{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:APU72CPECVGAJALT6J4FZYHAEM","short_pith_number":"pith:APU72CPE","schema_version":"1.0","canonical_sha256":"03e9fd09e4154c048173f2785ce0e02328f2af8969c5659c0c440cfc8dce5dce","source":{"kind":"arxiv","id":"2501.04861","version":2},"attestation_state":"computed","paper":{"title":"LayerMix: Enhanced Data Augmentation through Fractal Integration for Robust Deep Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Afshin Rahimi, Dario Morle, Hafiz Mughees Ahmad","submitted_at":"2025-01-08T22:22:44Z","abstract_excerpt":"Deep learning models have demonstrated remarkable performance across various computer vision tasks, yet their vulnerability to distribution shifts remains a critical challenge. Despite sophisticated neural network architectures, existing models often struggle to maintain consistent performance when confronted with Out-of-Distribution (OOD) samples, including natural corruptions, adversarial perturbations, and anomalous patterns. We introduce LayerMix, an innovative data augmentation approach that systematically enhances model robustness through structured fractal-based image synthesis. By meti"},"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":"2501.04861","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T22:22:44Z","cross_cats_sorted":[],"title_canon_sha256":"2b4bd91bb90cb0526a0ae147dbed97eacdf57b65c9a75335ba85d22125ce794d","abstract_canon_sha256":"43ecb9dec2cc46fe50af5fc6604e2a767987b145f1968eea21550201181ac1df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:59.402041Z","signature_b64":"Zpij6avSNkZ8mkaEDUaq8dF35GOzbC4ublHe/AtkQ3luVndJSNu1zglu5XT3DADSFAFGQsE6pVIQveGst1aWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03e9fd09e4154c048173f2785ce0e02328f2af8969c5659c0c440cfc8dce5dce","last_reissued_at":"2026-07-05T09:59:59.401608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:59.401608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LayerMix: Enhanced Data Augmentation through Fractal Integration for Robust Deep Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Afshin Rahimi, Dario Morle, Hafiz Mughees Ahmad","submitted_at":"2025-01-08T22:22:44Z","abstract_excerpt":"Deep learning models have demonstrated remarkable performance across various computer vision tasks, yet their vulnerability to distribution shifts remains a critical challenge. Despite sophisticated neural network architectures, existing models often struggle to maintain consistent performance when confronted with Out-of-Distribution (OOD) samples, including natural corruptions, adversarial perturbations, and anomalous patterns. We introduce LayerMix, an innovative data augmentation approach that systematically enhances model robustness through structured fractal-based image synthesis. By meti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04861","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/2501.04861/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":"2501.04861","created_at":"2026-07-05T09:59:59.401658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04861v2","created_at":"2026-07-05T09:59:59.401658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04861","created_at":"2026-07-05T09:59:59.401658+00:00"},{"alias_kind":"pith_short_12","alias_value":"APU72CPECVGA","created_at":"2026-07-05T09:59:59.401658+00:00"},{"alias_kind":"pith_short_16","alias_value":"APU72CPECVGAJALT","created_at":"2026-07-05T09:59:59.401658+00:00"},{"alias_kind":"pith_short_8","alias_value":"APU72CPE","created_at":"2026-07-05T09:59:59.401658+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/APU72CPECVGAJALT6J4FZYHAEM","json":"https://pith.science/pith/APU72CPECVGAJALT6J4FZYHAEM.json","graph_json":"https://pith.science/api/pith-number/APU72CPECVGAJALT6J4FZYHAEM/graph.json","events_json":"https://pith.science/api/pith-number/APU72CPECVGAJALT6J4FZYHAEM/events.json","paper":"https://pith.science/paper/APU72CPE"},"agent_actions":{"view_html":"https://pith.science/pith/APU72CPECVGAJALT6J4FZYHAEM","download_json":"https://pith.science/pith/APU72CPECVGAJALT6J4FZYHAEM.json","view_paper":"https://pith.science/paper/APU72CPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04861&json=true","fetch_graph":"https://pith.science/api/pith-number/APU72CPECVGAJALT6J4FZYHAEM/graph.json","fetch_events":"https://pith.science/api/pith-number/APU72CPECVGAJALT6J4FZYHAEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APU72CPECVGAJALT6J4FZYHAEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APU72CPECVGAJALT6J4FZYHAEM/action/storage_attestation","attest_author":"https://pith.science/pith/APU72CPECVGAJALT6J4FZYHAEM/action/author_attestation","sign_citation":"https://pith.science/pith/APU72CPECVGAJALT6J4FZYHAEM/action/citation_signature","submit_replication":"https://pith.science/pith/APU72CPECVGAJALT6J4FZYHAEM/action/replication_record"}},"created_at":"2026-07-05T09:59:59.401658+00:00","updated_at":"2026-07-05T09:59:59.401658+00:00"}