{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZBIF5MMNQ33PZPYYIRV6XG4JF6","short_pith_number":"pith:ZBIF5MMN","schema_version":"1.0","canonical_sha256":"c8505eb18d86f6fcbf18446beb9b892fa83bc7ba3ad13baa7dfc14214b98e74e","source":{"kind":"arxiv","id":"2007.14612","version":2},"attestation_state":"computed","paper":{"title":"Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Yuan, Feng Liu, Guangquan Zhang, Jie Lu, Yiyang Zhang, Zhen Fang","submitted_at":"2020-07-29T05:31:58Z","abstract_excerpt":"In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collect fully-true-label data in a source domain given a limited budget. To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA). The key benefit is that it is much less costly to collect co"},"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":"2007.14612","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-29T05:31:58Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b622d24811976302456a040bab2c662675c25aa901dfcc74c02c04bc9a29e2b2","abstract_canon_sha256":"f4d9a9994148fd788a21bc4198d14975d73d90a33937ca889e054625b30702cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:29.154474Z","signature_b64":"c8uQpnJMCjsl3vBm58w2LQNjFyGIbHxglfbxyn/1Havm3a21l/u2zcccJvhaFDLs2bfG3r0OHDckxf+HKCQrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8505eb18d86f6fcbf18446beb9b892fa83bc7ba3ad13baa7dfc14214b98e74e","last_reissued_at":"2026-07-05T02:20:29.154110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:29.154110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Yuan, Feng Liu, Guangquan Zhang, Jie Lu, Yiyang Zhang, Zhen Fang","submitted_at":"2020-07-29T05:31:58Z","abstract_excerpt":"In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collect fully-true-label data in a source domain given a limited budget. To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA). The key benefit is that it is much less costly to collect co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14612","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.14612/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":"2007.14612","created_at":"2026-07-05T02:20:29.154173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.14612v2","created_at":"2026-07-05T02:20:29.154173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14612","created_at":"2026-07-05T02:20:29.154173+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBIF5MMNQ33P","created_at":"2026-07-05T02:20:29.154173+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBIF5MMNQ33PZPYY","created_at":"2026-07-05T02:20:29.154173+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBIF5MMN","created_at":"2026-07-05T02:20:29.154173+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15356","citing_title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZBIF5MMNQ33PZPYYIRV6XG4JF6","json":"https://pith.science/pith/ZBIF5MMNQ33PZPYYIRV6XG4JF6.json","graph_json":"https://pith.science/api/pith-number/ZBIF5MMNQ33PZPYYIRV6XG4JF6/graph.json","events_json":"https://pith.science/api/pith-number/ZBIF5MMNQ33PZPYYIRV6XG4JF6/events.json","paper":"https://pith.science/paper/ZBIF5MMN"},"agent_actions":{"view_html":"https://pith.science/pith/ZBIF5MMNQ33PZPYYIRV6XG4JF6","download_json":"https://pith.science/pith/ZBIF5MMNQ33PZPYYIRV6XG4JF6.json","view_paper":"https://pith.science/paper/ZBIF5MMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.14612&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBIF5MMNQ33PZPYYIRV6XG4JF6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBIF5MMNQ33PZPYYIRV6XG4JF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBIF5MMNQ33PZPYYIRV6XG4JF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBIF5MMNQ33PZPYYIRV6XG4JF6/action/storage_attestation","attest_author":"https://pith.science/pith/ZBIF5MMNQ33PZPYYIRV6XG4JF6/action/author_attestation","sign_citation":"https://pith.science/pith/ZBIF5MMNQ33PZPYYIRV6XG4JF6/action/citation_signature","submit_replication":"https://pith.science/pith/ZBIF5MMNQ33PZPYYIRV6XG4JF6/action/replication_record"}},"created_at":"2026-07-05T02:20:29.154173+00:00","updated_at":"2026-07-05T02:20:29.154173+00:00"}