{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ARHYHWYO3F2UZHTT24O2IK4M33","short_pith_number":"pith:ARHYHWYO","schema_version":"1.0","canonical_sha256":"044f83db0ed9754c9e73d71da42b8cdec3b07ddd51c453934d2031b3cb8a7374","source":{"kind":"arxiv","id":"1712.02560","version":4},"attestation_state":"computed","paper":{"title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kohei Watanabe, Kuniaki Saito, Tatsuya Harada, Yoshitaka Ushiku","submitted_at":"2017-12-07T10:49:33Z","abstract_excerpt":"In this work, we present a method for unsupervised domain adaptation. Many adversarial learning methods train domain classifier networks to distinguish the features as either a source or target and train a feature generator network to mimic the discriminator. Two problems exist with these methods. First, the domain classifier only tries to distinguish the features as a source or target and thus does not consider task-specific decision boundaries between classes. Therefore, a trained generator can generate ambiguous features near class boundaries. Second, these methods aim to completely match t"},"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":"1712.02560","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-07T10:49:33Z","cross_cats_sorted":[],"title_canon_sha256":"6a97a022e49fb4147f41dc0fa2ca1b044aabf41a3635588a49db2b7a3d942110","abstract_canon_sha256":"6b274b9a3a32e1928b2781e06079b9a534b3132f9bc18f851abe48c9f9333629"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:34.944287Z","signature_b64":"5H04PhPGgXXOoo0KXWeb1hybVxgvBOuwCH9E4HSqXmi9WZiFqyGHtovR5lgyYlWGwM3pYSfPkYxXugTpQ5eLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"044f83db0ed9754c9e73d71da42b8cdec3b07ddd51c453934d2031b3cb8a7374","last_reissued_at":"2026-05-18T00:19:34.943451Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:34.943451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kohei Watanabe, Kuniaki Saito, Tatsuya Harada, Yoshitaka Ushiku","submitted_at":"2017-12-07T10:49:33Z","abstract_excerpt":"In this work, we present a method for unsupervised domain adaptation. Many adversarial learning methods train domain classifier networks to distinguish the features as either a source or target and train a feature generator network to mimic the discriminator. Two problems exist with these methods. First, the domain classifier only tries to distinguish the features as a source or target and thus does not consider task-specific decision boundaries between classes. Therefore, a trained generator can generate ambiguous features near class boundaries. Second, these methods aim to completely match t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.02560","kind":"arxiv","version":4},"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":"1712.02560","created_at":"2026-05-18T00:19:34.943590+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.02560v4","created_at":"2026-05-18T00:19:34.943590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.02560","created_at":"2026-05-18T00:19:34.943590+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARHYHWYO3F2U","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARHYHWYO3F2UZHTT","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARHYHWYO","created_at":"2026-05-18T12:31:05.417338+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/ARHYHWYO3F2UZHTT24O2IK4M33","json":"https://pith.science/pith/ARHYHWYO3F2UZHTT24O2IK4M33.json","graph_json":"https://pith.science/api/pith-number/ARHYHWYO3F2UZHTT24O2IK4M33/graph.json","events_json":"https://pith.science/api/pith-number/ARHYHWYO3F2UZHTT24O2IK4M33/events.json","paper":"https://pith.science/paper/ARHYHWYO"},"agent_actions":{"view_html":"https://pith.science/pith/ARHYHWYO3F2UZHTT24O2IK4M33","download_json":"https://pith.science/pith/ARHYHWYO3F2UZHTT24O2IK4M33.json","view_paper":"https://pith.science/paper/ARHYHWYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.02560&json=true","fetch_graph":"https://pith.science/api/pith-number/ARHYHWYO3F2UZHTT24O2IK4M33/graph.json","fetch_events":"https://pith.science/api/pith-number/ARHYHWYO3F2UZHTT24O2IK4M33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARHYHWYO3F2UZHTT24O2IK4M33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARHYHWYO3F2UZHTT24O2IK4M33/action/storage_attestation","attest_author":"https://pith.science/pith/ARHYHWYO3F2UZHTT24O2IK4M33/action/author_attestation","sign_citation":"https://pith.science/pith/ARHYHWYO3F2UZHTT24O2IK4M33/action/citation_signature","submit_replication":"https://pith.science/pith/ARHYHWYO3F2UZHTT24O2IK4M33/action/replication_record"}},"created_at":"2026-05-18T00:19:34.943590+00:00","updated_at":"2026-05-18T00:19:34.943590+00:00"}