{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PRTT37Y7OJZE3IQ2SDWTILDPLF","short_pith_number":"pith:PRTT37Y7","canonical_record":{"source":{"id":"2501.14322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T08:34:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed6c925ee6f4536a1ae263b21a3e509b7ff63279a0ef1f32a5ceb3e97910b575","abstract_canon_sha256":"eed8a32362e731dcba4c432d00514144d479cca0f26ebd178fda04bac52f3c1c"},"schema_version":"1.0"},"canonical_sha256":"7c673dff1f72724da21a90ed342c6f5947d4060dde0283c440d51b4f49c92765","source":{"kind":"arxiv","id":"2501.14322","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14322","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14322v1","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14322","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"PRTT37Y7OJZE","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"PRTT37Y7OJZE3IQ2","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"PRTT37Y7","created_at":"2026-07-05T10:04:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PRTT37Y7OJZE3IQ2SDWTILDPLF","target":"record","payload":{"canonical_record":{"source":{"id":"2501.14322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T08:34:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed6c925ee6f4536a1ae263b21a3e509b7ff63279a0ef1f32a5ceb3e97910b575","abstract_canon_sha256":"eed8a32362e731dcba4c432d00514144d479cca0f26ebd178fda04bac52f3c1c"},"schema_version":"1.0"},"canonical_sha256":"7c673dff1f72724da21a90ed342c6f5947d4060dde0283c440d51b4f49c92765","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:48.810393Z","signature_b64":"Mqm3UFuf6ehq4YB04prYQO39FE4g0DPYUQw28bmldI1jXG+Uo7mhG9Am0gjzOh0aQJIRwzKd91YKpq6m+1B2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c673dff1f72724da21a90ed342c6f5947d4060dde0283c440d51b4f49c92765","last_reissued_at":"2026-07-05T10:04:48.809844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:48.809844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.14322","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":"2026-07-05T10:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pq10/Fq0Gwqs5A0kguYrn0cevWK3I84/lFN8MMZqpJTp/NcRCCpRcDx0YWIKSDGubnpUrjrzqFuhDtNv+pKpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:29:51.648860Z"},"content_sha256":"56ccd8ceaefcc2cfefc1ffc3cbc5f3f72ee7b007757fffb4c8f9372511210a54","schema_version":"1.0","event_id":"sha256:56ccd8ceaefcc2cfefc1ffc3cbc5f3f72ee7b007757fffb4c8f9372511210a54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PRTT37Y7OJZE3IQ2SDWTILDPLF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Relative Layer-Wise Relevance Propagation: a more Robust Neural Networks eXplaination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eric Nyiri, Olivier Gibaru","submitted_at":"2025-01-24T08:34:22Z","abstract_excerpt":"Machine learning methods are solving very successfully a plethora of tasks, but they have the disadvantage of not providing any information about their decision. Consequently, estimating the reasoning of the system provides additional information. For this, Layer-Wise Relevance Propagation (LRP) is one of the methods in eXplainable Machine Learning (XML). Its purpose is to provide contributions of any neural network output in the domain of its input. The main drawback of current methods is mainly due to division by small values. To overcome this problem, we provide a new definition called Rela"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14322","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/2501.14322/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":"2026-07-05T10:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5C51TI1wmh6UhAe8bbBl8/AZ8kU+WSG43KDXnOO9svteu/O3wpnut4mBbvlsUURg0qjg0TsL8QbgP7RZPXDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:29:51.649366Z"},"content_sha256":"3042d2323c3c19a0b354a7ed8031da6243981d5639d80a23e4341094a9ef593b","schema_version":"1.0","event_id":"sha256:3042d2323c3c19a0b354a7ed8031da6243981d5639d80a23e4341094a9ef593b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PRTT37Y7OJZE3IQ2SDWTILDPLF/bundle.json","state_url":"https://pith.science/pith/PRTT37Y7OJZE3IQ2SDWTILDPLF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PRTT37Y7OJZE3IQ2SDWTILDPLF/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":"2026-08-13T16:29:51Z","links":{"resolver":"https://pith.science/pith/PRTT37Y7OJZE3IQ2SDWTILDPLF","bundle":"https://pith.science/pith/PRTT37Y7OJZE3IQ2SDWTILDPLF/bundle.json","state":"https://pith.science/pith/PRTT37Y7OJZE3IQ2SDWTILDPLF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PRTT37Y7OJZE3IQ2SDWTILDPLF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PRTT37Y7OJZE3IQ2SDWTILDPLF","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":"eed8a32362e731dcba4c432d00514144d479cca0f26ebd178fda04bac52f3c1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T08:34:22Z","title_canon_sha256":"ed6c925ee6f4536a1ae263b21a3e509b7ff63279a0ef1f32a5ceb3e97910b575"},"schema_version":"1.0","source":{"id":"2501.14322","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14322","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14322v1","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14322","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"PRTT37Y7OJZE","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"PRTT37Y7OJZE3IQ2","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"PRTT37Y7","created_at":"2026-07-05T10:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:3042d2323c3c19a0b354a7ed8031da6243981d5639d80a23e4341094a9ef593b","target":"graph","created_at":"2026-07-05T10:04:48Z","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/2501.14322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning methods are solving very successfully a plethora of tasks, but they have the disadvantage of not providing any information about their decision. Consequently, estimating the reasoning of the system provides additional information. For this, Layer-Wise Relevance Propagation (LRP) is one of the methods in eXplainable Machine Learning (XML). Its purpose is to provide contributions of any neural network output in the domain of its input. The main drawback of current methods is mainly due to division by small values. To overcome this problem, we provide a new definition called Rela","authors_text":"Eric Nyiri, Olivier Gibaru","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T08:34:22Z","title":"Relative Layer-Wise Relevance Propagation: a more Robust Neural Networks eXplaination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14322","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":"sha256:56ccd8ceaefcc2cfefc1ffc3cbc5f3f72ee7b007757fffb4c8f9372511210a54","target":"record","created_at":"2026-07-05T10:04:48Z","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":"eed8a32362e731dcba4c432d00514144d479cca0f26ebd178fda04bac52f3c1c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T08:34:22Z","title_canon_sha256":"ed6c925ee6f4536a1ae263b21a3e509b7ff63279a0ef1f32a5ceb3e97910b575"},"schema_version":"1.0","source":{"id":"2501.14322","kind":"arxiv","version":1}},"canonical_sha256":"7c673dff1f72724da21a90ed342c6f5947d4060dde0283c440d51b4f49c92765","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c673dff1f72724da21a90ed342c6f5947d4060dde0283c440d51b4f49c92765","first_computed_at":"2026-07-05T10:04:48.809844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:48.809844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mqm3UFuf6ehq4YB04prYQO39FE4g0DPYUQw28bmldI1jXG+Uo7mhG9Am0gjzOh0aQJIRwzKd91YKpq6m+1B2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:48.810393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14322","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56ccd8ceaefcc2cfefc1ffc3cbc5f3f72ee7b007757fffb4c8f9372511210a54","sha256:3042d2323c3c19a0b354a7ed8031da6243981d5639d80a23e4341094a9ef593b"],"state_sha256":"3301c154304723a58af3e6147f81d719c9c2a8fe1e6e173ed799671a4712f889"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ncD8OL1EsSruMcZyWEV2EWfyhoWL5nnGhzo6sizig4BUIN4sBmiw1PCUlZGXCznQ0X27QuI/Eq/zZXgjIO+QCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T16:29:51.662334Z","bundle_sha256":"dce79ffbf82a8d83826cb4a8db16ec8a84e9eeb442c6f2c4f7440ad1c5f1cdc5"}}