{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SZXPVA336XOAK3SZHTW4VFLKRS","short_pith_number":"pith:SZXPVA33","schema_version":"1.0","canonical_sha256":"966efa837bf5dc056e593cedca956a8cb116709a3238e1ae5593f4f8b719879c","source":{"kind":"arxiv","id":"2210.16525","version":2},"attestation_state":"computed","paper":{"title":"Spectral Representation Learning for Conditional Moment Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","econ.EM"],"primary_cat":"stat.ML","authors_text":"Bernhard Sch\\\"olkopf, Jun Zhu, Yucen Luo, Yueru Li, Ziyu Wang","submitted_at":"2022-10-29T07:48:29Z","abstract_excerpt":"Many problems in causal inference and economics can be formulated in the framework of conditional moment models, which characterize the target function through a collection of conditional moment restrictions. For nonparametric conditional moment models, efficient estimation often relies on preimposed conditions on various measures of ill-posedness of the hypothesis space, which are hard to validate when flexible models are used. In this work, we address this issue by proposing a procedure that automatically learns representations with controlled measures of ill-posedness. Our method approximat"},"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":"2210.16525","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-10-29T07:48:29Z","cross_cats_sorted":["cs.LG","econ.EM"],"title_canon_sha256":"eec5f55603392f2ab2927bc1f894e58ac8fff054c97e1a2b11798a3f555fb432","abstract_canon_sha256":"be2bf97693d9568473a22f98e6eeb987bef10113cd2281a96e6e65508a465eff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:48.389790Z","signature_b64":"oQiUFHjWkOgzZGr/rq9OMMhk7a+qpLu5YfdyTNZoHvh5LyWvzLQFIYRqqsEU1zrPozjw6SIz3Yboo0HoEPHnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"966efa837bf5dc056e593cedca956a8cb116709a3238e1ae5593f4f8b719879c","last_reissued_at":"2026-07-05T05:28:48.389311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:48.389311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral Representation Learning for Conditional Moment Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","econ.EM"],"primary_cat":"stat.ML","authors_text":"Bernhard Sch\\\"olkopf, Jun Zhu, Yucen Luo, Yueru Li, Ziyu Wang","submitted_at":"2022-10-29T07:48:29Z","abstract_excerpt":"Many problems in causal inference and economics can be formulated in the framework of conditional moment models, which characterize the target function through a collection of conditional moment restrictions. For nonparametric conditional moment models, efficient estimation often relies on preimposed conditions on various measures of ill-posedness of the hypothesis space, which are hard to validate when flexible models are used. In this work, we address this issue by proposing a procedure that automatically learns representations with controlled measures of ill-posedness. Our method approximat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16525","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/2210.16525/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":"2210.16525","created_at":"2026-07-05T05:28:48.389381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16525v2","created_at":"2026-07-05T05:28:48.389381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16525","created_at":"2026-07-05T05:28:48.389381+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZXPVA336XOA","created_at":"2026-07-05T05:28:48.389381+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZXPVA336XOAK3SZ","created_at":"2026-07-05T05:28:48.389381+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZXPVA33","created_at":"2026-07-05T05:28:48.389381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19809","citing_title":"Representation Learning for Equivariant Inference with Guarantees","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZXPVA336XOAK3SZHTW4VFLKRS","json":"https://pith.science/pith/SZXPVA336XOAK3SZHTW4VFLKRS.json","graph_json":"https://pith.science/api/pith-number/SZXPVA336XOAK3SZHTW4VFLKRS/graph.json","events_json":"https://pith.science/api/pith-number/SZXPVA336XOAK3SZHTW4VFLKRS/events.json","paper":"https://pith.science/paper/SZXPVA33"},"agent_actions":{"view_html":"https://pith.science/pith/SZXPVA336XOAK3SZHTW4VFLKRS","download_json":"https://pith.science/pith/SZXPVA336XOAK3SZHTW4VFLKRS.json","view_paper":"https://pith.science/paper/SZXPVA33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16525&json=true","fetch_graph":"https://pith.science/api/pith-number/SZXPVA336XOAK3SZHTW4VFLKRS/graph.json","fetch_events":"https://pith.science/api/pith-number/SZXPVA336XOAK3SZHTW4VFLKRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZXPVA336XOAK3SZHTW4VFLKRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZXPVA336XOAK3SZHTW4VFLKRS/action/storage_attestation","attest_author":"https://pith.science/pith/SZXPVA336XOAK3SZHTW4VFLKRS/action/author_attestation","sign_citation":"https://pith.science/pith/SZXPVA336XOAK3SZHTW4VFLKRS/action/citation_signature","submit_replication":"https://pith.science/pith/SZXPVA336XOAK3SZHTW4VFLKRS/action/replication_record"}},"created_at":"2026-07-05T05:28:48.389381+00:00","updated_at":"2026-07-05T05:28:48.389381+00:00"}