{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CP3XNWGUR7V44ZGRRLG5NWFRGE","short_pith_number":"pith:CP3XNWGU","schema_version":"1.0","canonical_sha256":"13f776d8d48febce64d18acdd6d8b131057f32dd80744cb351246011104e35f0","source":{"kind":"arxiv","id":"2305.02693","version":3},"attestation_state":"computed","paper":{"title":"Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Zhu, Wenkai Chen, Xinyang Huang","submitted_at":"2023-05-04T10:09:30Z","abstract_excerpt":"In semi-supervised domain adaptation (SSDA), a few labeled target samples of each class help the model to transfer knowledge representation from the fully labeled source domain to the target domain. Many existing methods ignore the benefits of making full use of the labeled target samples from multi-level. To make better use of this additional data, we propose a novel Prototype-based Multi-level Learning (ProML) framework to better tap the potential of labeled target samples. To achieve intra-domain adaptation, we first introduce a pseudo-label aggregation based on the intra-domain optimal tra"},"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":"2305.02693","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T10:09:30Z","cross_cats_sorted":[],"title_canon_sha256":"73470970b236b327a3f4def540d263ab8eb6a35ad8c9780ce31567cae3cd7b2d","abstract_canon_sha256":"6441a19a375f2e134ef2ed0b78d3b8adb3d708d31ba9bc3a2207f44f9e437960"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:04.322212Z","signature_b64":"jX95LHizwL2MXWrGTAxHcAV+b9EtKPhygECjQJMf9g/VWL2STz1h5eaxxiNUgxbDh/haHNNTzlqg/XLmEBbfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13f776d8d48febce64d18acdd6d8b131057f32dd80744cb351246011104e35f0","last_reissued_at":"2026-07-05T07:27:04.321719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:04.321719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuang Zhu, Wenkai Chen, Xinyang Huang","submitted_at":"2023-05-04T10:09:30Z","abstract_excerpt":"In semi-supervised domain adaptation (SSDA), a few labeled target samples of each class help the model to transfer knowledge representation from the fully labeled source domain to the target domain. Many existing methods ignore the benefits of making full use of the labeled target samples from multi-level. To make better use of this additional data, we propose a novel Prototype-based Multi-level Learning (ProML) framework to better tap the potential of labeled target samples. To achieve intra-domain adaptation, we first introduce a pseudo-label aggregation based on the intra-domain optimal tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02693","kind":"arxiv","version":3},"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/2305.02693/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":"2305.02693","created_at":"2026-07-05T07:27:04.321786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.02693v3","created_at":"2026-07-05T07:27:04.321786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02693","created_at":"2026-07-05T07:27:04.321786+00:00"},{"alias_kind":"pith_short_12","alias_value":"CP3XNWGUR7V4","created_at":"2026-07-05T07:27:04.321786+00:00"},{"alias_kind":"pith_short_16","alias_value":"CP3XNWGUR7V44ZGR","created_at":"2026-07-05T07:27:04.321786+00:00"},{"alias_kind":"pith_short_8","alias_value":"CP3XNWGU","created_at":"2026-07-05T07:27:04.321786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24567","citing_title":"Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CP3XNWGUR7V44ZGRRLG5NWFRGE","json":"https://pith.science/pith/CP3XNWGUR7V44ZGRRLG5NWFRGE.json","graph_json":"https://pith.science/api/pith-number/CP3XNWGUR7V44ZGRRLG5NWFRGE/graph.json","events_json":"https://pith.science/api/pith-number/CP3XNWGUR7V44ZGRRLG5NWFRGE/events.json","paper":"https://pith.science/paper/CP3XNWGU"},"agent_actions":{"view_html":"https://pith.science/pith/CP3XNWGUR7V44ZGRRLG5NWFRGE","download_json":"https://pith.science/pith/CP3XNWGUR7V44ZGRRLG5NWFRGE.json","view_paper":"https://pith.science/paper/CP3XNWGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.02693&json=true","fetch_graph":"https://pith.science/api/pith-number/CP3XNWGUR7V44ZGRRLG5NWFRGE/graph.json","fetch_events":"https://pith.science/api/pith-number/CP3XNWGUR7V44ZGRRLG5NWFRGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CP3XNWGUR7V44ZGRRLG5NWFRGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CP3XNWGUR7V44ZGRRLG5NWFRGE/action/storage_attestation","attest_author":"https://pith.science/pith/CP3XNWGUR7V44ZGRRLG5NWFRGE/action/author_attestation","sign_citation":"https://pith.science/pith/CP3XNWGUR7V44ZGRRLG5NWFRGE/action/citation_signature","submit_replication":"https://pith.science/pith/CP3XNWGUR7V44ZGRRLG5NWFRGE/action/replication_record"}},"created_at":"2026-07-05T07:27:04.321786+00:00","updated_at":"2026-07-05T07:27:04.321786+00:00"}