{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:I74FINIUNOU53Z3CAKUUMDKJUG","short_pith_number":"pith:I74FINIU","schema_version":"1.0","canonical_sha256":"47f85435146ba9dde76202a9460d49a1b28badc57fb2e8e485266c2bfaf1738b","source":{"kind":"arxiv","id":"2006.11478","version":1},"attestation_state":"computed","paper":{"title":"Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cynthia Dwork, Frances Ding, Giovanni Parmigiani, Pragya Sur, Prasad Patil, Rachel Hong, Zhun Deng","submitted_at":"2020-06-20T02:35:03Z","abstract_excerpt":"We investigate the power of censoring techniques, first developed for learning {\\em fair representations}, to address domain generalization. We examine {\\em adversarial} censoring techniques for learning invariant representations from multiple \"studies\" (or domains), where each study is drawn according to a distribution on domains. The mapping is used at test time to classify instances from a new domain. In many contexts, such as medical forecasting, domain generalization from studies in populous areas (where data are plentiful), to geographically remote populations (for which no training data"},"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":"2006.11478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-20T02:35:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c193f2fd84f860f67f40c73fc103dfb834bd5485cde1fcb16d9e90c7bc9e27b6","abstract_canon_sha256":"427bc3ebe7675855413b6dd07a8c68d70e3c82ea5a1ef882c5511303c99b7e4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:50.576763Z","signature_b64":"WLtM+WIdmtDUvO+GgCSBVp1JxJ3v6tlPO4a+r7kGp+Jl7avH/8+kksXFV8HVxJw/vvIC/P1L18wDVzaS9Dp+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47f85435146ba9dde76202a9460d49a1b28badc57fb2e8e485266c2bfaf1738b","last_reissued_at":"2026-07-05T01:11:50.576410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:50.576410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cynthia Dwork, Frances Ding, Giovanni Parmigiani, Pragya Sur, Prasad Patil, Rachel Hong, Zhun Deng","submitted_at":"2020-06-20T02:35:03Z","abstract_excerpt":"We investigate the power of censoring techniques, first developed for learning {\\em fair representations}, to address domain generalization. We examine {\\em adversarial} censoring techniques for learning invariant representations from multiple \"studies\" (or domains), where each study is drawn according to a distribution on domains. The mapping is used at test time to classify instances from a new domain. In many contexts, such as medical forecasting, domain generalization from studies in populous areas (where data are plentiful), to geographically remote populations (for which no training data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11478","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.11478/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":"2006.11478","created_at":"2026-07-05T01:11:50.576464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.11478v1","created_at":"2026-07-05T01:11:50.576464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11478","created_at":"2026-07-05T01:11:50.576464+00:00"},{"alias_kind":"pith_short_12","alias_value":"I74FINIUNOU5","created_at":"2026-07-05T01:11:50.576464+00:00"},{"alias_kind":"pith_short_16","alias_value":"I74FINIUNOU53Z3C","created_at":"2026-07-05T01:11:50.576464+00:00"},{"alias_kind":"pith_short_8","alias_value":"I74FINIU","created_at":"2026-07-05T01:11:50.576464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26820","citing_title":"Bridge: Basis-Driven Causal Inference Marries VFMs for Domain Generalization","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I74FINIUNOU53Z3CAKUUMDKJUG","json":"https://pith.science/pith/I74FINIUNOU53Z3CAKUUMDKJUG.json","graph_json":"https://pith.science/api/pith-number/I74FINIUNOU53Z3CAKUUMDKJUG/graph.json","events_json":"https://pith.science/api/pith-number/I74FINIUNOU53Z3CAKUUMDKJUG/events.json","paper":"https://pith.science/paper/I74FINIU"},"agent_actions":{"view_html":"https://pith.science/pith/I74FINIUNOU53Z3CAKUUMDKJUG","download_json":"https://pith.science/pith/I74FINIUNOU53Z3CAKUUMDKJUG.json","view_paper":"https://pith.science/paper/I74FINIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.11478&json=true","fetch_graph":"https://pith.science/api/pith-number/I74FINIUNOU53Z3CAKUUMDKJUG/graph.json","fetch_events":"https://pith.science/api/pith-number/I74FINIUNOU53Z3CAKUUMDKJUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I74FINIUNOU53Z3CAKUUMDKJUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I74FINIUNOU53Z3CAKUUMDKJUG/action/storage_attestation","attest_author":"https://pith.science/pith/I74FINIUNOU53Z3CAKUUMDKJUG/action/author_attestation","sign_citation":"https://pith.science/pith/I74FINIUNOU53Z3CAKUUMDKJUG/action/citation_signature","submit_replication":"https://pith.science/pith/I74FINIUNOU53Z3CAKUUMDKJUG/action/replication_record"}},"created_at":"2026-07-05T01:11:50.576464+00:00","updated_at":"2026-07-05T01:11:50.576464+00:00"}