{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:76XYOT2UJYC7YU6MZOAIBN3KN4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c036e08566f2cc89911cfb578d0eec98caded69900902f457218c2dc74a2ac87","cross_cats_sorted":["stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-28T13:21:27Z","title_canon_sha256":"051f2ec31de5baafbdf8f9622d6be6fb3f36a391fc5051a150719f851ed97362"},"schema_version":"1.0","source":{"id":"2107.13346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.13346","created_at":"2026-07-05T03:01:29Z"},{"alias_kind":"arxiv_version","alias_value":"2107.13346v1","created_at":"2026-07-05T03:01:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13346","created_at":"2026-07-05T03:01:29Z"},{"alias_kind":"pith_short_12","alias_value":"76XYOT2UJYC7","created_at":"2026-07-05T03:01:29Z"},{"alias_kind":"pith_short_16","alias_value":"76XYOT2UJYC7YU6M","created_at":"2026-07-05T03:01:29Z"},{"alias_kind":"pith_short_8","alias_value":"76XYOT2U","created_at":"2026-07-05T03:01:29Z"}],"graph_snapshots":[{"event_id":"sha256:ab808ea96659d1e39c7b2d993824b61c1626a8b6c963b6422eae349ce78a7c3c","target":"graph","created_at":"2026-07-05T03:01:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.13346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The machine learning toolbox for estimation of heterogeneous treatment effects from observational data is expanding rapidly, yet many of its algorithms have been evaluated only on a very limited set of semi-synthetic benchmark datasets. In this paper, we show that even in arguably the simplest setting -- estimation under ignorability assumptions -- the results of such empirical evaluations can be misleading if (i) the assumptions underlying the data-generating mechanisms in benchmark datasets and (ii) their interplay with baseline algorithms are inadequately discussed. We consider two popular ","authors_text":"Alicia Curth, Mihaela van der Schaar","cross_cats":["stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-28T13:21:27Z","title":"Doing Great at Estimating CATE? On the Neglected Assumptions in Benchmark Comparisons of Treatment Effect Estimators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13346","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:edb66fac4dc52b8156ffbdb7ac0a5499a2b6b2438eea8d1db9b3ccaed396c631","target":"record","created_at":"2026-07-05T03:01:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c036e08566f2cc89911cfb578d0eec98caded69900902f457218c2dc74a2ac87","cross_cats_sorted":["stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-28T13:21:27Z","title_canon_sha256":"051f2ec31de5baafbdf8f9622d6be6fb3f36a391fc5051a150719f851ed97362"},"schema_version":"1.0","source":{"id":"2107.13346","kind":"arxiv","version":1}},"canonical_sha256":"ffaf874f544e05fc53cccb8080b76a6f09509fa7f01c511647b1e0ee33fcb3ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffaf874f544e05fc53cccb8080b76a6f09509fa7f01c511647b1e0ee33fcb3ea","first_computed_at":"2026-07-05T03:01:29.250301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:01:29.250301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r1uXman5nuJkRlZsPCJJo7H14avrYeaXVYKPXzUYov2mEYqxsij6qly+xmsA16EHil+xiNymdZ7AOgm/w40+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:01:29.250735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.13346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:edb66fac4dc52b8156ffbdb7ac0a5499a2b6b2438eea8d1db9b3ccaed396c631","sha256:ab808ea96659d1e39c7b2d993824b61c1626a8b6c963b6422eae349ce78a7c3c"],"state_sha256":"b83826ff81324af14eb8ea8bb33fee452ce3d8f8119f2b020f01e940ad5859df"}