{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HH6ICZ4N4LHU2U2QO2BPQGZ54K","short_pith_number":"pith:HH6ICZ4N","canonical_record":{"source":{"id":"1903.10464","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-25T16:57:11Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"3249d2c919d273a500bc4b0688380d21dc5d5eaae3179144f8c490356d9a93c9","abstract_canon_sha256":"d17fe9e2d603a049d16c9d2905f6b967d5c7f8c1f275feedb188f22137c68cc6"},"schema_version":"1.0"},"canonical_sha256":"39fc81678de2cf4d53507682f81b3de280dc85a7cdb87a23d8abce86ebf9931c","source":{"kind":"arxiv","id":"1903.10464","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10464","created_at":"2026-07-05T00:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10464v3","created_at":"2026-07-05T00:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10464","created_at":"2026-07-05T00:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"HH6ICZ4N4LHU","created_at":"2026-07-05T00:38:44Z"},{"alias_kind":"pith_short_16","alias_value":"HH6ICZ4N4LHU2U2Q","created_at":"2026-07-05T00:38:44Z"},{"alias_kind":"pith_short_8","alias_value":"HH6ICZ4N","created_at":"2026-07-05T00:38:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HH6ICZ4N4LHU2U2QO2BPQGZ54K","target":"record","payload":{"canonical_record":{"source":{"id":"1903.10464","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-25T16:57:11Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"3249d2c919d273a500bc4b0688380d21dc5d5eaae3179144f8c490356d9a93c9","abstract_canon_sha256":"d17fe9e2d603a049d16c9d2905f6b967d5c7f8c1f275feedb188f22137c68cc6"},"schema_version":"1.0"},"canonical_sha256":"39fc81678de2cf4d53507682f81b3de280dc85a7cdb87a23d8abce86ebf9931c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:38:44.846430Z","signature_b64":"P6HTQ2oiEGnBaPVt1Gu9Wqv0LlJzaCt2tRMwwjhsyb4TRSZxHsEkt3Kk6BC7ZwJQYJFfbvxrdoHxYZEKYcbQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39fc81678de2cf4d53507682f81b3de280dc85a7cdb87a23d8abce86ebf9931c","last_reissued_at":"2026-07-05T00:38:44.845924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:38:44.845924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.10464","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:38:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VYm0YrvD+uj6kbbr76iMJaFyEngTIiehWGblEPMW3KLNtk6KP5kSBQsBM+LjrThPw2NqifJd2ulNwt8oCd1FAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:04:49.264634Z"},"content_sha256":"7bc0e943d6fa9b1c599ab0ee04dae05be1ac9417999cc4b28be7d204f13a6652","schema_version":"1.0","event_id":"sha256:7bc0e943d6fa9b1c599ab0ee04dae05be1ac9417999cc4b28be7d204f13a6652"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HH6ICZ4N4LHU2U2QO2BPQGZ54K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explaining individual predictions when features are dependent: More accurate approximations to Shapley values","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Anders L{\\o}land, Kjersti Aas, Martin Jullum","submitted_at":"2019-03-25T16:57:11Z","abstract_excerpt":"Explaining complex or seemingly simple machine learning models is an important practical problem. We want to explain individual predictions from a complex machine learning model by learning simple, interpretable explanations. Shapley values is a game theoretic concept that can be used for this purpose. The Shapley value framework has a series of desirable theoretical properties, and can in principle handle any predictive model. Kernel SHAP is a computationally efficient approximation to Shapley values in higher dimensions. Like several other existing methods, this approach assumes that the fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10464","kind":"arxiv","version":3},"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/1903.10464/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":"2026-07-05T00:38:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5QEIGt3gUCDIBSR0ZRhYoh3TG0iQkJ30/TkugATIHIFudoKhU6mehER8BDwktZKJQlGAjwetMdH1VF0DoQuQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:04:49.265148Z"},"content_sha256":"93f8d5873bff5f821bcd42134affe4a493bbc69d1b61631a615574a468bb0adc","schema_version":"1.0","event_id":"sha256:93f8d5873bff5f821bcd42134affe4a493bbc69d1b61631a615574a468bb0adc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HH6ICZ4N4LHU2U2QO2BPQGZ54K/bundle.json","state_url":"https://pith.science/pith/HH6ICZ4N4LHU2U2QO2BPQGZ54K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HH6ICZ4N4LHU2U2QO2BPQGZ54K/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":"2026-08-08T09:04:49Z","links":{"resolver":"https://pith.science/pith/HH6ICZ4N4LHU2U2QO2BPQGZ54K","bundle":"https://pith.science/pith/HH6ICZ4N4LHU2U2QO2BPQGZ54K/bundle.json","state":"https://pith.science/pith/HH6ICZ4N4LHU2U2QO2BPQGZ54K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HH6ICZ4N4LHU2U2QO2BPQGZ54K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HH6ICZ4N4LHU2U2QO2BPQGZ54K","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":"d17fe9e2d603a049d16c9d2905f6b967d5c7f8c1f275feedb188f22137c68cc6","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-25T16:57:11Z","title_canon_sha256":"3249d2c919d273a500bc4b0688380d21dc5d5eaae3179144f8c490356d9a93c9"},"schema_version":"1.0","source":{"id":"1903.10464","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10464","created_at":"2026-07-05T00:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10464v3","created_at":"2026-07-05T00:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10464","created_at":"2026-07-05T00:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"HH6ICZ4N4LHU","created_at":"2026-07-05T00:38:44Z"},{"alias_kind":"pith_short_16","alias_value":"HH6ICZ4N4LHU2U2Q","created_at":"2026-07-05T00:38:44Z"},{"alias_kind":"pith_short_8","alias_value":"HH6ICZ4N","created_at":"2026-07-05T00:38:44Z"}],"graph_snapshots":[{"event_id":"sha256:93f8d5873bff5f821bcd42134affe4a493bbc69d1b61631a615574a468bb0adc","target":"graph","created_at":"2026-07-05T00:38:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1903.10464/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Explaining complex or seemingly simple machine learning models is an important practical problem. We want to explain individual predictions from a complex machine learning model by learning simple, interpretable explanations. Shapley values is a game theoretic concept that can be used for this purpose. The Shapley value framework has a series of desirable theoretical properties, and can in principle handle any predictive model. Kernel SHAP is a computationally efficient approximation to Shapley values in higher dimensions. Like several other existing methods, this approach assumes that the fea","authors_text":"Anders L{\\o}land, Kjersti Aas, Martin Jullum","cross_cats":["cs.LG","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-25T16:57:11Z","title":"Explaining individual predictions when features are dependent: More accurate approximations to Shapley values"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10464","kind":"arxiv","version":3},"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":"sha256:7bc0e943d6fa9b1c599ab0ee04dae05be1ac9417999cc4b28be7d204f13a6652","target":"record","created_at":"2026-07-05T00:38:44Z","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":"d17fe9e2d603a049d16c9d2905f6b967d5c7f8c1f275feedb188f22137c68cc6","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-03-25T16:57:11Z","title_canon_sha256":"3249d2c919d273a500bc4b0688380d21dc5d5eaae3179144f8c490356d9a93c9"},"schema_version":"1.0","source":{"id":"1903.10464","kind":"arxiv","version":3}},"canonical_sha256":"39fc81678de2cf4d53507682f81b3de280dc85a7cdb87a23d8abce86ebf9931c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39fc81678de2cf4d53507682f81b3de280dc85a7cdb87a23d8abce86ebf9931c","first_computed_at":"2026-07-05T00:38:44.845924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:38:44.845924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P6HTQ2oiEGnBaPVt1Gu9Wqv0LlJzaCt2tRMwwjhsyb4TRSZxHsEkt3Kk6BC7ZwJQYJFfbvxrdoHxYZEKYcbQBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:38:44.846430Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.10464","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bc0e943d6fa9b1c599ab0ee04dae05be1ac9417999cc4b28be7d204f13a6652","sha256:93f8d5873bff5f821bcd42134affe4a493bbc69d1b61631a615574a468bb0adc"],"state_sha256":"b8e0f373ce99e8a6c3d490c635349f4422e6faf1d757a48d9ebf30424956e636"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lLa7YETCfstb7bSHTJNNpi52fM5p8hwUkOeIgz+acs4P52l/eKgVXaJ62z3x/2gMUgyzl0ztYClG7lWg/zNvCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:04:49.270156Z","bundle_sha256":"5ea81a38fee1b9934db0166bfe0155aad3037935da27943d0d4f6d64a77945f6"}}