{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:NUR4ART3NC76RA67V2XVD7TNKB","short_pith_number":"pith:NUR4ART3","schema_version":"1.0","canonical_sha256":"6d23c0467b68bfe883dfaeaf51fe6d5051412439816c89c026db96449eb2ef48","source":{"kind":"arxiv","id":"1502.02791","version":2},"attestation_state":"computed","paper":{"title":"Learning Transferable Features with Deep Adaptation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Michael I. Jordan, Mingsheng Long, Yue Cao","submitted_at":"2015-02-10T06:01:30Z","abstract_excerpt":"Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers with increasing domain discrepancy. Hence, it is important to formally reduce the dataset bias and enhance the transferability in task-specific layers. In this paper, we propose a new Deep Adaptation Network (DAN) architecture, which generalizes deep convolutional neural network to the domain adaptati"},"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":"1502.02791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-02-10T06:01:30Z","cross_cats_sorted":[],"title_canon_sha256":"ef57510ef584af3cac0aeb0e1862541ff323574ac3db87f08db42b927dc8accf","abstract_canon_sha256":"6abe346f80e633e53b69e2777e36d0ed6abff8349c488370046f192d452799e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:02:07.937345Z","signature_b64":"kuldSEJ9MjX/xsdux9BiVEbtVkAgM0JrWJWOzZxPcGK4D1wEs73ab8R5TC+sRsf31UZCwtxvOikXMn05ovj5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d23c0467b68bfe883dfaeaf51fe6d5051412439816c89c026db96449eb2ef48","last_reissued_at":"2026-05-18T02:02:07.936593Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:02:07.936593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Transferable Features with Deep Adaptation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Michael I. Jordan, Mingsheng Long, Yue Cao","submitted_at":"2015-02-10T06:01:30Z","abstract_excerpt":"Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers with increasing domain discrepancy. Hence, it is important to formally reduce the dataset bias and enhance the transferability in task-specific layers. In this paper, we propose a new Deep Adaptation Network (DAN) architecture, which generalizes deep convolutional neural network to the domain adaptati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.02791","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":"1502.02791","created_at":"2026-05-18T02:02:07.936728+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.02791v2","created_at":"2026-05-18T02:02:07.936728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.02791","created_at":"2026-05-18T02:02:07.936728+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUR4ART3NC76","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUR4ART3NC76RA67","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUR4ART3","created_at":"2026-05-18T12:29:34.919912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.23651","citing_title":"How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05415","citing_title":"Learning to learn with quantum neural networks via classical neural networks","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07480","citing_title":"Remaining Useful Lifetime Prediction via Deep Domain Adaptation","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11202","citing_title":"Unsupervised Domain Adaptation via Calibrating Uncertainties","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11740","citing_title":"Environment Probing Interaction Policies","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2603.05719","citing_title":"Unsupervised domain adaptation for radioisotope identification in gamma spectroscopy","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NUR4ART3NC76RA67V2XVD7TNKB","json":"https://pith.science/pith/NUR4ART3NC76RA67V2XVD7TNKB.json","graph_json":"https://pith.science/api/pith-number/NUR4ART3NC76RA67V2XVD7TNKB/graph.json","events_json":"https://pith.science/api/pith-number/NUR4ART3NC76RA67V2XVD7TNKB/events.json","paper":"https://pith.science/paper/NUR4ART3"},"agent_actions":{"view_html":"https://pith.science/pith/NUR4ART3NC76RA67V2XVD7TNKB","download_json":"https://pith.science/pith/NUR4ART3NC76RA67V2XVD7TNKB.json","view_paper":"https://pith.science/paper/NUR4ART3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.02791&json=true","fetch_graph":"https://pith.science/api/pith-number/NUR4ART3NC76RA67V2XVD7TNKB/graph.json","fetch_events":"https://pith.science/api/pith-number/NUR4ART3NC76RA67V2XVD7TNKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUR4ART3NC76RA67V2XVD7TNKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUR4ART3NC76RA67V2XVD7TNKB/action/storage_attestation","attest_author":"https://pith.science/pith/NUR4ART3NC76RA67V2XVD7TNKB/action/author_attestation","sign_citation":"https://pith.science/pith/NUR4ART3NC76RA67V2XVD7TNKB/action/citation_signature","submit_replication":"https://pith.science/pith/NUR4ART3NC76RA67V2XVD7TNKB/action/replication_record"}},"created_at":"2026-05-18T02:02:07.936728+00:00","updated_at":"2026-05-18T02:02:07.936728+00:00"}