{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OE3CINHD32FLRDGCZAJJ5E6VBZ","short_pith_number":"pith:OE3CINHD","schema_version":"1.0","canonical_sha256":"71362434e3de8ab88cc2c8129e93d50e79f8042e89e09960ec284e481b8a9516","source":{"kind":"arxiv","id":"1909.05288","version":4},"attestation_state":"computed","paper":{"title":"Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jingjing Liu, Lawrence Carin, Shuyang Dai, Yizhe Zhang, Yu Cheng, Zhe Gan","submitted_at":"2019-09-11T18:32:00Z","abstract_excerpt":"Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order to learn a better alignment between the two domains. This minimization can be achieved via a domain classifier to detect target-domain features that are divergent from source-domain features. However, by optimizing via such domain classification discrepancy, ambiguous target samples that are not smoothly distributed on the low-dimensional data manifold are often missed. To solve this issue, we propose a novel Contra"},"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":"1909.05288","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-11T18:32:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4ff9d19980cfed83c9c95aae529ffb26a9a9abfe5b30658c4bddacdd5058e0ad","abstract_canon_sha256":"9705448a5adaac7e9a6604fccd8cd7f9c654d4fc9077cceb696266132c1dbbb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:55.629954Z","signature_b64":"4AT2H6+pNibDWHjKvXdlAew6imDPwjI2vpJ6Nc+HPASt3SQARZ0ARopEh8+vFz041lISab/B1Sg+0YiSp1ZuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71362434e3de8ab88cc2c8129e93d50e79f8042e89e09960ec284e481b8a9516","last_reissued_at":"2026-07-05T01:40:55.629529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:55.629529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jingjing Liu, Lawrence Carin, Shuyang Dai, Yizhe Zhang, Yu Cheng, Zhe Gan","submitted_at":"2019-09-11T18:32:00Z","abstract_excerpt":"Recent unsupervised approaches to domain adaptation primarily focus on minimizing the gap between the source and the target domains through refining the feature generator, in order to learn a better alignment between the two domains. This minimization can be achieved via a domain classifier to detect target-domain features that are divergent from source-domain features. However, by optimizing via such domain classification discrepancy, ambiguous target samples that are not smoothly distributed on the low-dimensional data manifold are often missed. To solve this issue, we propose a novel Contra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.05288","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.05288/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":"1909.05288","created_at":"2026-07-05T01:40:55.629591+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.05288v4","created_at":"2026-07-05T01:40:55.629591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.05288","created_at":"2026-07-05T01:40:55.629591+00:00"},{"alias_kind":"pith_short_12","alias_value":"OE3CINHD32FL","created_at":"2026-07-05T01:40:55.629591+00:00"},{"alias_kind":"pith_short_16","alias_value":"OE3CINHD32FLRDGC","created_at":"2026-07-05T01:40:55.629591+00:00"},{"alias_kind":"pith_short_8","alias_value":"OE3CINHD","created_at":"2026-07-05T01:40:55.629591+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/OE3CINHD32FLRDGCZAJJ5E6VBZ","json":"https://pith.science/pith/OE3CINHD32FLRDGCZAJJ5E6VBZ.json","graph_json":"https://pith.science/api/pith-number/OE3CINHD32FLRDGCZAJJ5E6VBZ/graph.json","events_json":"https://pith.science/api/pith-number/OE3CINHD32FLRDGCZAJJ5E6VBZ/events.json","paper":"https://pith.science/paper/OE3CINHD"},"agent_actions":{"view_html":"https://pith.science/pith/OE3CINHD32FLRDGCZAJJ5E6VBZ","download_json":"https://pith.science/pith/OE3CINHD32FLRDGCZAJJ5E6VBZ.json","view_paper":"https://pith.science/paper/OE3CINHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.05288&json=true","fetch_graph":"https://pith.science/api/pith-number/OE3CINHD32FLRDGCZAJJ5E6VBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/OE3CINHD32FLRDGCZAJJ5E6VBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OE3CINHD32FLRDGCZAJJ5E6VBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OE3CINHD32FLRDGCZAJJ5E6VBZ/action/storage_attestation","attest_author":"https://pith.science/pith/OE3CINHD32FLRDGCZAJJ5E6VBZ/action/author_attestation","sign_citation":"https://pith.science/pith/OE3CINHD32FLRDGCZAJJ5E6VBZ/action/citation_signature","submit_replication":"https://pith.science/pith/OE3CINHD32FLRDGCZAJJ5E6VBZ/action/replication_record"}},"created_at":"2026-07-05T01:40:55.629591+00:00","updated_at":"2026-07-05T01:40:55.629591+00:00"}