{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LKNRHEFCUBEDWDQDKQLXQIK67M","short_pith_number":"pith:LKNRHEFC","canonical_record":{"source":{"id":"1807.05077","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-12T11:47:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"77789e1c312535cef0c2e238a58f6a58df172e5aff1d4c83240be3093849e0be","abstract_canon_sha256":"83fc5cd675a00379a32ad4509047c4d09a3b742de4234b0e69efafaa1d61c5a7"},"schema_version":"1.0"},"canonical_sha256":"5a9b1390a2a0483b0e03541778215efb24062af433969028ea8bfceae33293f3","source":{"kind":"arxiv","id":"1807.05077","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05077","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05077v2","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05077","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"pith_short_12","alias_value":"LKNRHEFCUBED","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LKNRHEFCUBEDWDQD","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LKNRHEFC","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LKNRHEFCUBEDWDQDKQLXQIK67M","target":"record","payload":{"canonical_record":{"source":{"id":"1807.05077","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-12T11:47:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"77789e1c312535cef0c2e238a58f6a58df172e5aff1d4c83240be3093849e0be","abstract_canon_sha256":"83fc5cd675a00379a32ad4509047c4d09a3b742de4234b0e69efafaa1d61c5a7"},"schema_version":"1.0"},"canonical_sha256":"5a9b1390a2a0483b0e03541778215efb24062af433969028ea8bfceae33293f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:44.124665Z","signature_b64":"wXF/9GU4t8E8EZbjFIBjjHBlYLIS1RCqDStT7IWoThqYfipJZc6vQQpAdUXlVNsMG8HhXIg1IIyOIYAuzbC3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a9b1390a2a0483b0e03541778215efb24062af433969028ea8bfceae33293f3","last_reissued_at":"2026-05-18T00:10:44.124088Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:44.124088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.05077","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:10:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wrTZaNuz9k68HFjGIP4ouBv1/rMGkIACWsas0iK55GiwWezsv9xatZiDLp2+ShF9sxWs2sEMbhf0BgNELHNDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:49:37.255807Z"},"content_sha256":"ac3677d61307aa68104c165c11e6bb9cab60f710543b1ab6813892774a3593b6","schema_version":"1.0","event_id":"sha256:ac3677d61307aa68104c165c11e6bb9cab60f710543b1ab6813892774a3593b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LKNRHEFCUBEDWDQDKQLXQIK67M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Maximizing Invariant Data Perturbation with Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kouichi Ikeno, Satoshi Hara","submitted_at":"2018-07-12T11:47:17Z","abstract_excerpt":"Feature attribution methods, or saliency maps, are one of the most popular approaches for explaining the decisions of complex machine learning models such as deep neural networks. In this study, we propose a stochastic optimization approach for the perturbation-based feature attribution method. While the original optimization problem of the perturbation-based feature attribution is difficult to solve because of the complex constraints, we propose to reformulate the problem as the maximization of a differentiable function, which can be solved using gradient-based algorithms. In particular, stoc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05077","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":""},"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":"2026-05-18T00:10:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AWkU3vo9jKfc6oKOx0fEEpHNn3uapatJ6KP9ZBWCEbgUSIAz/mTDmd/WSrn1u4UEHkN7iSNy1AliXDy1R7DlBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:49:37.256470Z"},"content_sha256":"f12b02cc7c0327b17bf02e8cc9e00bf76339d26f3c079f63c72ab9878add8e68","schema_version":"1.0","event_id":"sha256:f12b02cc7c0327b17bf02e8cc9e00bf76339d26f3c079f63c72ab9878add8e68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LKNRHEFCUBEDWDQDKQLXQIK67M/bundle.json","state_url":"https://pith.science/pith/LKNRHEFCUBEDWDQDKQLXQIK67M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LKNRHEFCUBEDWDQDKQLXQIK67M/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":"2026-06-07T16:49:37Z","links":{"resolver":"https://pith.science/pith/LKNRHEFCUBEDWDQDKQLXQIK67M","bundle":"https://pith.science/pith/LKNRHEFCUBEDWDQDKQLXQIK67M/bundle.json","state":"https://pith.science/pith/LKNRHEFCUBEDWDQDKQLXQIK67M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LKNRHEFCUBEDWDQDKQLXQIK67M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LKNRHEFCUBEDWDQDKQLXQIK67M","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":"83fc5cd675a00379a32ad4509047c4d09a3b742de4234b0e69efafaa1d61c5a7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-12T11:47:17Z","title_canon_sha256":"77789e1c312535cef0c2e238a58f6a58df172e5aff1d4c83240be3093849e0be"},"schema_version":"1.0","source":{"id":"1807.05077","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05077","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05077v2","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05077","created_at":"2026-05-18T00:10:44Z"},{"alias_kind":"pith_short_12","alias_value":"LKNRHEFCUBED","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LKNRHEFCUBEDWDQD","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LKNRHEFC","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:f12b02cc7c0327b17bf02e8cc9e00bf76339d26f3c079f63c72ab9878add8e68","target":"graph","created_at":"2026-05-18T00:10:44Z","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"},"paper":{"abstract_excerpt":"Feature attribution methods, or saliency maps, are one of the most popular approaches for explaining the decisions of complex machine learning models such as deep neural networks. In this study, we propose a stochastic optimization approach for the perturbation-based feature attribution method. While the original optimization problem of the perturbation-based feature attribution is difficult to solve because of the complex constraints, we propose to reformulate the problem as the maximization of a differentiable function, which can be solved using gradient-based algorithms. In particular, stoc","authors_text":"Kouichi Ikeno, Satoshi Hara","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-12T11:47:17Z","title":"Maximizing Invariant Data Perturbation with Stochastic Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05077","kind":"arxiv","version":2},"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:ac3677d61307aa68104c165c11e6bb9cab60f710543b1ab6813892774a3593b6","target":"record","created_at":"2026-05-18T00:10:44Z","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":"83fc5cd675a00379a32ad4509047c4d09a3b742de4234b0e69efafaa1d61c5a7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-12T11:47:17Z","title_canon_sha256":"77789e1c312535cef0c2e238a58f6a58df172e5aff1d4c83240be3093849e0be"},"schema_version":"1.0","source":{"id":"1807.05077","kind":"arxiv","version":2}},"canonical_sha256":"5a9b1390a2a0483b0e03541778215efb24062af433969028ea8bfceae33293f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a9b1390a2a0483b0e03541778215efb24062af433969028ea8bfceae33293f3","first_computed_at":"2026-05-18T00:10:44.124088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:44.124088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wXF/9GU4t8E8EZbjFIBjjHBlYLIS1RCqDStT7IWoThqYfipJZc6vQQpAdUXlVNsMG8HhXIg1IIyOIYAuzbC3BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:44.124665Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.05077","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac3677d61307aa68104c165c11e6bb9cab60f710543b1ab6813892774a3593b6","sha256:f12b02cc7c0327b17bf02e8cc9e00bf76339d26f3c079f63c72ab9878add8e68"],"state_sha256":"9567ed8b23908aee431063e12bc40fa8bf34fa12f5510c6f0806d2a2931f84e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ggoITAacWJsCPpkYpgQ5U4iOXM2O8LPL0Ymxgl5wKysgGH+UHXpuB+oJXaSrQkroH9kSbZbPmpiqXN/7qygIBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T16:49:37.260095Z","bundle_sha256":"cdd55b21240df8388f027388036503d6cf895a23fbd5a5c42dd30d2746846aa7"}}