{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:67LEJDLSXQFVURLDTOYTCRWULZ","short_pith_number":"pith:67LEJDLS","schema_version":"1.0","canonical_sha256":"f7d6448d72bc0b5a45639bb13146d45e66ed4300c5eb990d342fafec7dd9291d","source":{"kind":"arxiv","id":"2202.03881","version":3},"attestation_state":"computed","paper":{"title":"Robust Hybrid Learning With Expert Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antoine Wehenkel, Gilles Louppe, Guillermo Sapiro, Hsiang Hsu, Jens Behrmann, J\\\"orn-Henrik Jacobsen","submitted_at":"2022-02-08T14:11:04Z","abstract_excerpt":"Hybrid modelling reduces the misspecification of expert models by combining them with machine learning (ML) components learned from data. Similarly to many ML algorithms, hybrid model performance guarantees are limited to the training distribution. Leveraging the insight that the expert model is usually valid even outside the training domain, we overcome this limitation by introducing a hybrid data augmentation strategy termed \\textit{expert augmentation}. Based on a probabilistic formalization of hybrid modelling, we demonstrate that expert augmentation, which can be incorporated into existin"},"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":"2202.03881","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-08T14:11:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"458ff37bdc2181f5f8c1d30b5a81a1e00962dd3ec2a4868cff76e3350c83b313","abstract_canon_sha256":"3b72b5d7026a430946b57742f8b1a6c9de5c12b544e865a412bdc44b3cd5f210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:11.126644Z","signature_b64":"fr5/AGSPo0ZGryadc2kKaTmzHNiespTmk0s0Qbi8wOk5edrm0AOcrqJE98gg/8SRkOQbGcQFeAAgDcOu4lQsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7d6448d72bc0b5a45639bb13146d45e66ed4300c5eb990d342fafec7dd9291d","last_reissued_at":"2026-07-05T06:00:11.125915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:11.125915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Hybrid Learning With Expert Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antoine Wehenkel, Gilles Louppe, Guillermo Sapiro, Hsiang Hsu, Jens Behrmann, J\\\"orn-Henrik Jacobsen","submitted_at":"2022-02-08T14:11:04Z","abstract_excerpt":"Hybrid modelling reduces the misspecification of expert models by combining them with machine learning (ML) components learned from data. Similarly to many ML algorithms, hybrid model performance guarantees are limited to the training distribution. Leveraging the insight that the expert model is usually valid even outside the training domain, we overcome this limitation by introducing a hybrid data augmentation strategy termed \\textit{expert augmentation}. Based on a probabilistic formalization of hybrid modelling, we demonstrate that expert augmentation, which can be incorporated into existin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03881","kind":"arxiv","version":3},"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/2202.03881/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":"2202.03881","created_at":"2026-07-05T06:00:11.125998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03881v3","created_at":"2026-07-05T06:00:11.125998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03881","created_at":"2026-07-05T06:00:11.125998+00:00"},{"alias_kind":"pith_short_12","alias_value":"67LEJDLSXQFV","created_at":"2026-07-05T06:00:11.125998+00:00"},{"alias_kind":"pith_short_16","alias_value":"67LEJDLSXQFVURLD","created_at":"2026-07-05T06:00:11.125998+00:00"},{"alias_kind":"pith_short_8","alias_value":"67LEJDLS","created_at":"2026-07-05T06:00:11.125998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25923","citing_title":"$\\text{DT}^2$: Decision-Targeted Digital Twins","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18154","citing_title":"Learning Cardiac Electrophysiology Digital Twins Through Agentic Discovery of Hybrid Structure","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67LEJDLSXQFVURLDTOYTCRWULZ","json":"https://pith.science/pith/67LEJDLSXQFVURLDTOYTCRWULZ.json","graph_json":"https://pith.science/api/pith-number/67LEJDLSXQFVURLDTOYTCRWULZ/graph.json","events_json":"https://pith.science/api/pith-number/67LEJDLSXQFVURLDTOYTCRWULZ/events.json","paper":"https://pith.science/paper/67LEJDLS"},"agent_actions":{"view_html":"https://pith.science/pith/67LEJDLSXQFVURLDTOYTCRWULZ","download_json":"https://pith.science/pith/67LEJDLSXQFVURLDTOYTCRWULZ.json","view_paper":"https://pith.science/paper/67LEJDLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03881&json=true","fetch_graph":"https://pith.science/api/pith-number/67LEJDLSXQFVURLDTOYTCRWULZ/graph.json","fetch_events":"https://pith.science/api/pith-number/67LEJDLSXQFVURLDTOYTCRWULZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67LEJDLSXQFVURLDTOYTCRWULZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67LEJDLSXQFVURLDTOYTCRWULZ/action/storage_attestation","attest_author":"https://pith.science/pith/67LEJDLSXQFVURLDTOYTCRWULZ/action/author_attestation","sign_citation":"https://pith.science/pith/67LEJDLSXQFVURLDTOYTCRWULZ/action/citation_signature","submit_replication":"https://pith.science/pith/67LEJDLSXQFVURLDTOYTCRWULZ/action/replication_record"}},"created_at":"2026-07-05T06:00:11.125998+00:00","updated_at":"2026-07-05T06:00:11.125998+00:00"}