{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NQMZAD64TUKKMETX55PFAPJ4I6","short_pith_number":"pith:NQMZAD64","schema_version":"1.0","canonical_sha256":"6c19900fdc9d14a61277ef5e503d3c47967fe7c2be1a5fcc68fd4bb45c17d77d","source":{"kind":"arxiv","id":"2505.21595","version":1},"attestation_state":"computed","paper":{"title":"Relevance-driven Input Dropout: an Explanation-guided Regularization Technique","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lars Gr\\\"une, Leander Weber, Sebastian Lapuschkin, Shreyas Gururaj, Wojciech Samek","submitted_at":"2025-05-27T16:52:29Z","abstract_excerpt":"Overfitting is a well-known issue extending even to state-of-the-art (SOTA) Machine Learning (ML) models, resulting in reduced generalization, and a significant train-test performance gap. Mitigation measures include a combination of dropout, data augmentation, weight decay, and other regularization techniques. Among the various data augmentation strategies, occlusion is a prominent technique that typically focuses on randomly masking regions of the input during training. Most of the existing literature emphasizes randomness in selecting and modifying the input features instead of regions that"},"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":"2505.21595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T16:52:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"604b39aee7d9dcebc6283eebf220adf92b349608b3d803b16719d2fac3eb3006","abstract_canon_sha256":"5e82caa49066cfb601ce47f4800122646b317ed52fe66314535896c4b92b517f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:00.687858Z","signature_b64":"e4/JaGyNwJej7avsQEZy/0Ln7Anop9K1EdoCpaYsbKpDMSQwTsSFmnp40y805X76BZyqnHsYLMFX5yMmK+uJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c19900fdc9d14a61277ef5e503d3c47967fe7c2be1a5fcc68fd4bb45c17d77d","last_reissued_at":"2026-07-05T11:11:00.687386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:00.687386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relevance-driven Input Dropout: an Explanation-guided Regularization Technique","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lars Gr\\\"une, Leander Weber, Sebastian Lapuschkin, Shreyas Gururaj, Wojciech Samek","submitted_at":"2025-05-27T16:52:29Z","abstract_excerpt":"Overfitting is a well-known issue extending even to state-of-the-art (SOTA) Machine Learning (ML) models, resulting in reduced generalization, and a significant train-test performance gap. Mitigation measures include a combination of dropout, data augmentation, weight decay, and other regularization techniques. Among the various data augmentation strategies, occlusion is a prominent technique that typically focuses on randomly masking regions of the input during training. Most of the existing literature emphasizes randomness in selecting and modifying the input features instead of regions that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21595","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/2505.21595/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":"2505.21595","created_at":"2026-07-05T11:11:00.687443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21595v1","created_at":"2026-07-05T11:11:00.687443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21595","created_at":"2026-07-05T11:11:00.687443+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQMZAD64TUKK","created_at":"2026-07-05T11:11:00.687443+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQMZAD64TUKKMETX","created_at":"2026-07-05T11:11:00.687443+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQMZAD64","created_at":"2026-07-05T11:11:00.687443+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/NQMZAD64TUKKMETX55PFAPJ4I6","json":"https://pith.science/pith/NQMZAD64TUKKMETX55PFAPJ4I6.json","graph_json":"https://pith.science/api/pith-number/NQMZAD64TUKKMETX55PFAPJ4I6/graph.json","events_json":"https://pith.science/api/pith-number/NQMZAD64TUKKMETX55PFAPJ4I6/events.json","paper":"https://pith.science/paper/NQMZAD64"},"agent_actions":{"view_html":"https://pith.science/pith/NQMZAD64TUKKMETX55PFAPJ4I6","download_json":"https://pith.science/pith/NQMZAD64TUKKMETX55PFAPJ4I6.json","view_paper":"https://pith.science/paper/NQMZAD64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21595&json=true","fetch_graph":"https://pith.science/api/pith-number/NQMZAD64TUKKMETX55PFAPJ4I6/graph.json","fetch_events":"https://pith.science/api/pith-number/NQMZAD64TUKKMETX55PFAPJ4I6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQMZAD64TUKKMETX55PFAPJ4I6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQMZAD64TUKKMETX55PFAPJ4I6/action/storage_attestation","attest_author":"https://pith.science/pith/NQMZAD64TUKKMETX55PFAPJ4I6/action/author_attestation","sign_citation":"https://pith.science/pith/NQMZAD64TUKKMETX55PFAPJ4I6/action/citation_signature","submit_replication":"https://pith.science/pith/NQMZAD64TUKKMETX55PFAPJ4I6/action/replication_record"}},"created_at":"2026-07-05T11:11:00.687443+00:00","updated_at":"2026-07-05T11:11:00.687443+00:00"}