{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DN6EC76HQAJN5XWO3J7JVLCJTP","short_pith_number":"pith:DN6EC76H","schema_version":"1.0","canonical_sha256":"1b7c417fc78012dedeceda7e9aac499bf38519d70c76fa64180d145709d9da74","source":{"kind":"arxiv","id":"2103.10919","version":2},"attestation_state":"computed","paper":{"title":"Robustness via Cross-Domain Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Sax, Amir Zamir, O\\u{g}uzhan Fatih Kar, Teresa Yeo","submitted_at":"2021-03-19T17:28:03Z","abstract_excerpt":"We present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues (called 'middle domains') and ensembling them into one strong prediction. The premise of the idea is that predictions made via different cues respond differently to a distribution shift, hence one should be able to merge them into one robust final prediction. We perform the merging in a straightforward but principled manner based on the uncertainty associated with each prediction. The evaluations are perform"},"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":"2103.10919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T17:28:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ca847081034875c9a11fd01846bd9fbc95207bb419fa56fa7692a6997a4219c0","abstract_canon_sha256":"ebbd773934bddbc9d7e167bec67a0f3728dd86cc0ad1bfe864d23b50cf277a74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:12.198250Z","signature_b64":"f9BAgOUKfrhUs++rKF4EmHzEi15Y8MTALGxXMiqKCCfADk2eHJ7rNps3vn263FTmc0aw4dp1pdMcnoHAFbR7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b7c417fc78012dedeceda7e9aac499bf38519d70c76fa64180d145709d9da74","last_reissued_at":"2026-07-05T03:11:12.197825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:12.197825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustness via Cross-Domain Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Sax, Amir Zamir, O\\u{g}uzhan Fatih Kar, Teresa Yeo","submitted_at":"2021-03-19T17:28:03Z","abstract_excerpt":"We present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues (called 'middle domains') and ensembling them into one strong prediction. The premise of the idea is that predictions made via different cues respond differently to a distribution shift, hence one should be able to merge them into one robust final prediction. We perform the merging in a straightforward but principled manner based on the uncertainty associated with each prediction. The evaluations are perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10919","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/2103.10919/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":"2103.10919","created_at":"2026-07-05T03:11:12.197884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.10919v2","created_at":"2026-07-05T03:11:12.197884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10919","created_at":"2026-07-05T03:11:12.197884+00:00"},{"alias_kind":"pith_short_12","alias_value":"DN6EC76HQAJN","created_at":"2026-07-05T03:11:12.197884+00:00"},{"alias_kind":"pith_short_16","alias_value":"DN6EC76HQAJN5XWO","created_at":"2026-07-05T03:11:12.197884+00:00"},{"alias_kind":"pith_short_8","alias_value":"DN6EC76H","created_at":"2026-07-05T03:11:12.197884+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/DN6EC76HQAJN5XWO3J7JVLCJTP","json":"https://pith.science/pith/DN6EC76HQAJN5XWO3J7JVLCJTP.json","graph_json":"https://pith.science/api/pith-number/DN6EC76HQAJN5XWO3J7JVLCJTP/graph.json","events_json":"https://pith.science/api/pith-number/DN6EC76HQAJN5XWO3J7JVLCJTP/events.json","paper":"https://pith.science/paper/DN6EC76H"},"agent_actions":{"view_html":"https://pith.science/pith/DN6EC76HQAJN5XWO3J7JVLCJTP","download_json":"https://pith.science/pith/DN6EC76HQAJN5XWO3J7JVLCJTP.json","view_paper":"https://pith.science/paper/DN6EC76H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.10919&json=true","fetch_graph":"https://pith.science/api/pith-number/DN6EC76HQAJN5XWO3J7JVLCJTP/graph.json","fetch_events":"https://pith.science/api/pith-number/DN6EC76HQAJN5XWO3J7JVLCJTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DN6EC76HQAJN5XWO3J7JVLCJTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DN6EC76HQAJN5XWO3J7JVLCJTP/action/storage_attestation","attest_author":"https://pith.science/pith/DN6EC76HQAJN5XWO3J7JVLCJTP/action/author_attestation","sign_citation":"https://pith.science/pith/DN6EC76HQAJN5XWO3J7JVLCJTP/action/citation_signature","submit_replication":"https://pith.science/pith/DN6EC76HQAJN5XWO3J7JVLCJTP/action/replication_record"}},"created_at":"2026-07-05T03:11:12.197884+00:00","updated_at":"2026-07-05T03:11:12.197884+00:00"}