{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NO5SJFBXNSITPSJRQVF62WXTWU","short_pith_number":"pith:NO5SJFBX","schema_version":"1.0","canonical_sha256":"6bbb2494376c9137c931854bed5af3b510900ade2e64e3e22d6e7f10f42baeed","source":{"kind":"arxiv","id":"1702.05993","version":1},"attestation_state":"computed","paper":{"title":"An Extended Framework for Marginalized Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Boris Chidlovski, Gabriela Csurka, Sophia Michel, Stephane Clinchant","submitted_at":"2017-02-20T15:00:13Z","abstract_excerpt":"We propose an extended framework for marginalized domain adaptation, aimed at addressing unsupervised, supervised and semi-supervised scenarios. We argue that the denoising principle should be extended to explicitly promote domain-invariant features as well as help the classification task. Therefore we propose to jointly learn the data auto-encoders and the target classifiers. First, in order to make the denoised features domain-invariant, we propose a domain regularization that may be either a domain prediction loss or a maximum mean discrepancy between the source and target data. The noise m"},"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":"1702.05993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-20T15:00:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53f1eac716e9bc7891f7960c485a3c1acc4b8920c03c93252e2c52346690abea","abstract_canon_sha256":"b4beb08eb4ccd25a73bdc0ff583deed84fd8d34aed89b864dd892ff3e07b43e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:24.633295Z","signature_b64":"I75FRy8JxnmOe2in7f0OkU5owb74vnPPkS5EcNG9AvWL9hHLuxIFWApurlq4La8TB5bG0JDUGUBcXyGFrj0OBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bbb2494376c9137c931854bed5af3b510900ade2e64e3e22d6e7f10f42baeed","last_reissued_at":"2026-05-18T00:50:24.632538Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:24.632538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Extended Framework for Marginalized Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Boris Chidlovski, Gabriela Csurka, Sophia Michel, Stephane Clinchant","submitted_at":"2017-02-20T15:00:13Z","abstract_excerpt":"We propose an extended framework for marginalized domain adaptation, aimed at addressing unsupervised, supervised and semi-supervised scenarios. We argue that the denoising principle should be extended to explicitly promote domain-invariant features as well as help the classification task. Therefore we propose to jointly learn the data auto-encoders and the target classifiers. First, in order to make the denoised features domain-invariant, we propose a domain regularization that may be either a domain prediction loss or a maximum mean discrepancy between the source and target data. The noise m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.05993","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":""},"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":"1702.05993","created_at":"2026-05-18T00:50:24.632657+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.05993v1","created_at":"2026-05-18T00:50:24.632657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.05993","created_at":"2026-05-18T00:50:24.632657+00:00"},{"alias_kind":"pith_short_12","alias_value":"NO5SJFBXNSIT","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NO5SJFBXNSITPSJR","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NO5SJFBX","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NO5SJFBXNSITPSJRQVF62WXTWU","json":"https://pith.science/pith/NO5SJFBXNSITPSJRQVF62WXTWU.json","graph_json":"https://pith.science/api/pith-number/NO5SJFBXNSITPSJRQVF62WXTWU/graph.json","events_json":"https://pith.science/api/pith-number/NO5SJFBXNSITPSJRQVF62WXTWU/events.json","paper":"https://pith.science/paper/NO5SJFBX"},"agent_actions":{"view_html":"https://pith.science/pith/NO5SJFBXNSITPSJRQVF62WXTWU","download_json":"https://pith.science/pith/NO5SJFBXNSITPSJRQVF62WXTWU.json","view_paper":"https://pith.science/paper/NO5SJFBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.05993&json=true","fetch_graph":"https://pith.science/api/pith-number/NO5SJFBXNSITPSJRQVF62WXTWU/graph.json","fetch_events":"https://pith.science/api/pith-number/NO5SJFBXNSITPSJRQVF62WXTWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NO5SJFBXNSITPSJRQVF62WXTWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NO5SJFBXNSITPSJRQVF62WXTWU/action/storage_attestation","attest_author":"https://pith.science/pith/NO5SJFBXNSITPSJRQVF62WXTWU/action/author_attestation","sign_citation":"https://pith.science/pith/NO5SJFBXNSITPSJRQVF62WXTWU/action/citation_signature","submit_replication":"https://pith.science/pith/NO5SJFBXNSITPSJRQVF62WXTWU/action/replication_record"}},"created_at":"2026-05-18T00:50:24.632657+00:00","updated_at":"2026-05-18T00:50:24.632657+00:00"}