{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4L363TYINVTP6WSBP32ALEPOS6","short_pith_number":"pith:4L363TYI","canonical_record":{"source":{"id":"2103.02477","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-03T15:39:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2e49c32e36d1902057b55a7c913ebf2c6a10289f758ab9a0f1028fe9321178c5","abstract_canon_sha256":"00e444f5b2328a25559c704f12faf807a0ece1d4d1fb74c6f6b8716cec2deba6"},"schema_version":"1.0"},"canonical_sha256":"e2f7edcf086d66ff5a417ef40591ee97b44d33c1e8b74adbffb4f5849d370d96","source":{"kind":"arxiv","id":"2103.02477","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.02477","created_at":"2026-07-05T02:52:42Z"},{"alias_kind":"arxiv_version","alias_value":"2103.02477v2","created_at":"2026-07-05T02:52:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02477","created_at":"2026-07-05T02:52:42Z"},{"alias_kind":"pith_short_12","alias_value":"4L363TYINVTP","created_at":"2026-07-05T02:52:42Z"},{"alias_kind":"pith_short_16","alias_value":"4L363TYINVTP6WSB","created_at":"2026-07-05T02:52:42Z"},{"alias_kind":"pith_short_8","alias_value":"4L363TYI","created_at":"2026-07-05T02:52:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4L363TYINVTP6WSBP32ALEPOS6","target":"record","payload":{"canonical_record":{"source":{"id":"2103.02477","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-03T15:39:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2e49c32e36d1902057b55a7c913ebf2c6a10289f758ab9a0f1028fe9321178c5","abstract_canon_sha256":"00e444f5b2328a25559c704f12faf807a0ece1d4d1fb74c6f6b8716cec2deba6"},"schema_version":"1.0"},"canonical_sha256":"e2f7edcf086d66ff5a417ef40591ee97b44d33c1e8b74adbffb4f5849d370d96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:42.342900Z","signature_b64":"PYqD6hWR5D/H1JRDh40kU0FhVhsgrrNnKLGsfdi2h6QHBhPBTWFkBQxZR0mXyxsCOY1GhPlClT6OuN85EnJnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2f7edcf086d66ff5a417ef40591ee97b44d33c1e8b74adbffb4f5849d370d96","last_reissued_at":"2026-07-05T02:52:42.342300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:42.342300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.02477","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:52:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uQ9CZGxLTHnmF1OzrS0xzcaLNrFgU7ylY/ZoG3pWEoGeoD5ktaXZcm650r71q3fVsxYk9cGU2OYFthYY+ZReDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T07:46:21.142497Z"},"content_sha256":"eb0defb520205becfd6b5c9c358363be8b841995eedd15c913d5c912638c9e47","schema_version":"1.0","event_id":"sha256:eb0defb520205becfd6b5c9c358363be8b841995eedd15c913d5c912638c9e47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4L363TYINVTP6WSBP32ALEPOS6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularizing towards Causal Invariance: Linear Models with Proxies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Sontag, Jonas Peters, Michael Oberst, Nikolaj Thams","submitted_at":"2021-03-03T15:39:35Z","abstract_excerpt":"We propose a method for learning linear models whose predictive performance is robust to causal interventions on unobserved variables, when noisy proxies of those variables are available. Our approach takes the form of a regularization term that trades off between in-distribution performance and robustness to interventions. Under the assumption of a linear structural causal model, we show that a single proxy can be used to create estimators that are prediction optimal under interventions of bounded strength. This strength depends on the magnitude of the measurement noise in the proxy, which is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02477","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/2103.02477/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:52:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HUUzESa2o5gJdFG5n9L8SxEh5nUxyEie1F8I4Yw/4yy07MFfCpIhzgfDaBfv9Vhvf8ADgF9vh0qGKY83uyvGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T07:46:21.142876Z"},"content_sha256":"894fa3fab96b819b073d502bc4342279b6d6cea8127a65b7ec47ae28ee3b1349","schema_version":"1.0","event_id":"sha256:894fa3fab96b819b073d502bc4342279b6d6cea8127a65b7ec47ae28ee3b1349"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4L363TYINVTP6WSBP32ALEPOS6/bundle.json","state_url":"https://pith.science/pith/4L363TYINVTP6WSBP32ALEPOS6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4L363TYINVTP6WSBP32ALEPOS6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-23T07:46:21Z","links":{"resolver":"https://pith.science/pith/4L363TYINVTP6WSBP32ALEPOS6","bundle":"https://pith.science/pith/4L363TYINVTP6WSBP32ALEPOS6/bundle.json","state":"https://pith.science/pith/4L363TYINVTP6WSBP32ALEPOS6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4L363TYINVTP6WSBP32ALEPOS6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4L363TYINVTP6WSBP32ALEPOS6","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":"00e444f5b2328a25559c704f12faf807a0ece1d4d1fb74c6f6b8716cec2deba6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-03T15:39:35Z","title_canon_sha256":"2e49c32e36d1902057b55a7c913ebf2c6a10289f758ab9a0f1028fe9321178c5"},"schema_version":"1.0","source":{"id":"2103.02477","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.02477","created_at":"2026-07-05T02:52:42Z"},{"alias_kind":"arxiv_version","alias_value":"2103.02477v2","created_at":"2026-07-05T02:52:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02477","created_at":"2026-07-05T02:52:42Z"},{"alias_kind":"pith_short_12","alias_value":"4L363TYINVTP","created_at":"2026-07-05T02:52:42Z"},{"alias_kind":"pith_short_16","alias_value":"4L363TYINVTP6WSB","created_at":"2026-07-05T02:52:42Z"},{"alias_kind":"pith_short_8","alias_value":"4L363TYI","created_at":"2026-07-05T02:52:42Z"}],"graph_snapshots":[{"event_id":"sha256:894fa3fab96b819b073d502bc4342279b6d6cea8127a65b7ec47ae28ee3b1349","target":"graph","created_at":"2026-07-05T02:52:42Z","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/2103.02477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a method for learning linear models whose predictive performance is robust to causal interventions on unobserved variables, when noisy proxies of those variables are available. Our approach takes the form of a regularization term that trades off between in-distribution performance and robustness to interventions. Under the assumption of a linear structural causal model, we show that a single proxy can be used to create estimators that are prediction optimal under interventions of bounded strength. This strength depends on the magnitude of the measurement noise in the proxy, which is","authors_text":"David Sontag, Jonas Peters, Michael Oberst, Nikolaj Thams","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-03T15:39:35Z","title":"Regularizing towards Causal Invariance: Linear Models with Proxies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02477","kind":"arxiv","version":2},"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:eb0defb520205becfd6b5c9c358363be8b841995eedd15c913d5c912638c9e47","target":"record","created_at":"2026-07-05T02:52:42Z","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":"00e444f5b2328a25559c704f12faf807a0ece1d4d1fb74c6f6b8716cec2deba6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-03T15:39:35Z","title_canon_sha256":"2e49c32e36d1902057b55a7c913ebf2c6a10289f758ab9a0f1028fe9321178c5"},"schema_version":"1.0","source":{"id":"2103.02477","kind":"arxiv","version":2}},"canonical_sha256":"e2f7edcf086d66ff5a417ef40591ee97b44d33c1e8b74adbffb4f5849d370d96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2f7edcf086d66ff5a417ef40591ee97b44d33c1e8b74adbffb4f5849d370d96","first_computed_at":"2026-07-05T02:52:42.342300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:42.342300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PYqD6hWR5D/H1JRDh40kU0FhVhsgrrNnKLGsfdi2h6QHBhPBTWFkBQxZR0mXyxsCOY1GhPlClT6OuN85EnJnAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:42.342900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.02477","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb0defb520205becfd6b5c9c358363be8b841995eedd15c913d5c912638c9e47","sha256:894fa3fab96b819b073d502bc4342279b6d6cea8127a65b7ec47ae28ee3b1349"],"state_sha256":"49312d6176e9194c034d4c9b31c05f333948ad6b3b281346b753e0de9d4e880a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pfP2qS3eF7f0Dm4b+oM3lKXzVCn6iaHCWN9SCNJsPjpCsk5pqJ+ZH2Zh6RCW8N27VwayVJwE+RS0IlsrymfsCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-23T07:46:21.145349Z","bundle_sha256":"16b7658ea027c87a4ca463f190bb37614e0c3a9b09ab7277c40993354fbbc1d8"}}