{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IUWWGIGSDAY7VWSYRGFIQLWHI7","short_pith_number":"pith:IUWWGIGS","schema_version":"1.0","canonical_sha256":"452d6320d21831fada58898a882ec747c7b8983289685667ac55ebc55307046f","source":{"kind":"arxiv","id":"2106.13200","version":2},"attestation_state":"computed","paper":{"title":"Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christopher J. Anders, David Neumann, Klaus-Robert M\\\"uller, Sebastian Lapuschkin, Wojciech Samek","submitted_at":"2021-06-24T17:27:22Z","abstract_excerpt":"Deep Neural Networks (DNNs) are known to be strong predictors, but their prediction strategies can rarely be understood. With recent advances in Explainable Artificial Intelligence (XAI), approaches are available to explore the reasoning behind those complex models' predictions. Among post-hoc attribution methods, Layer-wise Relevance Propagation (LRP) shows high performance. For deeper quantitative analysis, manual approaches exist, but without the right tools they are unnecessarily labor intensive. In this software paper, we introduce three software packages targeted at scientists to explore"},"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":"2106.13200","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-24T17:27:22Z","cross_cats_sorted":[],"title_canon_sha256":"3f4578953797f89835f8685bd9c3492837cea4cfaebb0fed58bdf5feeca0fffa","abstract_canon_sha256":"0d4d0518182a519fde855b6428a500a3ea3d84bab5af9e5fa53c6eeb2defea5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:10.718568Z","signature_b64":"N38yWlDUCUjuPL/t8ODaF65HaDp4bAEs0zsRZzmwIftoHLJBmJChVHRUjuICFjuHy7trpjl9iMHdzIxzgO8ECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"452d6320d21831fada58898a882ec747c7b8983289685667ac55ebc55307046f","last_reissued_at":"2026-07-05T05:46:10.718056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:10.718056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christopher J. Anders, David Neumann, Klaus-Robert M\\\"uller, Sebastian Lapuschkin, Wojciech Samek","submitted_at":"2021-06-24T17:27:22Z","abstract_excerpt":"Deep Neural Networks (DNNs) are known to be strong predictors, but their prediction strategies can rarely be understood. With recent advances in Explainable Artificial Intelligence (XAI), approaches are available to explore the reasoning behind those complex models' predictions. Among post-hoc attribution methods, Layer-wise Relevance Propagation (LRP) shows high performance. For deeper quantitative analysis, manual approaches exist, but without the right tools they are unnecessarily labor intensive. In this software paper, we introduce three software packages targeted at scientists to explore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13200","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/2106.13200/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":"2106.13200","created_at":"2026-07-05T05:46:10.718123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13200v2","created_at":"2026-07-05T05:46:10.718123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13200","created_at":"2026-07-05T05:46:10.718123+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUWWGIGSDAY7","created_at":"2026-07-05T05:46:10.718123+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUWWGIGSDAY7VWSY","created_at":"2026-07-05T05:46:10.718123+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUWWGIGS","created_at":"2026-07-05T05:46:10.718123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26361","citing_title":"Does Aurora Encode Atmospheric Structure? Latent Regime Analysis and Attribution","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11885","citing_title":"From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUWWGIGSDAY7VWSYRGFIQLWHI7","json":"https://pith.science/pith/IUWWGIGSDAY7VWSYRGFIQLWHI7.json","graph_json":"https://pith.science/api/pith-number/IUWWGIGSDAY7VWSYRGFIQLWHI7/graph.json","events_json":"https://pith.science/api/pith-number/IUWWGIGSDAY7VWSYRGFIQLWHI7/events.json","paper":"https://pith.science/paper/IUWWGIGS"},"agent_actions":{"view_html":"https://pith.science/pith/IUWWGIGSDAY7VWSYRGFIQLWHI7","download_json":"https://pith.science/pith/IUWWGIGSDAY7VWSYRGFIQLWHI7.json","view_paper":"https://pith.science/paper/IUWWGIGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13200&json=true","fetch_graph":"https://pith.science/api/pith-number/IUWWGIGSDAY7VWSYRGFIQLWHI7/graph.json","fetch_events":"https://pith.science/api/pith-number/IUWWGIGSDAY7VWSYRGFIQLWHI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUWWGIGSDAY7VWSYRGFIQLWHI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUWWGIGSDAY7VWSYRGFIQLWHI7/action/storage_attestation","attest_author":"https://pith.science/pith/IUWWGIGSDAY7VWSYRGFIQLWHI7/action/author_attestation","sign_citation":"https://pith.science/pith/IUWWGIGSDAY7VWSYRGFIQLWHI7/action/citation_signature","submit_replication":"https://pith.science/pith/IUWWGIGSDAY7VWSYRGFIQLWHI7/action/replication_record"}},"created_at":"2026-07-05T05:46:10.718123+00:00","updated_at":"2026-07-05T05:46:10.718123+00:00"}