{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DAEYTKSHEZS3GY7G4YIB22H74T","short_pith_number":"pith:DAEYTKSH","schema_version":"1.0","canonical_sha256":"180989aa472665b363e6e6101d68ffe4c9a45c2c1879e55d0413eead59b6c8fc","source":{"kind":"arxiv","id":"2010.07591","version":1},"attestation_state":"computed","paper":{"title":"Respecting Domain Relations: Hypothesis Invariance for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jan van Gemert, Marco Loog, Ziqi Wang","submitted_at":"2020-10-15T08:26:08Z","abstract_excerpt":"In domain generalization, multiple labeled non-independent and non-identically distributed source domains are available during training while neither the data nor the labels of target domains are. Currently, learning so-called domain invariant representations (DIRs) is the prevalent approach to domain generalization. In this work, we define DIRs employed by existing works in probabilistic terms and show that by learning DIRs, overly strict requirements are imposed concerning the invariance. Particularly, DIRs aim to perfectly align representations of different domains, i.e. their input distrib"},"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":"2010.07591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-15T08:26:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"04110fd7746609bd795b07b4f4f66f01acc2a6acf784c6a6eeb793a190f18097","abstract_canon_sha256":"27f45f36c03a509237c9e3fe2ce52a0c5acaceee20f61b809b78954c4182304c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:18.675602Z","signature_b64":"vM4dlG3SXTgqzOZzbeTRmQDCvns3//NJkEM0bUf4Da/n4SHZqMCjFpurvQnEPKJcD0Gh4vzhLBCKEiFdSV1SAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"180989aa472665b363e6e6101d68ffe4c9a45c2c1879e55d0413eead59b6c8fc","last_reissued_at":"2026-07-05T01:43:18.675218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:18.675218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Respecting Domain Relations: Hypothesis Invariance for Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jan van Gemert, Marco Loog, Ziqi Wang","submitted_at":"2020-10-15T08:26:08Z","abstract_excerpt":"In domain generalization, multiple labeled non-independent and non-identically distributed source domains are available during training while neither the data nor the labels of target domains are. Currently, learning so-called domain invariant representations (DIRs) is the prevalent approach to domain generalization. In this work, we define DIRs employed by existing works in probabilistic terms and show that by learning DIRs, overly strict requirements are imposed concerning the invariance. Particularly, DIRs aim to perfectly align representations of different domains, i.e. their input distrib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.07591","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/2010.07591/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":"2010.07591","created_at":"2026-07-05T01:43:18.675281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.07591v1","created_at":"2026-07-05T01:43:18.675281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.07591","created_at":"2026-07-05T01:43:18.675281+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAEYTKSHEZS3","created_at":"2026-07-05T01:43:18.675281+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAEYTKSHEZS3GY7G","created_at":"2026-07-05T01:43:18.675281+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAEYTKSH","created_at":"2026-07-05T01:43:18.675281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.06881","citing_title":"NeuRN: Neuro-inspired Domain Generalization for Image Classification","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DAEYTKSHEZS3GY7G4YIB22H74T","json":"https://pith.science/pith/DAEYTKSHEZS3GY7G4YIB22H74T.json","graph_json":"https://pith.science/api/pith-number/DAEYTKSHEZS3GY7G4YIB22H74T/graph.json","events_json":"https://pith.science/api/pith-number/DAEYTKSHEZS3GY7G4YIB22H74T/events.json","paper":"https://pith.science/paper/DAEYTKSH"},"agent_actions":{"view_html":"https://pith.science/pith/DAEYTKSHEZS3GY7G4YIB22H74T","download_json":"https://pith.science/pith/DAEYTKSHEZS3GY7G4YIB22H74T.json","view_paper":"https://pith.science/paper/DAEYTKSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.07591&json=true","fetch_graph":"https://pith.science/api/pith-number/DAEYTKSHEZS3GY7G4YIB22H74T/graph.json","fetch_events":"https://pith.science/api/pith-number/DAEYTKSHEZS3GY7G4YIB22H74T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAEYTKSHEZS3GY7G4YIB22H74T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAEYTKSHEZS3GY7G4YIB22H74T/action/storage_attestation","attest_author":"https://pith.science/pith/DAEYTKSHEZS3GY7G4YIB22H74T/action/author_attestation","sign_citation":"https://pith.science/pith/DAEYTKSHEZS3GY7G4YIB22H74T/action/citation_signature","submit_replication":"https://pith.science/pith/DAEYTKSHEZS3GY7G4YIB22H74T/action/replication_record"}},"created_at":"2026-07-05T01:43:18.675281+00:00","updated_at":"2026-07-05T01:43:18.675281+00:00"}