{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MUO2X6JQYNJO3ZQYMQN4M7X6GC","short_pith_number":"pith:MUO2X6JQ","schema_version":"1.0","canonical_sha256":"651dabf930c352ede618641bc67efe3091d58e840fe17b94373f06332ec5010c","source":{"kind":"arxiv","id":"2404.04399","version":2},"attestation_state":"computed","paper":{"title":"Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.AP","stat.ME"],"primary_cat":"stat.ML","authors_text":"Hiroyasu Iso, Mark van der Laan, Mingduo Zhao, Sky Qiu, Toru Shirakawa, Yi Li, Yulun Wu, Yuxuan Li","submitted_at":"2024-04-05T20:56:15Z","abstract_excerpt":"We propose Deep Longitudinal Targeted Minimum Loss-based Estimation (Deep LTMLE), a novel approach to estimate the counterfactual mean of outcome under dynamic treatment policies in longitudinal problem settings. Our approach utilizes a transformer architecture with heterogeneous type embedding trained using temporal-difference learning. After obtaining an initial estimate using the transformer, following the targeted minimum loss-based likelihood estimation (TMLE) framework, we statistically corrected for the bias commonly associated with machine learning algorithms. Furthermore, our method a"},"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":"2404.04399","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-04-05T20:56:15Z","cross_cats_sorted":["cs.AI","cs.LG","stat.AP","stat.ME"],"title_canon_sha256":"28facb9fad5d4fdc0f25d3f1cf09ae0b06172ba32f938b235bd87068020e8729","abstract_canon_sha256":"befe38fafcb71ebeeb19b239431a806212f1ef2db699dbac8e0595b4cfd403cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:48.880719Z","signature_b64":"YvRBvoMWrXJ1HV3lRucRDzJlWXWs3bmAgUdApDSfNFME7vojcnjAsw7EOZKKZcOwCEhbN1+JqF86hFTRbEW9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"651dabf930c352ede618641bc67efe3091d58e840fe17b94373f06332ec5010c","last_reissued_at":"2026-07-05T11:16:48.880214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:48.880214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.AP","stat.ME"],"primary_cat":"stat.ML","authors_text":"Hiroyasu Iso, Mark van der Laan, Mingduo Zhao, Sky Qiu, Toru Shirakawa, Yi Li, Yulun Wu, Yuxuan Li","submitted_at":"2024-04-05T20:56:15Z","abstract_excerpt":"We propose Deep Longitudinal Targeted Minimum Loss-based Estimation (Deep LTMLE), a novel approach to estimate the counterfactual mean of outcome under dynamic treatment policies in longitudinal problem settings. Our approach utilizes a transformer architecture with heterogeneous type embedding trained using temporal-difference learning. After obtaining an initial estimate using the transformer, following the targeted minimum loss-based likelihood estimation (TMLE) framework, we statistically corrected for the bias commonly associated with machine learning algorithms. Furthermore, our method a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04399","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/2404.04399/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":"2404.04399","created_at":"2026-07-05T11:16:48.880274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04399v2","created_at":"2026-07-05T11:16:48.880274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04399","created_at":"2026-07-05T11:16:48.880274+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUO2X6JQYNJO","created_at":"2026-07-05T11:16:48.880274+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUO2X6JQYNJO3ZQY","created_at":"2026-07-05T11:16:48.880274+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUO2X6JQ","created_at":"2026-07-05T11:16:48.880274+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14284","citing_title":"Smooth Multi-Policy Causal Effect Estimation in Longitudinal Settings","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MUO2X6JQYNJO3ZQYMQN4M7X6GC","json":"https://pith.science/pith/MUO2X6JQYNJO3ZQYMQN4M7X6GC.json","graph_json":"https://pith.science/api/pith-number/MUO2X6JQYNJO3ZQYMQN4M7X6GC/graph.json","events_json":"https://pith.science/api/pith-number/MUO2X6JQYNJO3ZQYMQN4M7X6GC/events.json","paper":"https://pith.science/paper/MUO2X6JQ"},"agent_actions":{"view_html":"https://pith.science/pith/MUO2X6JQYNJO3ZQYMQN4M7X6GC","download_json":"https://pith.science/pith/MUO2X6JQYNJO3ZQYMQN4M7X6GC.json","view_paper":"https://pith.science/paper/MUO2X6JQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04399&json=true","fetch_graph":"https://pith.science/api/pith-number/MUO2X6JQYNJO3ZQYMQN4M7X6GC/graph.json","fetch_events":"https://pith.science/api/pith-number/MUO2X6JQYNJO3ZQYMQN4M7X6GC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUO2X6JQYNJO3ZQYMQN4M7X6GC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUO2X6JQYNJO3ZQYMQN4M7X6GC/action/storage_attestation","attest_author":"https://pith.science/pith/MUO2X6JQYNJO3ZQYMQN4M7X6GC/action/author_attestation","sign_citation":"https://pith.science/pith/MUO2X6JQYNJO3ZQYMQN4M7X6GC/action/citation_signature","submit_replication":"https://pith.science/pith/MUO2X6JQYNJO3ZQYMQN4M7X6GC/action/replication_record"}},"created_at":"2026-07-05T11:16:48.880274+00:00","updated_at":"2026-07-05T11:16:48.880274+00:00"}