{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MLIH5VMISPZWBLKDJXQZEKOB2K","short_pith_number":"pith:MLIH5VMI","schema_version":"1.0","canonical_sha256":"62d07ed58893f360ad434de19229c1d2a0ba057cad1f1dbb65bfe3f87ae439d0","source":{"kind":"arxiv","id":"2307.03449","version":2},"attestation_state":"computed","paper":{"title":"Universal Semi-supervised Model Adaptation via Collaborative Consistency Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanbin Li, Shuguang Cui, Xiaoguang Han, Yipeng Qin, Yushuang Wu, Zizheng Yan","submitted_at":"2023-07-07T08:19:40Z","abstract_excerpt":"In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained source model, ii) allows the source and target domain to have different label sets, i.e., they share a common label set and hold their own private label set, and iii) requires only a few labeled samples in each class of the target domain. To address USMA, we propose a collaborative consistency training framework that regularizes the prediction consistency between two models, i.e., a pre-trained source model and its vari"},"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":"2307.03449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-07T08:19:40Z","cross_cats_sorted":[],"title_canon_sha256":"ba5b8f949f813f57c6192f9531e08c9de58ef55965020bd7b368a22c75dc086c","abstract_canon_sha256":"e3afc6940a65c21637c37f3a4f5f2eaeced4670d10cb81d29089d297abdc172c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:42.500125Z","signature_b64":"qsDcVdekYWmaMh2HmVUIsN4X24abzxTNKk9IfZvBmNO5F7ckdFv97FVQzTWhPZNqJB+RSMLvLVTwGHBo6Fd8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62d07ed58893f360ad434de19229c1d2a0ba057cad1f1dbb65bfe3f87ae439d0","last_reissued_at":"2026-07-05T07:08:42.499582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:42.499582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Semi-supervised Model Adaptation via Collaborative Consistency Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanbin Li, Shuguang Cui, Xiaoguang Han, Yipeng Qin, Yushuang Wu, Zizheng Yan","submitted_at":"2023-07-07T08:19:40Z","abstract_excerpt":"In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained source model, ii) allows the source and target domain to have different label sets, i.e., they share a common label set and hold their own private label set, and iii) requires only a few labeled samples in each class of the target domain. To address USMA, we propose a collaborative consistency training framework that regularizes the prediction consistency between two models, i.e., a pre-trained source model and its vari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03449","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/2307.03449/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":"2307.03449","created_at":"2026-07-05T07:08:42.499640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03449v2","created_at":"2026-07-05T07:08:42.499640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03449","created_at":"2026-07-05T07:08:42.499640+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLIH5VMISPZW","created_at":"2026-07-05T07:08:42.499640+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLIH5VMISPZWBLKD","created_at":"2026-07-05T07:08:42.499640+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLIH5VMI","created_at":"2026-07-05T07:08:42.499640+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/MLIH5VMISPZWBLKDJXQZEKOB2K","json":"https://pith.science/pith/MLIH5VMISPZWBLKDJXQZEKOB2K.json","graph_json":"https://pith.science/api/pith-number/MLIH5VMISPZWBLKDJXQZEKOB2K/graph.json","events_json":"https://pith.science/api/pith-number/MLIH5VMISPZWBLKDJXQZEKOB2K/events.json","paper":"https://pith.science/paper/MLIH5VMI"},"agent_actions":{"view_html":"https://pith.science/pith/MLIH5VMISPZWBLKDJXQZEKOB2K","download_json":"https://pith.science/pith/MLIH5VMISPZWBLKDJXQZEKOB2K.json","view_paper":"https://pith.science/paper/MLIH5VMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03449&json=true","fetch_graph":"https://pith.science/api/pith-number/MLIH5VMISPZWBLKDJXQZEKOB2K/graph.json","fetch_events":"https://pith.science/api/pith-number/MLIH5VMISPZWBLKDJXQZEKOB2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLIH5VMISPZWBLKDJXQZEKOB2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLIH5VMISPZWBLKDJXQZEKOB2K/action/storage_attestation","attest_author":"https://pith.science/pith/MLIH5VMISPZWBLKDJXQZEKOB2K/action/author_attestation","sign_citation":"https://pith.science/pith/MLIH5VMISPZWBLKDJXQZEKOB2K/action/citation_signature","submit_replication":"https://pith.science/pith/MLIH5VMISPZWBLKDJXQZEKOB2K/action/replication_record"}},"created_at":"2026-07-05T07:08:42.499640+00:00","updated_at":"2026-07-05T07:08:42.499640+00:00"}