{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KBCJCB5TUQGMBVSZBQKMO6XT3S","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":"a3b2a14b57c8db7bbc81b640fb07c4c1d1e8f3a994768e54f9eea3b8bb2da0a6","cross_cats_sorted":["cs.AI","cs.LG","econ.EM","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-02T06:21:04Z","title_canon_sha256":"9ee54394e7df3458ec509565de0b0889926f5f7832a5fccc06a01f86346fcaf6"},"schema_version":"1.0","source":{"id":"2410.01265","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01265","created_at":"2026-07-05T11:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01265v3","created_at":"2026-07-05T11:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01265","created_at":"2026-07-05T11:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"KBCJCB5TUQGM","created_at":"2026-07-05T11:01:01Z"},{"alias_kind":"pith_short_16","alias_value":"KBCJCB5TUQGMBVSZ","created_at":"2026-07-05T11:01:01Z"},{"alias_kind":"pith_short_8","alias_value":"KBCJCB5T","created_at":"2026-07-05T11:01:01Z"}],"graph_snapshots":[{"event_id":"sha256:b533de4819f3e4e3992b4344d74d4de2bd53c7bff9b66ab0b0af33c2ad0858db","target":"graph","created_at":"2026-07-05T11:01:01Z","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/2410.01265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore the capability of transformers to address endogeneity in in-context linear regression. Our main finding is that transformers inherently possess a mechanism to handle endogeneity effectively using instrumental variables (IV). First, we demonstrate that the transformer architecture can emulate a gradient-based bi-level optimization procedure that converges to the widely used two-stage least squares $(\\textsf{2SLS})$ solution at an exponential rate. Next, we propose an in-context pretraining scheme and provide theoretical guarantees showing that the global minimizer of the pre-training","authors_text":"Haodong Liang, Krishnakumar Balasubramanian, Lifeng Lai","cross_cats":["cs.AI","cs.LG","econ.EM","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-02T06:21:04Z","title":"Transformers Handle Endogeneity in In-Context Linear Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01265","kind":"arxiv","version":3},"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":"sha256:3bf101942c2a424ec12ddeda90a2aa69cecf359298b6624d600677c578b5411d","target":"record","created_at":"2026-07-05T11:01:01Z","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":"a3b2a14b57c8db7bbc81b640fb07c4c1d1e8f3a994768e54f9eea3b8bb2da0a6","cross_cats_sorted":["cs.AI","cs.LG","econ.EM","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-02T06:21:04Z","title_canon_sha256":"9ee54394e7df3458ec509565de0b0889926f5f7832a5fccc06a01f86346fcaf6"},"schema_version":"1.0","source":{"id":"2410.01265","kind":"arxiv","version":3}},"canonical_sha256":"50449107b3a40cc0d6590c14c77af3dc91002c47987f9708ee79708e104999e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50449107b3a40cc0d6590c14c77af3dc91002c47987f9708ee79708e104999e4","first_computed_at":"2026-07-05T11:01:01.820035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:01.820035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d9reUYMZcoWDMRO4rR0UZ7ag938wT6otIH/MZtAnkR9M7SDkwAzLPCF0FTrsx5pHxqFzsf6lK+G6Cp31rDOMAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:01.820603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01265","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3bf101942c2a424ec12ddeda90a2aa69cecf359298b6624d600677c578b5411d","sha256:b533de4819f3e4e3992b4344d74d4de2bd53c7bff9b66ab0b0af33c2ad0858db"],"state_sha256":"40c65c2bcbc369facd0b39bc89cdd7a5d1955e5c6858c6a77d4d15030bb43ffd"}