith_short_12","alias_value":"FXIVIKNQGZ56","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"pith_short_16","alias_value":"FXIVIKNQGZ56W7W6","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"pith_short_8","alias_value":"FXIVIKNQ","created_at":"2026-07-05T09:29:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FXIVIKNQGZ56W7W6VG6R2EYEOR","target":"record","payload":{"canonical_record":{"source":{"id":"2410.23672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T06:41:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6c13f83a9319d4f28f4c1cf35e773927862215a8dc652743f44fad00a82aa134","abstract_canon_sha256":"423815230579a9f9c712721edec69917092a93b600d0da4644899ddd8cf78329"},"schema_version":"1.0"},"canonical_sha256":"2dd15429b0367beb7edea9bd1d1304744dee2e6384cf2f3b051fce56b274a61e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:03.695045Z","signature_b64":"62b/jcE8uYZ5GIiwKaJ/nPyrvhl+Qaecd8LemCaqbt4QaI2AGcwONMzhlju0loxKFOSOI8EagP7dZP2BL8fUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dd15429b0367beb7edea9bd1d1304744dee2e6384cf2f3b051fce56b274a61e","last_reissued_at":"2026-07-05T09:29:03.694549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:03.694549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.23672","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:29:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UlYcCXj+Z28YdvKdveE/o+RIYWrfAXyQB/+ZyI0vdBsjuMjMTUQiuYDpojG5MtM0ZN18+IVAf0ntcBioEsAkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:36:17.222628Z"},"content_sha256":"f813c588af6c4898c4893c8b65a2b07f965b56f9ae309a421a8a74bcfcbee052","schema_version":"1.0","event_id":"sha256:f813c588af6c4898c4893c8b65a2b07f965b56f9ae309a421a8a74bcfcbee052"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FXIVIKNQGZ56W7W6VG6R2EYEOR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provable Benefit of Cutout and CutMix for Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chulhee Yun, Junsoo Oh","submitted_at":"2024-10-31T06:41:10Z","abstract_excerpt":"Patch-level data augmentation techniques such as Cutout and CutMix have demonstrated significant efficacy in enhancing the performance of vision tasks. However, a comprehensive theoretical understanding of these methods remains elusive. In this paper, we study two-layer neural networks trained using three distinct methods: vanilla training without augmentation, Cutout training, and CutMix training. Our analysis focuses on a feature-noise data model, which consists of several label-dependent features of varying rarity and label-independent noises of differing strengths. Our theorems demonstrate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23672","kind":"arxiv","version":1},"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/2410.23672/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":"2026-07-05T09:29:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7luJX0vyA/86BjxydMCZ5fgsNRdC4/03s4cyFvYjDUxAn7s6VC4QCafxEZorzYqz/rUZInYQLW3+tOFcgMvlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:36:17.223133Z"},"content_sha256":"daa30862dc2f5f83428dc2c406f278fd7f25ef0ba50c658b6725314a8bba9cd7","schema_version":"1.0","event_id":"sha256:daa30862dc2f5f83428dc2c406f278fd7f25ef0ba50c658b6725314a8bba9cd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FXIVIKNQGZ56W7W6VG6R2EYEOR/bundle.json","state_url":"https://pith.science/pith/FXIVIKNQGZ56W7W6VG6R2EYEOR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FXIVIKNQGZ56W7W6VG6R2EYEOR/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":"2026-08-08T21:36:17Z","links":{"resolver":"https://pith.science/pith/FXIVIKNQGZ56W7W6VG6R2EYEOR","bundle":"https://pith.science/pith/FXIVIKNQGZ56W7W6VG6R2EYEOR/bundle.json","state":"https://pith.science/pith/FXIVIKNQGZ56W7W6VG6R2EYEOR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FXIVIKNQGZ56W7W6VG6R2EYEOR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FXIVIKNQGZ56W7W6VG6R2EYEOR","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":"423815230579a9f9c712721edec69917092a93b600d0da4644899ddd8cf78329","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T06:41:10Z","title_canon_sha256":"6c13f83a9319d4f28f4c1cf35e773927862215a8dc652743f44fad00a82aa134"},"schema_version":"1.0","source":{"id":"2410.23672","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23672","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23672v1","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23672","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"pith_short_12","alias_value":"FXIVIKNQGZ56","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"pith_short_16","alias_value":"FXIVIKNQGZ56W7W6","created_at":"2026-07-05T09:29:03Z"},{"alias_kind":"pith_short_8","alias_value":"FXIVIKNQ","created_at":"2026-07-05T09:29:03Z"}],"graph_snapshots":[{"event_id":"sha256:daa30862dc2f5f83428dc2c406f278fd7f25ef0ba50c658b6725314a8bba9cd7","target":"graph","created_at":"2026-07-05T09:29:03Z","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/2410.23672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Patch-level data augmentation techniques such as Cutout and CutMix have demonstrated significant efficacy in enhancing the performance of vision tasks. However, a comprehensive theoretical understanding of these methods remains elusive. In this paper, we study two-layer neural networks trained using three distinct methods: vanilla training without augmentation, Cutout training, and CutMix training. Our analysis focuses on a feature-noise data model, which consists of several label-dependent features of varying rarity and label-independent noises of differing strengths. Our theorems demonstrate","authors_text":"Chulhee Yun, Junsoo Oh","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T06:41:10Z","title":"Provable Benefit of Cutout and CutMix for Feature Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23672","kind":"arxiv","version":1},"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:f813c588af6c4898c4893c8b65a2b07f965b56f9ae309a421a8a74bcfcbee052","target":"record","created_at":"2026-07-05T09:29:03Z","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":"423815230579a9f9c712721edec69917092a93b600d0da4644899ddd8cf78329","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T06:41:10Z","title_canon_sha256":"6c13f83a9319d4f28f4c1cf35e773927862215a8dc652743f44fad00a82aa134"},"schema_version":"1.0","source":{"id":"2410.23672","kind":"arxiv","version":1}},"canonical_sha256":"2dd15429b0367beb7edea9bd1d1304744dee2e6384cf2f3b051fce56b274a61e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2dd15429b0367beb7edea9bd1d1304744dee2e6384cf2f3b051fce56b274a61e","first_computed_at":"2026-07-05T09:29:03.694549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:03.694549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"62b/jcE8uYZ5GIiwKaJ/nPyrvhl+Qaecd8LemCaqbt4QaI2AGcwONMzhlju0loxKFOSOI8EagP7dZP2BL8fUBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:03.695045Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23672","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f813c588af6c4898c4893c8b65a2b07f965b56f9ae309a421a8a74bcfcbee052","sha256:daa30862dc2f5f83428dc2c406f278fd7f25ef0ba50c658b6725314a8bba9cd7"],"state_sha256":"1b427008b05c5f5a08011ec60eea9333d010c890ef35612d69f7054b48a0f9fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0cWHhdLiNEOqDRr/UyXasZsVjRDQQ1q7Y4tD/a1h7gXprE0QNud4PvAzqxoz0Y5d52TpZnw85BECGNbG7vKlCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:36:17.227329Z","bundle_sha256":"35442e3e194f70e5806b2b5ab6531044162603af91c4f685a02414fdf5ddc3af"}}