{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GF47O3DAPQOFRRWQCTDJZKP4ER","short_pith_number":"pith:GF47O3DA","canonical_record":{"source":{"id":"1901.08576","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T18:48:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7155aa2613303a1493bd5574b56144b376d1da3484a907daaef7bafb9ae69cc5","abstract_canon_sha256":"0448b29cff851138c693beac803af5b6f5cadef129ec3a93be9bb0aeac3e6bb0"},"schema_version":"1.0"},"canonical_sha256":"3179f76c607c1c58c6d014c69ca9fc246a507d675c895b107848840064569f59","source":{"kind":"arxiv","id":"1901.08576","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08576","created_at":"2026-07-05T03:21:32Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08576v2","created_at":"2026-07-05T03:21:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08576","created_at":"2026-07-05T03:21:32Z"},{"alias_kind":"pith_short_12","alias_value":"GF47O3DAPQOF","created_at":"2026-07-05T03:21:32Z"},{"alias_kind":"pith_short_16","alias_value":"GF47O3DAPQOFRRWQ","created_at":"2026-07-05T03:21:32Z"},{"alias_kind":"pith_short_8","alias_value":"GF47O3DA","created_at":"2026-07-05T03:21:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GF47O3DAPQOFRRWQCTDJZKP4ER","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08576","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T18:48:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7155aa2613303a1493bd5574b56144b376d1da3484a907daaef7bafb9ae69cc5","abstract_canon_sha256":"0448b29cff851138c693beac803af5b6f5cadef129ec3a93be9bb0aeac3e6bb0"},"schema_version":"1.0"},"canonical_sha256":"3179f76c607c1c58c6d014c69ca9fc246a507d675c895b107848840064569f59","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:32.084572Z","signature_b64":"I0UyPUEGueE1eqmwITK3BFHGBaolf7ysJi9U/Q9mQ59vUQMKqGioHSHOlm60GtmpyDeQuPQcOlotwhy8tsvyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3179f76c607c1c58c6d014c69ca9fc246a507d675c895b107848840064569f59","last_reissued_at":"2026-07-05T03:21:32.084166Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:32.084166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08576","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":"2026-07-05T03:21:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7E2Wyh0GNmeH3KL8Srnat/a6VEzVbR3f0XhtWsca0QQfjEUIxSJOG0c9M/n6bOl8liO95V4yIZhP/QPAk6MUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:24:25.011540Z"},"content_sha256":"16a31fe1149309d7a78e26bea17001b4e826bec9c74193d26fe9ec35ee4b324f","schema_version":"1.0","event_id":"sha256:16a31fe1149309d7a78e26bea17001b4e826bec9c74193d26fe9ec35ee4b324f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GF47O3DAPQOFRRWQCTDJZKP4ER","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Interpretable Models with Causal Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carolyn Kim, Osbert Bastani","submitted_at":"2019-01-24T18:48:40Z","abstract_excerpt":"Machine learning has shown much promise in helping improve the quality of medical, legal, and financial decision-making. In these applications, machine learning models must satisfy two important criteria: (i) they must be causal, since the goal is typically to predict individual treatment effects, and (ii) they must be interpretable, so that human decision makers can validate and trust the model predictions. There has recently been much progress along each direction independently, yet the state-of-the-art approaches are fundamentally incompatible. We propose a framework for learning interpreta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08576","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1901.08576/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":"2026-07-05T03:21:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mxPOCvrX5f5y/FLdDEmkz4ggkoirvsn3HGsk7GQ1Rj8i35x/+cyYRVESlMCq5g9og62m72HTkrfk8TCYgwH5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:24:25.012279Z"},"content_sha256":"7778eb3762c85c89557baeffbbd3c873adc21f98cbf5ad49b60f802b82062ff4","schema_version":"1.0","event_id":"sha256:7778eb3762c85c89557baeffbbd3c873adc21f98cbf5ad49b60f802b82062ff4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GF47O3DAPQOFRRWQCTDJZKP4ER/bundle.json","state_url":"https://pith.science/pith/GF47O3DAPQOFRRWQCTDJZKP4ER/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GF47O3DAPQOFRRWQCTDJZKP4ER/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":"2026-08-05T17:24:25Z","links":{"resolver":"https://pith.science/pith/GF47O3DAPQOFRRWQCTDJZKP4ER","bundle":"https://pith.science/pith/GF47O3DAPQOFRRWQCTDJZKP4ER/bundle.json","state":"https://pith.science/pith/GF47O3DAPQOFRRWQCTDJZKP4ER/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GF47O3DAPQOFRRWQCTDJZKP4ER/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GF47O3DAPQOFRRWQCTDJZKP4ER","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":"0448b29cff851138c693beac803af5b6f5cadef129ec3a93be9bb0aeac3e6bb0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T18:48:40Z","title_canon_sha256":"7155aa2613303a1493bd5574b56144b376d1da3484a907daaef7bafb9ae69cc5"},"schema_version":"1.0","source":{"id":"1901.08576","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08576","created_at":"2026-07-05T03:21:32Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08576v2","created_at":"2026-07-05T03:21:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08576","created_at":"2026-07-05T03:21:32Z"},{"alias_kind":"pith_short_12","alias_value":"GF47O3DAPQOF","created_at":"2026-07-05T03:21:32Z"},{"alias_kind":"pith_short_16","alias_value":"GF47O3DAPQOFRRWQ","created_at":"2026-07-05T03:21:32Z"},{"alias_kind":"pith_short_8","alias_value":"GF47O3DA","created_at":"2026-07-05T03:21:32Z"}],"graph_snapshots":[{"event_id":"sha256:7778eb3762c85c89557baeffbbd3c873adc21f98cbf5ad49b60f802b82062ff4","target":"graph","created_at":"2026-07-05T03:21:32Z","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/1901.08576/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning has shown much promise in helping improve the quality of medical, legal, and financial decision-making. In these applications, machine learning models must satisfy two important criteria: (i) they must be causal, since the goal is typically to predict individual treatment effects, and (ii) they must be interpretable, so that human decision makers can validate and trust the model predictions. There has recently been much progress along each direction independently, yet the state-of-the-art approaches are fundamentally incompatible. We propose a framework for learning interpreta","authors_text":"Carolyn Kim, Osbert Bastani","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T18:48:40Z","title":"Learning Interpretable Models with Causal Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08576","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":"sha256:16a31fe1149309d7a78e26bea17001b4e826bec9c74193d26fe9ec35ee4b324f","target":"record","created_at":"2026-07-05T03:21:32Z","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":"0448b29cff851138c693beac803af5b6f5cadef129ec3a93be9bb0aeac3e6bb0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T18:48:40Z","title_canon_sha256":"7155aa2613303a1493bd5574b56144b376d1da3484a907daaef7bafb9ae69cc5"},"schema_version":"1.0","source":{"id":"1901.08576","kind":"arxiv","version":2}},"canonical_sha256":"3179f76c607c1c58c6d014c69ca9fc246a507d675c895b107848840064569f59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3179f76c607c1c58c6d014c69ca9fc246a507d675c895b107848840064569f59","first_computed_at":"2026-07-05T03:21:32.084166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:32.084166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I0UyPUEGueE1eqmwITK3BFHGBaolf7ysJi9U/Q9mQ59vUQMKqGioHSHOlm60GtmpyDeQuPQcOlotwhy8tsvyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:32.084572Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08576","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16a31fe1149309d7a78e26bea17001b4e826bec9c74193d26fe9ec35ee4b324f","sha256:7778eb3762c85c89557baeffbbd3c873adc21f98cbf5ad49b60f802b82062ff4"],"state_sha256":"9359eb36d3c76e66b1e3c5a561c405b3af8628f3ee00e68ac058141f154d8d0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0FTOSK0RJ31Twu2mFubxN1kAMSg8WE/Rg+JAmFj9VaBzuZCZI22XgCExlZKpO9Ol21hmRd+pdSfubSW4DP9ADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:24:25.019037Z","bundle_sha256":"a4f63abaef6a0241ef22af33905c887357a1de19216587f4da9aaf2dd5cb5b13"}}