{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BYCMEAHP2V5MI7BEQBIAV7OLQU","short_pith_number":"pith:BYCMEAHP","schema_version":"1.0","canonical_sha256":"0e04c200efd57ac47c2480500afdcb8532f26e7a3b0073b284aef8214d1e6bd1","source":{"kind":"arxiv","id":"2103.02193","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Consistency Regularization for Semi-Supervised Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abulikemu Abuduweili, Cheng-zhong Xu, Dejing Dou, Humphrey Shi, Xingjian Li","submitted_at":"2021-03-03T05:46:39Z","abstract_excerpt":"While recent studies on semi-supervised learning have shown remarkable progress in leveraging both labeled and unlabeled data, most of them presume a basic setting of the model is randomly initialized. In this work, we consider semi-supervised learning and transfer learning jointly, leading to a more practical and competitive paradigm that can utilize both powerful pre-trained models from source domain as well as labeled/unlabeled data in the target domain. To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization th"},"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":"2103.02193","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-03T05:46:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c3e54de023adc6f5f75e27ab64cb31703fd7df68f73e5a8c877d54b0fdee3508","abstract_canon_sha256":"a26f5c52fdd55feb79d38399bdccb65ac6600274dce1b3c61574aaaf76a3dc5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:04.002379Z","signature_b64":"/KkmepBv8rzSL73TJlnkLaC5SU9LJReFjzjyCtdDX6XOMaop37Q5hwxanDHM/Fw1cgnk4im/kurAUbeD4RrhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e04c200efd57ac47c2480500afdcb8532f26e7a3b0073b284aef8214d1e6bd1","last_reissued_at":"2026-07-05T03:04:04.001975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:04.001975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Consistency Regularization for Semi-Supervised Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abulikemu Abuduweili, Cheng-zhong Xu, Dejing Dou, Humphrey Shi, Xingjian Li","submitted_at":"2021-03-03T05:46:39Z","abstract_excerpt":"While recent studies on semi-supervised learning have shown remarkable progress in leveraging both labeled and unlabeled data, most of them presume a basic setting of the model is randomly initialized. In this work, we consider semi-supervised learning and transfer learning jointly, leading to a more practical and competitive paradigm that can utilize both powerful pre-trained models from source domain as well as labeled/unlabeled data in the target domain. To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02193","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/2103.02193/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":"2103.02193","created_at":"2026-07-05T03:04:04.002032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.02193v2","created_at":"2026-07-05T03:04:04.002032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02193","created_at":"2026-07-05T03:04:04.002032+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYCMEAHP2V5M","created_at":"2026-07-05T03:04:04.002032+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYCMEAHP2V5MI7BE","created_at":"2026-07-05T03:04:04.002032+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYCMEAHP","created_at":"2026-07-05T03:04:04.002032+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/BYCMEAHP2V5MI7BEQBIAV7OLQU","json":"https://pith.science/pith/BYCMEAHP2V5MI7BEQBIAV7OLQU.json","graph_json":"https://pith.science/api/pith-number/BYCMEAHP2V5MI7BEQBIAV7OLQU/graph.json","events_json":"https://pith.science/api/pith-number/BYCMEAHP2V5MI7BEQBIAV7OLQU/events.json","paper":"https://pith.science/paper/BYCMEAHP"},"agent_actions":{"view_html":"https://pith.science/pith/BYCMEAHP2V5MI7BEQBIAV7OLQU","download_json":"https://pith.science/pith/BYCMEAHP2V5MI7BEQBIAV7OLQU.json","view_paper":"https://pith.science/paper/BYCMEAHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.02193&json=true","fetch_graph":"https://pith.science/api/pith-number/BYCMEAHP2V5MI7BEQBIAV7OLQU/graph.json","fetch_events":"https://pith.science/api/pith-number/BYCMEAHP2V5MI7BEQBIAV7OLQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYCMEAHP2V5MI7BEQBIAV7OLQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYCMEAHP2V5MI7BEQBIAV7OLQU/action/storage_attestation","attest_author":"https://pith.science/pith/BYCMEAHP2V5MI7BEQBIAV7OLQU/action/author_attestation","sign_citation":"https://pith.science/pith/BYCMEAHP2V5MI7BEQBIAV7OLQU/action/citation_signature","submit_replication":"https://pith.science/pith/BYCMEAHP2V5MI7BEQBIAV7OLQU/action/replication_record"}},"created_at":"2026-07-05T03:04:04.002032+00:00","updated_at":"2026-07-05T03:04:04.002032+00:00"}