{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ORYOHWOG7QDTL6PLWQR35E2HWP","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":"b031d9864ab1c85f5273a4cd3d225a1beaf59381435ca9a4b131fc7e3ae2ede1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T17:09:34Z","title_canon_sha256":"aeb539886dd3c8561f1535e495a6bb9473ab30c34497c0d1df60b2038fdb815e"},"schema_version":"1.0","source":{"id":"1906.10670","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10670","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10670v2","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10670","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"ORYOHWOG7QDT","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"ORYOHWOG7QDTL6PL","created_at":"2026-07-05T01:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"ORYOHWOG","created_at":"2026-07-05T01:50:46Z"}],"graph_snapshots":[{"event_id":"sha256:7ae396adf76ae0415cb4c49f50e20500f7a9ad74d11fb5b5aa598a83df578c29","target":"graph","created_at":"2026-07-05T01:50:46Z","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/1906.10670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whose attributions have certain desirable properties -- most frequently, that particular features are important or unimportant. These attribution priors are often based on attribution methods that are not guaranteed to satisfy desirable interpretability axioms, such as completeness and implementation invariance. Here, we introduce attribution priors to optimize for higher-level properties of explanations, such as smoothn","authors_text":"Gabriel Erion, Joseph D. Janizek, Pascal Sturmfels, Scott Lundberg, Su-In Lee","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T17:09:34Z","title":"Improving performance of deep learning models with axiomatic attribution priors and expected gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10670","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":"sha256:395aa853df4d211dc5b4093e5bea527183254ecd6b483dc13e8c42bedaac86b5","target":"record","created_at":"2026-07-05T01:50:46Z","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":"b031d9864ab1c85f5273a4cd3d225a1beaf59381435ca9a4b131fc7e3ae2ede1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T17:09:34Z","title_canon_sha256":"aeb539886dd3c8561f1535e495a6bb9473ab30c34497c0d1df60b2038fdb815e"},"schema_version":"1.0","source":{"id":"1906.10670","kind":"arxiv","version":2}},"canonical_sha256":"7470e3d9c6fc0735f9ebb423be9347b3fdeeb2257d5f7e23f17972be480f611b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7470e3d9c6fc0735f9ebb423be9347b3fdeeb2257d5f7e23f17972be480f611b","first_computed_at":"2026-07-05T01:50:46.209760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:50:46.209760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RIlhECIvR4B/YWNjB02qNS7KWAdWMCTwNZDCvzethFP2P72nFIkjiyTMK0NYSXNNRSin3OOhob2VbLJriE9bCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:50:46.210277Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.10670","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:395aa853df4d211dc5b4093e5bea527183254ecd6b483dc13e8c42bedaac86b5","sha256:7ae396adf76ae0415cb4c49f50e20500f7a9ad74d11fb5b5aa598a83df578c29"],"state_sha256":"3a0a15d125c2493929b427809d8038c53f2d3160a2c80b74131e30976641374f"}