{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EU7SZNP2BYXISZIZ3CRMU7XBLH","short_pith_number":"pith:EU7SZNP2","canonical_record":{"source":{"id":"1810.00869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T17:43:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"201e66de5a42a9cdf4eeccb0ce349260b18f36de8a8c3da4aabef39d47833844","abstract_canon_sha256":"d5da69f7e2dd1be8ac6fa794a52e08b52532e133a1c9ba04b9af5c1a5954f578"},"schema_version":"1.0"},"canonical_sha256":"253f2cb5fa0e2e896519d8a2ca7ee159f964758d2c21b1b265364a294a5ba2cf","source":{"kind":"arxiv","id":"1810.00869","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00869","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00869v1","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00869","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"EU7SZNP2BYXI","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EU7SZNP2BYXISZIZ","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EU7SZNP2","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EU7SZNP2BYXISZIZ3CRMU7XBLH","target":"record","payload":{"canonical_record":{"source":{"id":"1810.00869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T17:43:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"201e66de5a42a9cdf4eeccb0ce349260b18f36de8a8c3da4aabef39d47833844","abstract_canon_sha256":"d5da69f7e2dd1be8ac6fa794a52e08b52532e133a1c9ba04b9af5c1a5954f578"},"schema_version":"1.0"},"canonical_sha256":"253f2cb5fa0e2e896519d8a2ca7ee159f964758d2c21b1b265364a294a5ba2cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:19.742650Z","signature_b64":"wCZWWO4jPBx+OxxDQwgVa0e9+DbGRPVuTXRjroGSWdZjlPZ9nhtIWJD93FjL93lo0+jpHg4hvKuD2MDKp5SiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"253f2cb5fa0e2e896519d8a2ca7ee159f964758d2c21b1b265364a294a5ba2cf","last_reissued_at":"2026-05-18T00:04:19.742006Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:19.742006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.00869","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":"2026-05-18T00:04:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M8Kj8viqCGl7LsWGvA0CmtHYzrmLYEELv3qybBm+svmP8Fhg669PHehcK577VaiZ3TdtLjHglZWsMEI4ewWcDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T21:52:03.377289Z"},"content_sha256":"58e8ddcb5ef1ea49cffff4837e27120364fd3b66eb6c3135c02953c13fb9adb6","schema_version":"1.0","event_id":"sha256:58e8ddcb5ef1ea49cffff4837e27120364fd3b66eb6c3135c02953c13fb9adb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EU7SZNP2BYXISZIZ3CRMU7XBLH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Machine Learning Models by Regularizing their Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Slavin Ross","submitted_at":"2018-09-29T17:43:21Z","abstract_excerpt":"Neural networks are among the most accurate supervised learning methods in use today. However, their opacity makes them difficult to trust in critical applications, especially when conditions in training may differ from those in practice. Recent efforts to develop explanations for neural networks and machine learning models more generally have produced tools to shed light on the implicit rules behind predictions. These tools can help us identify when models are right for the wrong reasons. However, they do not always scale to explaining predictions for entire datasets, are not always at the ri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00869","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":""},"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":"2026-05-18T00:04:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E/EgBBc2SmxegZ79d6Rd2s1sFXeI4HDSlUEMjejdDwjrG4aRItCRzvX4OS0G0EXNhiDIHjhCfHimiABkfX3GAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T21:52:03.377655Z"},"content_sha256":"1db1311830fdea6d97bfe8712af98bb17ed95c43dfb87b15498f69aeade77e0a","schema_version":"1.0","event_id":"sha256:1db1311830fdea6d97bfe8712af98bb17ed95c43dfb87b15498f69aeade77e0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EU7SZNP2BYXISZIZ3CRMU7XBLH/bundle.json","state_url":"https://pith.science/pith/EU7SZNP2BYXISZIZ3CRMU7XBLH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EU7SZNP2BYXISZIZ3CRMU7XBLH/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":"2026-06-08T21:52:03Z","links":{"resolver":"https://pith.science/pith/EU7SZNP2BYXISZIZ3CRMU7XBLH","bundle":"https://pith.science/pith/EU7SZNP2BYXISZIZ3CRMU7XBLH/bundle.json","state":"https://pith.science/pith/EU7SZNP2BYXISZIZ3CRMU7XBLH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EU7SZNP2BYXISZIZ3CRMU7XBLH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EU7SZNP2BYXISZIZ3CRMU7XBLH","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":"d5da69f7e2dd1be8ac6fa794a52e08b52532e133a1c9ba04b9af5c1a5954f578","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T17:43:21Z","title_canon_sha256":"201e66de5a42a9cdf4eeccb0ce349260b18f36de8a8c3da4aabef39d47833844"},"schema_version":"1.0","source":{"id":"1810.00869","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00869","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00869v1","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00869","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"EU7SZNP2BYXI","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EU7SZNP2BYXISZIZ","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EU7SZNP2","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:1db1311830fdea6d97bfe8712af98bb17ed95c43dfb87b15498f69aeade77e0a","target":"graph","created_at":"2026-05-18T00:04:19Z","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":"Neural networks are among the most accurate supervised learning methods in use today. However, their opacity makes them difficult to trust in critical applications, especially when conditions in training may differ from those in practice. Recent efforts to develop explanations for neural networks and machine learning models more generally have produced tools to shed light on the implicit rules behind predictions. These tools can help us identify when models are right for the wrong reasons. However, they do not always scale to explaining predictions for entire datasets, are not always at the ri","authors_text":"Andrew Slavin Ross","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T17:43:21Z","title":"Training Machine Learning Models by Regularizing their Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00869","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":"sha256:58e8ddcb5ef1ea49cffff4837e27120364fd3b66eb6c3135c02953c13fb9adb6","target":"record","created_at":"2026-05-18T00:04:19Z","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":"d5da69f7e2dd1be8ac6fa794a52e08b52532e133a1c9ba04b9af5c1a5954f578","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-29T17:43:21Z","title_canon_sha256":"201e66de5a42a9cdf4eeccb0ce349260b18f36de8a8c3da4aabef39d47833844"},"schema_version":"1.0","source":{"id":"1810.00869","kind":"arxiv","version":1}},"canonical_sha256":"253f2cb5fa0e2e896519d8a2ca7ee159f964758d2c21b1b265364a294a5ba2cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"253f2cb5fa0e2e896519d8a2ca7ee159f964758d2c21b1b265364a294a5ba2cf","first_computed_at":"2026-05-18T00:04:19.742006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:19.742006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wCZWWO4jPBx+OxxDQwgVa0e9+DbGRPVuTXRjroGSWdZjlPZ9nhtIWJD93FjL93lo0+jpHg4hvKuD2MDKp5SiAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:19.742650Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00869","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58e8ddcb5ef1ea49cffff4837e27120364fd3b66eb6c3135c02953c13fb9adb6","sha256:1db1311830fdea6d97bfe8712af98bb17ed95c43dfb87b15498f69aeade77e0a"],"state_sha256":"445d6aeeb9620c259493081b3186dc97c4821c9358cec8f7983bd1760280fe7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hW2N4lV/vYFjredCsh3z9AqyMFG0jzbJXFSiSVXlXjlMDGYnAGc6/ur9Fl34SgTyB8tyiGHgwKrnyHCtdVivDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T21:52:03.379556Z","bundle_sha256":"1c3ee313e2079eab78f20cc87239aa18092f4c706be0858345edaaf55acbdc02"}}