{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Z575MVVPU5FZU7CT5IUZOEK2LE","short_pith_number":"pith:Z575MVVP","canonical_record":{"source":{"id":"1811.10799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-27T04:26:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2aaab3d01d35bd6cd80939a74461f05d4e411ae4dfb91b63137dd696b766b9f","abstract_canon_sha256":"19223a0d4d3f7f79fe74cdb4fdf58acec7955c981dbab706d567ff7c6e19748a"},"schema_version":"1.0"},"canonical_sha256":"cf7fd656afa74b9a7c53ea2997115a5924cf1649edd06639f49ce60dd08eb0e4","source":{"kind":"arxiv","id":"1811.10799","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10799","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10799v2","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10799","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"pith_short_12","alias_value":"Z575MVVPU5FZ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z575MVVPU5FZU7CT","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z575MVVP","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Z575MVVPU5FZU7CT5IUZOEK2LE","target":"record","payload":{"canonical_record":{"source":{"id":"1811.10799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-27T04:26:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2aaab3d01d35bd6cd80939a74461f05d4e411ae4dfb91b63137dd696b766b9f","abstract_canon_sha256":"19223a0d4d3f7f79fe74cdb4fdf58acec7955c981dbab706d567ff7c6e19748a"},"schema_version":"1.0"},"canonical_sha256":"cf7fd656afa74b9a7c53ea2997115a5924cf1649edd06639f49ce60dd08eb0e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:33.009282Z","signature_b64":"ErN7BHV+wOROcJomENqDZ5lVGSJf0b26l0FfExFy2yDMC7If79dVRRXA8QTj2V0POTEwWuPN+izoQWvb3PX3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf7fd656afa74b9a7c53ea2997115a5924cf1649edd06639f49ce60dd08eb0e4","last_reissued_at":"2026-05-17T23:43:33.008822Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:33.008822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.10799","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":"2026-05-17T23:43:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yGRY/J+cnTnDN63K618HdAQaCXKrx3aY9VrCqTOGex2OMeHL8GXi08i4lpVqKwcVLjqsFAUJ6pRLOoUCsJAYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:03:24.325813Z"},"content_sha256":"f1f002cfd7b59bfe448ef262ec661c20e5a79985c056a836a8e6712220b4009c","schema_version":"1.0","event_id":"sha256:f1f002cfd7b59bfe448ef262ec661c20e5a79985c056a836a8e6712220b4009c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Z575MVVPU5FZU7CT5IUZOEK2LE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What is Interpretable? Using Machine Learning to Design Interpretable Decision-Support Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mihaela van der Schaar, Nicholas Mastronarde, Owen Lahav","submitted_at":"2018-11-27T04:26:36Z","abstract_excerpt":"Recent efforts in Machine Learning (ML) interpretability have focused on creating methods for explaining black-box ML models. However, these methods rely on the assumption that simple approximations, such as linear models or decision-trees, are inherently human-interpretable, which has not been empirically tested. Additionally, past efforts have focused exclusively on comprehension, neglecting to explore the trust component necessary to convince non-technical experts, such as clinicians, to utilize ML models in practice. In this paper, we posit that reinforcement learning (RL) can be used to l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10799","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":"2026-05-17T23:43:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J14taF+5QZp4YJpWdwyb2fcgD9pE8iVtMfiR6IvBmw6uXT+AYvc7EzMmRYj2FxNCHhA6WBKFhmuuJJyjLM7CBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:03:24.326157Z"},"content_sha256":"92b09beca588421e5e3a652f08aa07fdfc41594cc737084f7e2a437aede269cb","schema_version":"1.0","event_id":"sha256:92b09beca588421e5e3a652f08aa07fdfc41594cc737084f7e2a437aede269cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z575MVVPU5FZU7CT5IUZOEK2LE/bundle.json","state_url":"https://pith.science/pith/Z575MVVPU5FZU7CT5IUZOEK2LE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z575MVVPU5FZU7CT5IUZOEK2LE/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":"2026-05-28T15:03:24Z","links":{"resolver":"https://pith.science/pith/Z575MVVPU5FZU7CT5IUZOEK2LE","bundle":"https://pith.science/pith/Z575MVVPU5FZU7CT5IUZOEK2LE/bundle.json","state":"https://pith.science/pith/Z575MVVPU5FZU7CT5IUZOEK2LE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z575MVVPU5FZU7CT5IUZOEK2LE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Z575MVVPU5FZU7CT5IUZOEK2LE","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":"19223a0d4d3f7f79fe74cdb4fdf58acec7955c981dbab706d567ff7c6e19748a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-27T04:26:36Z","title_canon_sha256":"e2aaab3d01d35bd6cd80939a74461f05d4e411ae4dfb91b63137dd696b766b9f"},"schema_version":"1.0","source":{"id":"1811.10799","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10799","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10799v2","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10799","created_at":"2026-05-17T23:43:33Z"},{"alias_kind":"pith_short_12","alias_value":"Z575MVVPU5FZ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z575MVVPU5FZU7CT","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z575MVVP","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:92b09beca588421e5e3a652f08aa07fdfc41594cc737084f7e2a437aede269cb","target":"graph","created_at":"2026-05-17T23:43:33Z","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":"Recent efforts in Machine Learning (ML) interpretability have focused on creating methods for explaining black-box ML models. However, these methods rely on the assumption that simple approximations, such as linear models or decision-trees, are inherently human-interpretable, which has not been empirically tested. Additionally, past efforts have focused exclusively on comprehension, neglecting to explore the trust component necessary to convince non-technical experts, such as clinicians, to utilize ML models in practice. In this paper, we posit that reinforcement learning (RL) can be used to l","authors_text":"Mihaela van der Schaar, Nicholas Mastronarde, Owen Lahav","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-27T04:26:36Z","title":"What is Interpretable? Using Machine Learning to Design Interpretable Decision-Support Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10799","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:f1f002cfd7b59bfe448ef262ec661c20e5a79985c056a836a8e6712220b4009c","target":"record","created_at":"2026-05-17T23:43:33Z","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":"19223a0d4d3f7f79fe74cdb4fdf58acec7955c981dbab706d567ff7c6e19748a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-27T04:26:36Z","title_canon_sha256":"e2aaab3d01d35bd6cd80939a74461f05d4e411ae4dfb91b63137dd696b766b9f"},"schema_version":"1.0","source":{"id":"1811.10799","kind":"arxiv","version":2}},"canonical_sha256":"cf7fd656afa74b9a7c53ea2997115a5924cf1649edd06639f49ce60dd08eb0e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf7fd656afa74b9a7c53ea2997115a5924cf1649edd06639f49ce60dd08eb0e4","first_computed_at":"2026-05-17T23:43:33.008822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:33.008822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ErN7BHV+wOROcJomENqDZ5lVGSJf0b26l0FfExFy2yDMC7If79dVRRXA8QTj2V0POTEwWuPN+izoQWvb3PX3AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:33.009282Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.10799","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1f002cfd7b59bfe448ef262ec661c20e5a79985c056a836a8e6712220b4009c","sha256:92b09beca588421e5e3a652f08aa07fdfc41594cc737084f7e2a437aede269cb"],"state_sha256":"89c8b279ea04f626cddbda35f903d74c92901ae1967d618539c97b6ebf09cadc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kv5/VZb5SaFmpuUf03bJs6yFdaG/8VcDb4sA11DPbDvz3PKTZOzwGHrg8CPJWQuMlv+1lJP6+EnVpc5fBVVXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T15:03:24.328228Z","bundle_sha256":"7f83d25323b81dff65847616247719408214d1a017ebab1d00e77aa013ccab35"}}