{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GX6L2TS5Y4DKPKC5GJNLAAV6UF","short_pith_number":"pith:GX6L2TS5","canonical_record":{"source":{"id":"1812.04778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-12T02:16:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ecd2ba7c2d33e98aa6607c11d7b7dcc672e0541a8dd0994d672c080397a3e566","abstract_canon_sha256":"fd8f5b9dc86ac11676fc9ee2491832635b77f90a4a149b5af37eda5cdf50b155"},"schema_version":"1.0"},"canonical_sha256":"35fcbd4e5dc706a7a85d325ab002bea1656e34fba9f2e0e0d32c9c6ae601399c","source":{"kind":"arxiv","id":"1812.04778","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.04778","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"1812.04778v1","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04778","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"GX6L2TS5Y4DK","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GX6L2TS5Y4DKPKC5","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GX6L2TS5","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GX6L2TS5Y4DKPKC5GJNLAAV6UF","target":"record","payload":{"canonical_record":{"source":{"id":"1812.04778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-12T02:16:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ecd2ba7c2d33e98aa6607c11d7b7dcc672e0541a8dd0994d672c080397a3e566","abstract_canon_sha256":"fd8f5b9dc86ac11676fc9ee2491832635b77f90a4a149b5af37eda5cdf50b155"},"schema_version":"1.0"},"canonical_sha256":"35fcbd4e5dc706a7a85d325ab002bea1656e34fba9f2e0e0d32c9c6ae601399c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:29.511712Z","signature_b64":"0nc1EFZA3Ux1nmyVAQBCVuXGWQ26mypbe7iPb6mnn1MbD7RvbBI92PnmFomki06kT7eG+OCdsdYADJFfxQNiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35fcbd4e5dc706a7a85d325ab002bea1656e34fba9f2e0e0d32c9c6ae601399c","last_reissued_at":"2026-05-17T23:58:29.511169Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:29.511169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.04778","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vKCA2CrfW+IrHX+KnGWFrRGC5sAbqycfb9okEXeIFLRR1jZbXNmVnES0qRQ94wsZaGVIwaOtTLVCtpG7Z1h+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:41:08.178013Z"},"content_sha256":"db4c1f4208f1c2bf62ebe1c16af217ab45405a4ffcce9a19e10551d09e12b538","schema_version":"1.0","event_id":"sha256:db4c1f4208f1c2bf62ebe1c16af217ab45405a4ffcce9a19e10551d09e12b538"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GX6L2TS5Y4DKPKC5GJNLAAV6UF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging the Generalization Gap: Training Robust Models on Confounded Biological Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Drake, Ajay Kannan, Marvin Bertin, Nathan Wan, Tzu-Yu Liu","submitted_at":"2018-12-12T02:16:20Z","abstract_excerpt":"Statistical learning on biological data can be challenging due to confounding variables in sample collection and processing. Confounders can cause models to generalize poorly and result in inaccurate prediction performance metrics if models are not validated thoroughly. In this paper, we propose methods to control for confounding factors and further improve prediction performance. We introduce OrthoNormal basis construction In cOnfounding factor Normalization (ONION) to remove confounding covariates and use the Domain-Adversarial Neural Network (DANN) to penalize models for encoding confounder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04778","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":""},"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":"2026-05-17T23:58:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4bHwa9tVBsjHiIyKQfqKbIyJ7xCLvIkw6W4w6aqtpu8max/JErxPsYbnUzJ8yXmjJNe0G6P8q0mWkEaVw4bBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:41:08.178373Z"},"content_sha256":"1a532f45ef7ceca21e9f1362237716631866a4acffa42ebc0b71fb3e08c2cd81","schema_version":"1.0","event_id":"sha256:1a532f45ef7ceca21e9f1362237716631866a4acffa42ebc0b71fb3e08c2cd81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GX6L2TS5Y4DKPKC5GJNLAAV6UF/bundle.json","state_url":"https://pith.science/pith/GX6L2TS5Y4DKPKC5GJNLAAV6UF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GX6L2TS5Y4DKPKC5GJNLAAV6UF/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":"2026-06-03T08:41:08Z","links":{"resolver":"https://pith.science/pith/GX6L2TS5Y4DKPKC5GJNLAAV6UF","bundle":"https://pith.science/pith/GX6L2TS5Y4DKPKC5GJNLAAV6UF/bundle.json","state":"https://pith.science/pith/GX6L2TS5Y4DKPKC5GJNLAAV6UF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GX6L2TS5Y4DKPKC5GJNLAAV6UF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GX6L2TS5Y4DKPKC5GJNLAAV6UF","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":"fd8f5b9dc86ac11676fc9ee2491832635b77f90a4a149b5af37eda5cdf50b155","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-12T02:16:20Z","title_canon_sha256":"ecd2ba7c2d33e98aa6607c11d7b7dcc672e0541a8dd0994d672c080397a3e566"},"schema_version":"1.0","source":{"id":"1812.04778","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.04778","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"arxiv_version","alias_value":"1812.04778v1","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04778","created_at":"2026-05-17T23:58:29Z"},{"alias_kind":"pith_short_12","alias_value":"GX6L2TS5Y4DK","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GX6L2TS5Y4DKPKC5","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GX6L2TS5","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:1a532f45ef7ceca21e9f1362237716631866a4acffa42ebc0b71fb3e08c2cd81","target":"graph","created_at":"2026-05-17T23:58:29Z","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"},"paper":{"abstract_excerpt":"Statistical learning on biological data can be challenging due to confounding variables in sample collection and processing. Confounders can cause models to generalize poorly and result in inaccurate prediction performance metrics if models are not validated thoroughly. In this paper, we propose methods to control for confounding factors and further improve prediction performance. We introduce OrthoNormal basis construction In cOnfounding factor Normalization (ONION) to remove confounding covariates and use the Domain-Adversarial Neural Network (DANN) to penalize models for encoding confounder","authors_text":"Adam Drake, Ajay Kannan, Marvin Bertin, Nathan Wan, Tzu-Yu Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-12T02:16:20Z","title":"Bridging the Generalization Gap: Training Robust Models on Confounded Biological Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04778","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:db4c1f4208f1c2bf62ebe1c16af217ab45405a4ffcce9a19e10551d09e12b538","target":"record","created_at":"2026-05-17T23:58:29Z","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":"fd8f5b9dc86ac11676fc9ee2491832635b77f90a4a149b5af37eda5cdf50b155","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-12T02:16:20Z","title_canon_sha256":"ecd2ba7c2d33e98aa6607c11d7b7dcc672e0541a8dd0994d672c080397a3e566"},"schema_version":"1.0","source":{"id":"1812.04778","kind":"arxiv","version":1}},"canonical_sha256":"35fcbd4e5dc706a7a85d325ab002bea1656e34fba9f2e0e0d32c9c6ae601399c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35fcbd4e5dc706a7a85d325ab002bea1656e34fba9f2e0e0d32c9c6ae601399c","first_computed_at":"2026-05-17T23:58:29.511169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:29.511169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0nc1EFZA3Ux1nmyVAQBCVuXGWQ26mypbe7iPb6mnn1MbD7RvbBI92PnmFomki06kT7eG+OCdsdYADJFfxQNiAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:29.511712Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.04778","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db4c1f4208f1c2bf62ebe1c16af217ab45405a4ffcce9a19e10551d09e12b538","sha256:1a532f45ef7ceca21e9f1362237716631866a4acffa42ebc0b71fb3e08c2cd81"],"state_sha256":"8b010f926d8ccd4c6e1719018c99f29e497506eeada53de976b51aa757904e95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kc0mdTCfb3IvpDpc/v3rNSLHMoJ4qb+3nwHUaN95KbztiWwN7KD0QTBO8RVK1pUF4YFncEcPeNbCet+/vVevDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T08:41:08.180368Z","bundle_sha256":"e6bc169257cb53e3426a0de1a74078cdc9c7fb77c083722929eae5d4e5e227ff"}}