{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CA3DQJD6FXKS4XQRJQDKGSB75K","short_pith_number":"pith:CA3DQJD6","schema_version":"1.0","canonical_sha256":"103638247e2dd52e5e114c06a3483feab9fd4108c856f2933de8a8d03d0d0612","source":{"kind":"arxiv","id":"2104.13486","version":2},"attestation_state":"computed","paper":{"title":"Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian D. Davison, Youshan Zhang","submitted_at":"2021-04-27T21:35:28Z","abstract_excerpt":"Domain adaptation (DA) mitigates the domain shift problem when transferring knowledge from one annotated domain to another similar but different unlabeled domain. However, existing models often utilize one of the ImageNet models as the backbone without exploring others, and fine-tuning or retraining the backbone ImageNet model is also time-consuming. Moreover, pseudo-labeling has been used to improve the performance in the target domain, while how to generate confident pseudo labels and explicitly align domain distributions has not been well addressed. In this paper, we show how to efficiently"},"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":"2104.13486","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-27T21:35:28Z","cross_cats_sorted":[],"title_canon_sha256":"c0d16dc8b2d4f4515908dc49672d05860924ddf834a46bfd93c02632718770ce","abstract_canon_sha256":"29c59bb0275f7866a956973311bcae2b0e53de279284ced209f9d18235dfa670"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:32.770114Z","signature_b64":"H41qH7llbnC92VpaURghdfOXFkuV/gYS3k8u2Ip1tzNL6te7luCT2ChuSIBEuy9STxuNvCPnMZeXk5QsjsbSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"103638247e2dd52e5e114c06a3483feab9fd4108c856f2933de8a8d03d0d0612","last_reissued_at":"2026-07-05T02:36:32.769558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:32.769558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian D. Davison, Youshan Zhang","submitted_at":"2021-04-27T21:35:28Z","abstract_excerpt":"Domain adaptation (DA) mitigates the domain shift problem when transferring knowledge from one annotated domain to another similar but different unlabeled domain. However, existing models often utilize one of the ImageNet models as the backbone without exploring others, and fine-tuning or retraining the backbone ImageNet model is also time-consuming. Moreover, pseudo-labeling has been used to improve the performance in the target domain, while how to generate confident pseudo labels and explicitly align domain distributions has not been well addressed. In this paper, we show how to efficiently"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13486","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/2104.13486/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":"2104.13486","created_at":"2026-07-05T02:36:32.769619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.13486v2","created_at":"2026-07-05T02:36:32.769619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13486","created_at":"2026-07-05T02:36:32.769619+00:00"},{"alias_kind":"pith_short_12","alias_value":"CA3DQJD6FXKS","created_at":"2026-07-05T02:36:32.769619+00:00"},{"alias_kind":"pith_short_16","alias_value":"CA3DQJD6FXKS4XQR","created_at":"2026-07-05T02:36:32.769619+00:00"},{"alias_kind":"pith_short_8","alias_value":"CA3DQJD6","created_at":"2026-07-05T02:36:32.769619+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/CA3DQJD6FXKS4XQRJQDKGSB75K","json":"https://pith.science/pith/CA3DQJD6FXKS4XQRJQDKGSB75K.json","graph_json":"https://pith.science/api/pith-number/CA3DQJD6FXKS4XQRJQDKGSB75K/graph.json","events_json":"https://pith.science/api/pith-number/CA3DQJD6FXKS4XQRJQDKGSB75K/events.json","paper":"https://pith.science/paper/CA3DQJD6"},"agent_actions":{"view_html":"https://pith.science/pith/CA3DQJD6FXKS4XQRJQDKGSB75K","download_json":"https://pith.science/pith/CA3DQJD6FXKS4XQRJQDKGSB75K.json","view_paper":"https://pith.science/paper/CA3DQJD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.13486&json=true","fetch_graph":"https://pith.science/api/pith-number/CA3DQJD6FXKS4XQRJQDKGSB75K/graph.json","fetch_events":"https://pith.science/api/pith-number/CA3DQJD6FXKS4XQRJQDKGSB75K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CA3DQJD6FXKS4XQRJQDKGSB75K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CA3DQJD6FXKS4XQRJQDKGSB75K/action/storage_attestation","attest_author":"https://pith.science/pith/CA3DQJD6FXKS4XQRJQDKGSB75K/action/author_attestation","sign_citation":"https://pith.science/pith/CA3DQJD6FXKS4XQRJQDKGSB75K/action/citation_signature","submit_replication":"https://pith.science/pith/CA3DQJD6FXKS4XQRJQDKGSB75K/action/replication_record"}},"created_at":"2026-07-05T02:36:32.769619+00:00","updated_at":"2026-07-05T02:36:32.769619+00:00"}