{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JCHAF324ZGQFXBWQ45SOIQ65RQ","short_pith_number":"pith:JCHAF324","schema_version":"1.0","canonical_sha256":"488e02ef5cc9a05b86d0e764e443dd8c04c83cf1ce4ade411c8c1fa03e575b85","source":{"kind":"arxiv","id":"2106.02266","version":2},"attestation_state":"computed","paper":{"title":"SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Irina Rish, Jean-Christophe Gagnon-Audet, Kartik Ahuja, Mojtaba Faramarzi, Soroosh Shahtalebi, Touraj Laleh","submitted_at":"2021-06-04T05:20:54Z","abstract_excerpt":"A major bottleneck in the real-world applications of machine learning models is their failure in generalizing to unseen domains whose data distribution is not i.i.d to the training domains. This failure often stems from learning non-generalizable features in the training domains that are spuriously correlated with the label of data. To address this shortcoming, there has been a growing surge of interest in learning good explanations that are hard to vary, which is studied under the notion of Out-of-Distribution (OOD) Generalization. The search for good explanations that are \\textit{invariant} "},"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":"2106.02266","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T05:20:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"01bfaced68da6afdfce75d2bec7a6af04220d689d8445a3a705aab9e985f95f3","abstract_canon_sha256":"c12cf87c8cb8492541c34f63ff76de4ad7a50ad50c230aa9e6133f42ae28eb65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:15.206405Z","signature_b64":"sw6IwGUNQTYYtSXroeIXVShmmYbIQoZGCNu0Q3iaZr+XkpIxG+/mtzqJbiGaFCp1K4KSAZAMbT8MGbgIt1hWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"488e02ef5cc9a05b86d0e764e443dd8c04c83cf1ce4ade411c8c1fa03e575b85","last_reissued_at":"2026-07-05T03:17:15.205917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:15.205917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Irina Rish, Jean-Christophe Gagnon-Audet, Kartik Ahuja, Mojtaba Faramarzi, Soroosh Shahtalebi, Touraj Laleh","submitted_at":"2021-06-04T05:20:54Z","abstract_excerpt":"A major bottleneck in the real-world applications of machine learning models is their failure in generalizing to unseen domains whose data distribution is not i.i.d to the training domains. This failure often stems from learning non-generalizable features in the training domains that are spuriously correlated with the label of data. To address this shortcoming, there has been a growing surge of interest in learning good explanations that are hard to vary, which is studied under the notion of Out-of-Distribution (OOD) Generalization. The search for good explanations that are \\textit{invariant} "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02266","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/2106.02266/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":"2106.02266","created_at":"2026-07-05T03:17:15.205976+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.02266v2","created_at":"2026-07-05T03:17:15.205976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02266","created_at":"2026-07-05T03:17:15.205976+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCHAF324ZGQF","created_at":"2026-07-05T03:17:15.205976+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCHAF324ZGQFXBWQ","created_at":"2026-07-05T03:17:15.205976+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCHAF324","created_at":"2026-07-05T03:17:15.205976+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24781","citing_title":"Assessing Distribution Shift in Human Activity Recognition for Domain Generalization","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23758","citing_title":"Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05025","citing_title":"Invariant Gradient Alignment for Robust Reasoning Distillation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2209.14742","citing_title":"Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JCHAF324ZGQFXBWQ45SOIQ65RQ","json":"https://pith.science/pith/JCHAF324ZGQFXBWQ45SOIQ65RQ.json","graph_json":"https://pith.science/api/pith-number/JCHAF324ZGQFXBWQ45SOIQ65RQ/graph.json","events_json":"https://pith.science/api/pith-number/JCHAF324ZGQFXBWQ45SOIQ65RQ/events.json","paper":"https://pith.science/paper/JCHAF324"},"agent_actions":{"view_html":"https://pith.science/pith/JCHAF324ZGQFXBWQ45SOIQ65RQ","download_json":"https://pith.science/pith/JCHAF324ZGQFXBWQ45SOIQ65RQ.json","view_paper":"https://pith.science/paper/JCHAF324","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.02266&json=true","fetch_graph":"https://pith.science/api/pith-number/JCHAF324ZGQFXBWQ45SOIQ65RQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JCHAF324ZGQFXBWQ45SOIQ65RQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCHAF324ZGQFXBWQ45SOIQ65RQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCHAF324ZGQFXBWQ45SOIQ65RQ/action/storage_attestation","attest_author":"https://pith.science/pith/JCHAF324ZGQFXBWQ45SOIQ65RQ/action/author_attestation","sign_citation":"https://pith.science/pith/JCHAF324ZGQFXBWQ45SOIQ65RQ/action/citation_signature","submit_replication":"https://pith.science/pith/JCHAF324ZGQFXBWQ45SOIQ65RQ/action/replication_record"}},"created_at":"2026-07-05T03:17:15.205976+00:00","updated_at":"2026-07-05T03:17:15.205976+00:00"}