{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:NULTB72XE6PWZUUEFPKWT2AXNG","short_pith_number":"pith:NULTB72X","canonical_record":{"source":{"id":"1706.05966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-19T14:12:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6e1c58c0b45a8390beef7070e23a7cdf16ef1b6dfd596e4c14fe57a4997f64ea","abstract_canon_sha256":"3c9748eb80982dfa9d529808aa63268c26056f21273a66c5e5c883142322cec1"},"schema_version":"1.0"},"canonical_sha256":"6d1730ff57279f6cd2842bd569e81769a0b1642c8f30c8c52e5e6802edeab99e","source":{"kind":"arxiv","id":"1706.05966","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.05966","created_at":"2026-05-18T00:42:08Z"},{"alias_kind":"arxiv_version","alias_value":"1706.05966v1","created_at":"2026-05-18T00:42:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.05966","created_at":"2026-05-18T00:42:08Z"},{"alias_kind":"pith_short_12","alias_value":"NULTB72XE6PW","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"NULTB72XE6PWZUUE","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"NULTB72X","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:NULTB72XE6PWZUUEFPKWT2AXNG","target":"record","payload":{"canonical_record":{"source":{"id":"1706.05966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-19T14:12:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6e1c58c0b45a8390beef7070e23a7cdf16ef1b6dfd596e4c14fe57a4997f64ea","abstract_canon_sha256":"3c9748eb80982dfa9d529808aa63268c26056f21273a66c5e5c883142322cec1"},"schema_version":"1.0"},"canonical_sha256":"6d1730ff57279f6cd2842bd569e81769a0b1642c8f30c8c52e5e6802edeab99e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:08.391035Z","signature_b64":"EHHHri66mMpi1C5U+mHkEpJfY/4tYu1UhOXb2Kl4osnVejI3ao7M16m6CyM9bKx3f9sI/V/AoKAHEgoP0OrRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d1730ff57279f6cd2842bd569e81769a0b1642c8f30c8c52e5e6802edeab99e","last_reissued_at":"2026-05-18T00:42:08.390594Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:08.390594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.05966","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":"2026-05-18T00:42:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QVPG9KoeXDMgbUIy4acQx5Hq6d+LgUn9bnSUrpOJ/uG0rsSiuXi9dQiUji8CFtZqCkAwqkXwHK82GngIqa+6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T18:08:37.718972Z"},"content_sha256":"87538f54223408f7558e76fa4eefbe71284590e55ff255e038e2021474346f8e","schema_version":"1.0","event_id":"sha256:87538f54223408f7558e76fa4eefbe71284590e55ff255e038e2021474346f8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:NULTB72XE6PWZUUEFPKWT2AXNG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Counterfactual Networks with Propensity-Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed M. Alaa, Michael Weisz, Mihaela van der Schaar","submitted_at":"2017-06-19T14:12:12Z","abstract_excerpt":"We propose a novel approach for inferring the individualized causal effects of a treatment (intervention) from observational data. Our approach conceptualizes causal inference as a multitask learning problem; we model a subject's potential outcomes using a deep multitask network with a set of shared layers among the factual and counterfactual outcomes, and a set of outcome-specific layers. The impact of selection bias in the observational data is alleviated via a propensity-dropout regularization scheme, in which the network is thinned for every training example via a dropout probability that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.05966","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":"2026-05-18T00:42:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14f3r07rukUwEELqBpXWiHwUIKkylLDR+hkMKmj+zq0HMPtr7Ly36SAd2L4yOmtBZe1H9kZFsZPgjbhGXbv5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T18:08:37.719312Z"},"content_sha256":"9227ed46f31ef15de96385a84f67da1f28185632ce4ae8625fe0fcacbc8f14fa","schema_version":"1.0","event_id":"sha256:9227ed46f31ef15de96385a84f67da1f28185632ce4ae8625fe0fcacbc8f14fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NULTB72XE6PWZUUEFPKWT2AXNG/bundle.json","state_url":"https://pith.science/pith/NULTB72XE6PWZUUEFPKWT2AXNG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NULTB72XE6PWZUUEFPKWT2AXNG/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":"2026-05-20T18:08:37Z","links":{"resolver":"https://pith.science/pith/NULTB72XE6PWZUUEFPKWT2AXNG","bundle":"https://pith.science/pith/NULTB72XE6PWZUUEFPKWT2AXNG/bundle.json","state":"https://pith.science/pith/NULTB72XE6PWZUUEFPKWT2AXNG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NULTB72XE6PWZUUEFPKWT2AXNG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:NULTB72XE6PWZUUEFPKWT2AXNG","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":"3c9748eb80982dfa9d529808aa63268c26056f21273a66c5e5c883142322cec1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-19T14:12:12Z","title_canon_sha256":"6e1c58c0b45a8390beef7070e23a7cdf16ef1b6dfd596e4c14fe57a4997f64ea"},"schema_version":"1.0","source":{"id":"1706.05966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.05966","created_at":"2026-05-18T00:42:08Z"},{"alias_kind":"arxiv_version","alias_value":"1706.05966v1","created_at":"2026-05-18T00:42:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.05966","created_at":"2026-05-18T00:42:08Z"},{"alias_kind":"pith_short_12","alias_value":"NULTB72XE6PW","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"NULTB72XE6PWZUUE","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"NULTB72X","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:9227ed46f31ef15de96385a84f67da1f28185632ce4ae8625fe0fcacbc8f14fa","target":"graph","created_at":"2026-05-18T00:42:08Z","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":"We propose a novel approach for inferring the individualized causal effects of a treatment (intervention) from observational data. Our approach conceptualizes causal inference as a multitask learning problem; we model a subject's potential outcomes using a deep multitask network with a set of shared layers among the factual and counterfactual outcomes, and a set of outcome-specific layers. The impact of selection bias in the observational data is alleviated via a propensity-dropout regularization scheme, in which the network is thinned for every training example via a dropout probability that ","authors_text":"Ahmed M. Alaa, Michael Weisz, Mihaela van der Schaar","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-19T14:12:12Z","title":"Deep Counterfactual Networks with Propensity-Dropout"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.05966","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":"sha256:87538f54223408f7558e76fa4eefbe71284590e55ff255e038e2021474346f8e","target":"record","created_at":"2026-05-18T00:42:08Z","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":"3c9748eb80982dfa9d529808aa63268c26056f21273a66c5e5c883142322cec1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-19T14:12:12Z","title_canon_sha256":"6e1c58c0b45a8390beef7070e23a7cdf16ef1b6dfd596e4c14fe57a4997f64ea"},"schema_version":"1.0","source":{"id":"1706.05966","kind":"arxiv","version":1}},"canonical_sha256":"6d1730ff57279f6cd2842bd569e81769a0b1642c8f30c8c52e5e6802edeab99e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d1730ff57279f6cd2842bd569e81769a0b1642c8f30c8c52e5e6802edeab99e","first_computed_at":"2026-05-18T00:42:08.390594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:08.390594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EHHHri66mMpi1C5U+mHkEpJfY/4tYu1UhOXb2Kl4osnVejI3ao7M16m6CyM9bKx3f9sI/V/AoKAHEgoP0OrRCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:08.391035Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.05966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87538f54223408f7558e76fa4eefbe71284590e55ff255e038e2021474346f8e","sha256:9227ed46f31ef15de96385a84f67da1f28185632ce4ae8625fe0fcacbc8f14fa"],"state_sha256":"3e5790f0bf4a5b9b9f5a67fce26440829f15a25b8179a8a3acb6d1853c473a39"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHXYuFJXyXA12P3OcyxajpGJZPyniG4RqFfDEXqwDuWZ/GIQ3qHWYe+oRtsB7bOs9fPCmInsYfbR3pZIHIKVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T18:08:37.721238Z","bundle_sha256":"37cf36b220d947ebb329aab9499c586980b4dc6d7829b82eec7d124ac94caae1"}}