{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3ORP3U67CADMONC2CVN5HCMF2P","short_pith_number":"pith:3ORP3U67","schema_version":"1.0","canonical_sha256":"dba2fdd3df1006c7345a155bd38985d3c550237761046198b3d726b95276478a","source":{"kind":"arxiv","id":"2407.18428","version":1},"attestation_state":"computed","paper":{"title":"Weighted Risk Invariance: Domain Generalization under Invariant Feature Shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Anqi Liu, Gina Wong, Joshua Gleason, Rama Chellappa, Yoav Wald","submitted_at":"2024-07-25T23:27:10Z","abstract_excerpt":"Learning models whose predictions are invariant under multiple environments is a promising approach for out-of-distribution generalization. Such models are trained to extract features $X_{\\text{inv}}$ where the conditional distribution $Y \\mid X_{\\text{inv}}$ of the label given the extracted features does not change across environments. Invariant models are also supposed to generalize to shifts in the marginal distribution $p(X_{\\text{inv}})$ of the extracted features $X_{\\text{inv}}$, a type of shift we call an $\\textit{invariant covariate shift}$. However, we show that proposed methods for l"},"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":"2407.18428","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-25T23:27:10Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"fa0d4c3b7b06499564e4b50eeb4b94d5497d9756fa085afd6ab99dd07baefaf0","abstract_canon_sha256":"0545265caf64bb40a25a57bf45cee7b9c57209232fa17dbb5aa6e214fa26d18f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:05:39.878835Z","signature_b64":"4lwB5hJ7nyNw4HcXwxtd/43FlZ8u8KSpR0qlooNwFF09xSk79cgi+caPWqlwzL75uq/FrdxrB0Kyw2WIzkpkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dba2fdd3df1006c7345a155bd38985d3c550237761046198b3d726b95276478a","last_reissued_at":"2026-06-03T02:05:39.878344Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:05:39.878344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weighted Risk Invariance: Domain Generalization under Invariant Feature Shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Anqi Liu, Gina Wong, Joshua Gleason, Rama Chellappa, Yoav Wald","submitted_at":"2024-07-25T23:27:10Z","abstract_excerpt":"Learning models whose predictions are invariant under multiple environments is a promising approach for out-of-distribution generalization. Such models are trained to extract features $X_{\\text{inv}}$ where the conditional distribution $Y \\mid X_{\\text{inv}}$ of the label given the extracted features does not change across environments. Invariant models are also supposed to generalize to shifts in the marginal distribution $p(X_{\\text{inv}})$ of the extracted features $X_{\\text{inv}}$, a type of shift we call an $\\textit{invariant covariate shift}$. However, we show that proposed methods for l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18428","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/2407.18428/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":"2407.18428","created_at":"2026-06-03T02:05:39.878402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18428v1","created_at":"2026-06-03T02:05:39.878402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18428","created_at":"2026-06-03T02:05:39.878402+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ORP3U67CADM","created_at":"2026-06-03T02:05:39.878402+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ORP3U67CADMONC2","created_at":"2026-06-03T02:05:39.878402+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ORP3U67","created_at":"2026-06-03T02:05:39.878402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.18579","citing_title":"S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18579","citing_title":"S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ORP3U67CADMONC2CVN5HCMF2P","json":"https://pith.science/pith/3ORP3U67CADMONC2CVN5HCMF2P.json","graph_json":"https://pith.science/api/pith-number/3ORP3U67CADMONC2CVN5HCMF2P/graph.json","events_json":"https://pith.science/api/pith-number/3ORP3U67CADMONC2CVN5HCMF2P/events.json","paper":"https://pith.science/paper/3ORP3U67"},"agent_actions":{"view_html":"https://pith.science/pith/3ORP3U67CADMONC2CVN5HCMF2P","download_json":"https://pith.science/pith/3ORP3U67CADMONC2CVN5HCMF2P.json","view_paper":"https://pith.science/paper/3ORP3U67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18428&json=true","fetch_graph":"https://pith.science/api/pith-number/3ORP3U67CADMONC2CVN5HCMF2P/graph.json","fetch_events":"https://pith.science/api/pith-number/3ORP3U67CADMONC2CVN5HCMF2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ORP3U67CADMONC2CVN5HCMF2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ORP3U67CADMONC2CVN5HCMF2P/action/storage_attestation","attest_author":"https://pith.science/pith/3ORP3U67CADMONC2CVN5HCMF2P/action/author_attestation","sign_citation":"https://pith.science/pith/3ORP3U67CADMONC2CVN5HCMF2P/action/citation_signature","submit_replication":"https://pith.science/pith/3ORP3U67CADMONC2CVN5HCMF2P/action/replication_record"}},"created_at":"2026-06-03T02:05:39.878402+00:00","updated_at":"2026-06-03T02:05:39.878402+00:00"}