{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U4UALB5ILYZZZ3E4GHYJIENRWQ","short_pith_number":"pith:U4UALB5I","schema_version":"1.0","canonical_sha256":"a7280587a85e339cec9c31f09411b1b410f4a511a105bf7f95d33c46b947f265","source":{"kind":"arxiv","id":"2606.07399","version":1},"attestation_state":"computed","paper":{"title":"Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jingsen Zhu, Michele Santacatterina, Ramin Zabih, Raphael C Kim","submitted_at":"2026-06-05T15:40:59Z","abstract_excerpt":"Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification. We introduce ADIGen, a framework for automatic, debiased, and invariant counterfactual generation under general interventions, including high-dimensional interventions and outcomes. ADIGen combines Riesz regression to avoid unstable density-ratio estimation, causal invariance to improve generalization under distribution shift, "},"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":"2606.07399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-05T15:40:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"20b16c073ae76793f47ec767fdbe620dbe58abe7d9c79d36185472c5845be0ff","abstract_canon_sha256":"3fcd89d402f5407a2ef966a180178710979c79f15b103990e2637c48c8042ba9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:24.834886Z","signature_b64":"lu3LD9hy+OfP90cjfVkifvDBH6/bBb9p7yPcuuwewgVdwzrwlMEnOUFE25ii7p0l8G6ldp+ivhy2VuO3wr+RDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7280587a85e339cec9c31f09411b1b410f4a511a105bf7f95d33c46b947f265","last_reissued_at":"2026-06-08T01:05:24.834011Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:24.834011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jingsen Zhu, Michele Santacatterina, Ramin Zabih, Raphael C Kim","submitted_at":"2026-06-05T15:40:59Z","abstract_excerpt":"Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification. We introduce ADIGen, a framework for automatic, debiased, and invariant counterfactual generation under general interventions, including high-dimensional interventions and outcomes. ADIGen combines Riesz regression to avoid unstable density-ratio estimation, causal invariance to improve generalization under distribution shift, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07399","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/2606.07399/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":"2606.07399","created_at":"2026-06-08T01:05:24.834155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07399v1","created_at":"2026-06-08T01:05:24.834155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07399","created_at":"2026-06-08T01:05:24.834155+00:00"},{"alias_kind":"pith_short_12","alias_value":"U4UALB5ILYZZ","created_at":"2026-06-08T01:05:24.834155+00:00"},{"alias_kind":"pith_short_16","alias_value":"U4UALB5ILYZZZ3E4","created_at":"2026-06-08T01:05:24.834155+00:00"},{"alias_kind":"pith_short_8","alias_value":"U4UALB5I","created_at":"2026-06-08T01:05:24.834155+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/U4UALB5ILYZZZ3E4GHYJIENRWQ","json":"https://pith.science/pith/U4UALB5ILYZZZ3E4GHYJIENRWQ.json","graph_json":"https://pith.science/api/pith-number/U4UALB5ILYZZZ3E4GHYJIENRWQ/graph.json","events_json":"https://pith.science/api/pith-number/U4UALB5ILYZZZ3E4GHYJIENRWQ/events.json","paper":"https://pith.science/paper/U4UALB5I"},"agent_actions":{"view_html":"https://pith.science/pith/U4UALB5ILYZZZ3E4GHYJIENRWQ","download_json":"https://pith.science/pith/U4UALB5ILYZZZ3E4GHYJIENRWQ.json","view_paper":"https://pith.science/paper/U4UALB5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07399&json=true","fetch_graph":"https://pith.science/api/pith-number/U4UALB5ILYZZZ3E4GHYJIENRWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/U4UALB5ILYZZZ3E4GHYJIENRWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U4UALB5ILYZZZ3E4GHYJIENRWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U4UALB5ILYZZZ3E4GHYJIENRWQ/action/storage_attestation","attest_author":"https://pith.science/pith/U4UALB5ILYZZZ3E4GHYJIENRWQ/action/author_attestation","sign_citation":"https://pith.science/pith/U4UALB5ILYZZZ3E4GHYJIENRWQ/action/citation_signature","submit_replication":"https://pith.science/pith/U4UALB5ILYZZZ3E4GHYJIENRWQ/action/replication_record"}},"created_at":"2026-06-08T01:05:24.834155+00:00","updated_at":"2026-06-08T01:05:24.834155+00:00"}