{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LHNVDRS4XWXQHWAPOKZU3IVZHA","short_pith_number":"pith:LHNVDRS4","schema_version":"1.0","canonical_sha256":"59db51c65cbdaf03d80f72b34da2b9382319f7d41ad400303107beecb8f0bf5f","source":{"kind":"arxiv","id":"2402.01785","version":1},"attestation_state":"computed","paper":{"title":"DoubleMLDeep: Estimation of Causal Effects with Multimodal Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","econ.EM","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jan Teichert-Kluge, Martin Spindler, Philipp Bach, Suhas Vijaykumar, Sven Klaassen, Victor Chernozhukov","submitted_at":"2024-02-01T21:34:34Z","abstract_excerpt":"This paper explores the use of unstructured, multimodal data, namely text and images, in causal inference and treatment effect estimation. We propose a neural network architecture that is adapted to the double machine learning (DML) framework, specifically the partially linear model. An additional contribution of our paper is a new method to generate a semi-synthetic dataset which can be used to evaluate the performance of causal effect estimation in the presence of text and images as confounders. The proposed methods and architectures are evaluated on the semi-synthetic dataset and compared t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.01785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T21:34:34Z","cross_cats_sorted":["cs.AI","econ.EM","stat.ME","stat.ML"],"title_canon_sha256":"b717ee741c7666f946e12f5e6ad4e8e07c59b589f5462785f9289e0dd6755c9e","abstract_canon_sha256":"25b59cd6ac8fee4aee03f2a8e46e1d4a7c456859d91348798ecf1b1d2ef9ab56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:06.781143Z","signature_b64":"xmx2evPJslIArzFlv093+QtSyQyKWc9EjCpixQU1+kbL+mrrdARh5VwUiD4o4AdPi9pFg10usrGpp9jksIO/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59db51c65cbdaf03d80f72b34da2b9382319f7d41ad400303107beecb8f0bf5f","last_reissued_at":"2026-07-05T07:41:06.780617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:06.780617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DoubleMLDeep: Estimation of Causal Effects with Multimodal Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","econ.EM","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jan Teichert-Kluge, Martin Spindler, Philipp Bach, Suhas Vijaykumar, Sven Klaassen, Victor Chernozhukov","submitted_at":"2024-02-01T21:34:34Z","abstract_excerpt":"This paper explores the use of unstructured, multimodal data, namely text and images, in causal inference and treatment effect estimation. We propose a neural network architecture that is adapted to the double machine learning (DML) framework, specifically the partially linear model. An additional contribution of our paper is a new method to generate a semi-synthetic dataset which can be used to evaluate the performance of causal effect estimation in the presence of text and images as confounders. The proposed methods and architectures are evaluated on the semi-synthetic dataset and compared t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01785","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.01785/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.01785","created_at":"2026-07-05T07:41:06.780675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01785v1","created_at":"2026-07-05T07:41:06.780675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01785","created_at":"2026-07-05T07:41:06.780675+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHNVDRS4XWXQ","created_at":"2026-07-05T07:41:06.780675+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHNVDRS4XWXQHWAP","created_at":"2026-07-05T07:41:06.780675+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHNVDRS4","created_at":"2026-07-05T07:41:06.780675+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.20993","citing_title":"Annotation-Assisted Learning of Treatment Policies From Multimodal Electronic Health Records","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00176","citing_title":"SHIFT: Robust Double Machine Learning for Average Dose-Response Functions under Heavy-Tailed Contamination","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHNVDRS4XWXQHWAPOKZU3IVZHA","json":"https://pith.science/pith/LHNVDRS4XWXQHWAPOKZU3IVZHA.json","graph_json":"https://pith.science/api/pith-number/LHNVDRS4XWXQHWAPOKZU3IVZHA/graph.json","events_json":"https://pith.science/api/pith-number/LHNVDRS4XWXQHWAPOKZU3IVZHA/events.json","paper":"https://pith.science/paper/LHNVDRS4"},"agent_actions":{"view_html":"https://pith.science/pith/LHNVDRS4XWXQHWAPOKZU3IVZHA","download_json":"https://pith.science/pith/LHNVDRS4XWXQHWAPOKZU3IVZHA.json","view_paper":"https://pith.science/paper/LHNVDRS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01785&json=true","fetch_graph":"https://pith.science/api/pith-number/LHNVDRS4XWXQHWAPOKZU3IVZHA/graph.json","fetch_events":"https://pith.science/api/pith-number/LHNVDRS4XWXQHWAPOKZU3IVZHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHNVDRS4XWXQHWAPOKZU3IVZHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHNVDRS4XWXQHWAPOKZU3IVZHA/action/storage_attestation","attest_author":"https://pith.science/pith/LHNVDRS4XWXQHWAPOKZU3IVZHA/action/author_attestation","sign_citation":"https://pith.science/pith/LHNVDRS4XWXQHWAPOKZU3IVZHA/action/citation_signature","submit_replication":"https://pith.science/pith/LHNVDRS4XWXQHWAPOKZU3IVZHA/action/replication_record"}},"created_at":"2026-07-05T07:41:06.780675+00:00","updated_at":"2026-07-05T07:41:06.780675+00:00"}