{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NTMH54GU5JSOC77I23OJO27CHO","short_pith_number":"pith:NTMH54GU","schema_version":"1.0","canonical_sha256":"6cd87ef0d4ea64e17fe8d6dc976be23bb9758316f01f695c6032a9e4b075117c","source":{"kind":"arxiv","id":"2506.02200","version":2},"attestation_state":"computed","paper":{"title":"Learning Treatment Representations for Downstream Instrumental Variable Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.LG","authors_text":"Hui Lan, Shiangyi Lin, Vasilis Syrgkanis","submitted_at":"2025-06-02T19:41:23Z","abstract_excerpt":"Traditional instrumental variable (IV) estimators face a fundamental constraint: they can only accommodate as many endogenous treatment variables as available instruments. This limitation becomes particularly challenging in settings where the treatment is presented in a high-dimensional and unstructured manner (e.g. descriptions of patient treatment pathways in a hospital). In such settings, researchers typically resort to applying unsupervised dimension reduction techniques to learn a low-dimensional treatment representation prior to implementing IV regression analysis. We show that such meth"},"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":"2506.02200","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T19:41:23Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"f392bfb7602c3f96c94049660ef767ab6bc575ec474f29cf83cfce9ed15d1b94","abstract_canon_sha256":"3a0774acb3e46169395ab57b23f23615105eaee3a25a5ca9b56254763f9d2c20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:05.080829Z","signature_b64":"Q7UNexSq6yiTY74oX6lKu+D2bwvAlbbVHI1mm0hjGk/ABF5NJjpPrdu+UZndgkWURbSYF0HGpLvceV6nJInLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cd87ef0d4ea64e17fe8d6dc976be23bb9758316f01f695c6032a9e4b075117c","last_reissued_at":"2026-07-05T11:26:05.080324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:05.080324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Treatment Representations for Downstream Instrumental Variable Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.LG","authors_text":"Hui Lan, Shiangyi Lin, Vasilis Syrgkanis","submitted_at":"2025-06-02T19:41:23Z","abstract_excerpt":"Traditional instrumental variable (IV) estimators face a fundamental constraint: they can only accommodate as many endogenous treatment variables as available instruments. This limitation becomes particularly challenging in settings where the treatment is presented in a high-dimensional and unstructured manner (e.g. descriptions of patient treatment pathways in a hospital). In such settings, researchers typically resort to applying unsupervised dimension reduction techniques to learn a low-dimensional treatment representation prior to implementing IV regression analysis. We show that such meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02200","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/2506.02200/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":"2506.02200","created_at":"2026-07-05T11:26:05.080406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02200v2","created_at":"2026-07-05T11:26:05.080406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02200","created_at":"2026-07-05T11:26:05.080406+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTMH54GU5JSO","created_at":"2026-07-05T11:26:05.080406+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTMH54GU5JSOC77I","created_at":"2026-07-05T11:26:05.080406+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTMH54GU","created_at":"2026-07-05T11:26:05.080406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTMH54GU5JSOC77I23OJO27CHO","json":"https://pith.science/pith/NTMH54GU5JSOC77I23OJO27CHO.json","graph_json":"https://pith.science/api/pith-number/NTMH54GU5JSOC77I23OJO27CHO/graph.json","events_json":"https://pith.science/api/pith-number/NTMH54GU5JSOC77I23OJO27CHO/events.json","paper":"https://pith.science/paper/NTMH54GU"},"agent_actions":{"view_html":"https://pith.science/pith/NTMH54GU5JSOC77I23OJO27CHO","download_json":"https://pith.science/pith/NTMH54GU5JSOC77I23OJO27CHO.json","view_paper":"https://pith.science/paper/NTMH54GU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02200&json=true","fetch_graph":"https://pith.science/api/pith-number/NTMH54GU5JSOC77I23OJO27CHO/graph.json","fetch_events":"https://pith.science/api/pith-number/NTMH54GU5JSOC77I23OJO27CHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTMH54GU5JSOC77I23OJO27CHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTMH54GU5JSOC77I23OJO27CHO/action/storage_attestation","attest_author":"https://pith.science/pith/NTMH54GU5JSOC77I23OJO27CHO/action/author_attestation","sign_citation":"https://pith.science/pith/NTMH54GU5JSOC77I23OJO27CHO/action/citation_signature","submit_replication":"https://pith.science/pith/NTMH54GU5JSOC77I23OJO27CHO/action/replication_record"}},"created_at":"2026-07-05T11:26:05.080406+00:00","updated_at":"2026-07-05T11:26:05.080406+00:00"}