{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UQCZOCHW632VBHY5LOFXSAQ3C7","short_pith_number":"pith:UQCZOCHW","schema_version":"1.0","canonical_sha256":"a4059708f6f6f5509f1d5b8b79021b17ea324d68c1e0083e5d064581e24b97b2","source":{"kind":"arxiv","id":"2007.12942","version":1},"attestation_state":"computed","paper":{"title":"Gradient Regularized Contrastive Learning for Continual Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Di Qiu, Ni Zhao, Peng Gao, Peng Su, Shixiang Tang, Xiaogang Wang","submitted_at":"2020-07-25T14:30:03Z","abstract_excerpt":"Human beings can quickly adapt to environmental changes by leveraging learning experience. However, the poor ability of adapting to dynamic environments remains a major challenge for AI models. To better understand this issue, we study the problem of continual domain adaptation, where the model is presented with a labeled source domain and a sequence of unlabeled target domains. There are two major obstacles in this problem: domain shifts and catastrophic forgetting. In this work, we propose Gradient Regularized Contrastive Learning to solve the above obstacles. At the core of our method, grad"},"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":"2007.12942","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-25T14:30:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"39ebd176177f655b2ece510320232d8e8d6bb642767445525f4bab670cf3fddf","abstract_canon_sha256":"431ac77d12696e4efb2b03d23f7f8479a93980a16c451cfdb5fe01bf32ac85a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:05.163184Z","signature_b64":"T2k1/1rE+ZLwIJlqB2FZ0H9F+y02em3hF0ih295yW+KN9/EbGhvGjk9MXaME5IdCycafjHDCZmG7va490+tADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4059708f6f6f5509f1d5b8b79021b17ea324d68c1e0083e5d064581e24b97b2","last_reissued_at":"2026-07-05T01:22:05.162766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:05.162766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Regularized Contrastive Learning for Continual Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Di Qiu, Ni Zhao, Peng Gao, Peng Su, Shixiang Tang, Xiaogang Wang","submitted_at":"2020-07-25T14:30:03Z","abstract_excerpt":"Human beings can quickly adapt to environmental changes by leveraging learning experience. However, the poor ability of adapting to dynamic environments remains a major challenge for AI models. To better understand this issue, we study the problem of continual domain adaptation, where the model is presented with a labeled source domain and a sequence of unlabeled target domains. There are two major obstacles in this problem: domain shifts and catastrophic forgetting. In this work, we propose Gradient Regularized Contrastive Learning to solve the above obstacles. At the core of our method, grad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12942","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/2007.12942/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":"2007.12942","created_at":"2026-07-05T01:22:05.162825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.12942v1","created_at":"2026-07-05T01:22:05.162825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12942","created_at":"2026-07-05T01:22:05.162825+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQCZOCHW632V","created_at":"2026-07-05T01:22:05.162825+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQCZOCHW632VBHY5","created_at":"2026-07-05T01:22:05.162825+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQCZOCHW","created_at":"2026-07-05T01:22:05.162825+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/UQCZOCHW632VBHY5LOFXSAQ3C7","json":"https://pith.science/pith/UQCZOCHW632VBHY5LOFXSAQ3C7.json","graph_json":"https://pith.science/api/pith-number/UQCZOCHW632VBHY5LOFXSAQ3C7/graph.json","events_json":"https://pith.science/api/pith-number/UQCZOCHW632VBHY5LOFXSAQ3C7/events.json","paper":"https://pith.science/paper/UQCZOCHW"},"agent_actions":{"view_html":"https://pith.science/pith/UQCZOCHW632VBHY5LOFXSAQ3C7","download_json":"https://pith.science/pith/UQCZOCHW632VBHY5LOFXSAQ3C7.json","view_paper":"https://pith.science/paper/UQCZOCHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.12942&json=true","fetch_graph":"https://pith.science/api/pith-number/UQCZOCHW632VBHY5LOFXSAQ3C7/graph.json","fetch_events":"https://pith.science/api/pith-number/UQCZOCHW632VBHY5LOFXSAQ3C7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQCZOCHW632VBHY5LOFXSAQ3C7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQCZOCHW632VBHY5LOFXSAQ3C7/action/storage_attestation","attest_author":"https://pith.science/pith/UQCZOCHW632VBHY5LOFXSAQ3C7/action/author_attestation","sign_citation":"https://pith.science/pith/UQCZOCHW632VBHY5LOFXSAQ3C7/action/citation_signature","submit_replication":"https://pith.science/pith/UQCZOCHW632VBHY5LOFXSAQ3C7/action/replication_record"}},"created_at":"2026-07-05T01:22:05.162825+00:00","updated_at":"2026-07-05T01:22:05.162825+00:00"}