{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IIVMWOCKNNZHVGDPE7NFP4QBNZ","short_pith_number":"pith:IIVMWOCK","schema_version":"1.0","canonical_sha256":"422acb384a6b727a986f27da57f2016e4266f6b3c87b9d30d69cfefe75c89a46","source":{"kind":"arxiv","id":"2104.00808","version":1},"attestation_state":"computed","paper":{"title":"Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Evgeny Krivosheev, Nicu Sebe, Subhankar Roy, Zhun Zhong","submitted_at":"2021-04-01T23:41:41Z","abstract_excerpt":"In this paper we address multi-target domain adaptation (MTDA), where given one labeled source dataset and multiple unlabeled target datasets that differ in data distributions, the task is to learn a robust predictor for all the target domains. We identify two key aspects that can help to alleviate multiple domain-shifts in the MTDA: feature aggregation and curriculum learning. To this end, we propose Curriculum Graph Co-Teaching (CGCT) that uses a dual classifier head, with one of them being a graph convolutional network (GCN) which aggregates features from similar samples across the domains."},"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":"2104.00808","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T23:41:41Z","cross_cats_sorted":[],"title_canon_sha256":"84e4c4a0de572024c86684c51ca73b8ceeefa411c738a2b3547af9de310b6174","abstract_canon_sha256":"5b41a8044cd79d7d0ff5715fb3435693f91ee33f7d1a3d3a481c3729c1be74a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:36.132985Z","signature_b64":"qrL1F2+Z5/7YPUqHOX/wgfLqBKndYxhrv6ylwRt7MOXHzsLCIY/6/VtPg3WX575HsgxZDzuFTHvJC79fXwe+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"422acb384a6b727a986f27da57f2016e4266f6b3c87b9d30d69cfefe75c89a46","last_reissued_at":"2026-07-05T02:28:36.132526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:36.132526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Evgeny Krivosheev, Nicu Sebe, Subhankar Roy, Zhun Zhong","submitted_at":"2021-04-01T23:41:41Z","abstract_excerpt":"In this paper we address multi-target domain adaptation (MTDA), where given one labeled source dataset and multiple unlabeled target datasets that differ in data distributions, the task is to learn a robust predictor for all the target domains. We identify two key aspects that can help to alleviate multiple domain-shifts in the MTDA: feature aggregation and curriculum learning. To this end, we propose Curriculum Graph Co-Teaching (CGCT) that uses a dual classifier head, with one of them being a graph convolutional network (GCN) which aggregates features from similar samples across the domains."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00808","kind":"arxiv","version":1},"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/2104.00808/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":"2104.00808","created_at":"2026-07-05T02:28:36.132588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.00808v1","created_at":"2026-07-05T02:28:36.132588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00808","created_at":"2026-07-05T02:28:36.132588+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIVMWOCKNNZH","created_at":"2026-07-05T02:28:36.132588+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIVMWOCKNNZHVGDP","created_at":"2026-07-05T02:28:36.132588+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIVMWOCK","created_at":"2026-07-05T02:28:36.132588+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/IIVMWOCKNNZHVGDPE7NFP4QBNZ","json":"https://pith.science/pith/IIVMWOCKNNZHVGDPE7NFP4QBNZ.json","graph_json":"https://pith.science/api/pith-number/IIVMWOCKNNZHVGDPE7NFP4QBNZ/graph.json","events_json":"https://pith.science/api/pith-number/IIVMWOCKNNZHVGDPE7NFP4QBNZ/events.json","paper":"https://pith.science/paper/IIVMWOCK"},"agent_actions":{"view_html":"https://pith.science/pith/IIVMWOCKNNZHVGDPE7NFP4QBNZ","download_json":"https://pith.science/pith/IIVMWOCKNNZHVGDPE7NFP4QBNZ.json","view_paper":"https://pith.science/paper/IIVMWOCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.00808&json=true","fetch_graph":"https://pith.science/api/pith-number/IIVMWOCKNNZHVGDPE7NFP4QBNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IIVMWOCKNNZHVGDPE7NFP4QBNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIVMWOCKNNZHVGDPE7NFP4QBNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIVMWOCKNNZHVGDPE7NFP4QBNZ/action/storage_attestation","attest_author":"https://pith.science/pith/IIVMWOCKNNZHVGDPE7NFP4QBNZ/action/author_attestation","sign_citation":"https://pith.science/pith/IIVMWOCKNNZHVGDPE7NFP4QBNZ/action/citation_signature","submit_replication":"https://pith.science/pith/IIVMWOCKNNZHVGDPE7NFP4QBNZ/action/replication_record"}},"created_at":"2026-07-05T02:28:36.132588+00:00","updated_at":"2026-07-05T02:28:36.132588+00:00"}