{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7QTKHRASZHCRJXIUOVDHH6QQB7","short_pith_number":"pith:7QTKHRAS","schema_version":"1.0","canonical_sha256":"fc26a3c412c9c514dd14754673fa100fc2ee4211aff6118f2548e91ca22c3ee5","source":{"kind":"arxiv","id":"1802.08735","version":2},"attestation_state":"computed","paper":{"title":"A DIRT-T Approach to Unsupervised Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Hirokazu Narui, Hung H. Bui, Rui Shu, Stefano Ermon","submitted_at":"2018-02-23T20:57:28Z","abstract_excerpt":"Domain adaptation refers to the problem of leveraging labeled data in a source domain to learn an accurate model in a target domain where labels are scarce or unavailable. A recent approach for finding a common representation of the two domains is via domain adversarial training (Ganin & Lempitsky, 2015), which attempts to induce a feature extractor that matches the source and target feature distributions in some feature space. However, domain adversarial training faces two critical limitations: 1) if the feature extraction function has high-capacity, then feature distribution matching is a we"},"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":"1802.08735","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-23T20:57:28Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"2fa197a2c7a484bfaba965cfeabb160235eb14052dd6cdbdec9a22025f2ac9e6","abstract_canon_sha256":"7126ee6126c6f07811a8a3bdcfe83b0c6e930030728741d0ccb8bc3f4443a275"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:44.044164Z","signature_b64":"+QG5NIQ/N6OwirU6AluR0HPl5rM1gyHt/ZabQzYIugde0ndsePPa296Ot2ulqYXDsqEsTJRsuU9hHNA1HW/TAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc26a3c412c9c514dd14754673fa100fc2ee4211aff6118f2548e91ca22c3ee5","last_reissued_at":"2026-05-18T00:20:44.043552Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:44.043552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A DIRT-T Approach to Unsupervised Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Hirokazu Narui, Hung H. Bui, Rui Shu, Stefano Ermon","submitted_at":"2018-02-23T20:57:28Z","abstract_excerpt":"Domain adaptation refers to the problem of leveraging labeled data in a source domain to learn an accurate model in a target domain where labels are scarce or unavailable. A recent approach for finding a common representation of the two domains is via domain adversarial training (Ganin & Lempitsky, 2015), which attempts to induce a feature extractor that matches the source and target feature distributions in some feature space. However, domain adversarial training faces two critical limitations: 1) if the feature extraction function has high-capacity, then feature distribution matching is a we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08735","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":""},"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":"1802.08735","created_at":"2026-05-18T00:20:44.043640+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08735v2","created_at":"2026-05-18T00:20:44.043640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08735","created_at":"2026-05-18T00:20:44.043640+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QTKHRASZHCR","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QTKHRASZHCRJXIU","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QTKHRAS","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.03389","citing_title":"Blending-target Domain Adaptation by Adversarial Meta-Adaptation Networks","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11202","citing_title":"Unsupervised Domain Adaptation via Calibrating Uncertainties","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03462","citing_title":"From Muscle Bursts to Motor Intent: Self-Supervised Token Modeling for Heterogeneous EMG","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03462","citing_title":"From Muscle Bursts to Motor Intent: Self-Supervised Token Modeling for Heterogeneous EMG","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23790","citing_title":"A General Representation-Based Approach to Multi-Source Domain Adaptation","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05710","citing_title":"On the Blessing of Pre-training in Weak-to-Strong Generalization","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06736","citing_title":"STDA-Net: Spectrogram-Based Domain Adaptation for cross-dataset Sleep Stage Classification","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QTKHRASZHCRJXIUOVDHH6QQB7","json":"https://pith.science/pith/7QTKHRASZHCRJXIUOVDHH6QQB7.json","graph_json":"https://pith.science/api/pith-number/7QTKHRASZHCRJXIUOVDHH6QQB7/graph.json","events_json":"https://pith.science/api/pith-number/7QTKHRASZHCRJXIUOVDHH6QQB7/events.json","paper":"https://pith.science/paper/7QTKHRAS"},"agent_actions":{"view_html":"https://pith.science/pith/7QTKHRASZHCRJXIUOVDHH6QQB7","download_json":"https://pith.science/pith/7QTKHRASZHCRJXIUOVDHH6QQB7.json","view_paper":"https://pith.science/paper/7QTKHRAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08735&json=true","fetch_graph":"https://pith.science/api/pith-number/7QTKHRASZHCRJXIUOVDHH6QQB7/graph.json","fetch_events":"https://pith.science/api/pith-number/7QTKHRASZHCRJXIUOVDHH6QQB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QTKHRASZHCRJXIUOVDHH6QQB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QTKHRASZHCRJXIUOVDHH6QQB7/action/storage_attestation","attest_author":"https://pith.science/pith/7QTKHRASZHCRJXIUOVDHH6QQB7/action/author_attestation","sign_citation":"https://pith.science/pith/7QTKHRASZHCRJXIUOVDHH6QQB7/action/citation_signature","submit_replication":"https://pith.science/pith/7QTKHRASZHCRJXIUOVDHH6QQB7/action/replication_record"}},"created_at":"2026-05-18T00:20:44.043640+00:00","updated_at":"2026-05-18T00:20:44.043640+00:00"}